Machine learning

Subterms

    More stories

    • 163 Shares129 Views

      in Data Management & Statistics

      Busy GPUs: Sampling and pipelining method speeds up deep learning on large graphs

      by

      Graphs, a potentially extensive web of nodes connected by edges, can be used to express and interrogate relationships between data, like social connections, financial transactions, traffic, energy grids, and molecular interactions. As researchers collect more data and build out these graphical pictures, researchers will need faster and more efficient methods, as well as more computational power, to conduct deep learning on them, in the way of graph neural networks (GNN).  

      Now, a new method, called SALIENT (SAmpling, sLIcing, and data movemeNT), developed by researchers at MIT and IBM Research, improves the training and inference performance by addressing three key bottlenecks in computation. This dramatically cuts down on the runtime of GNNs on large datasets, which, for example, contain on the scale of 100 million nodes and 1 billion edges. Further, the team found that the technique scales well when computational power is added from one to 16 graphical processing units (GPUs). The work was presented at the Fifth Conference on Machine Learning and Systems.

      “We started to look at the challenges current systems experienced when scaling state-of-the-art machine learning techniques for graphs to really big datasets. It turned out there was a lot of work to be done, because a lot of the existing systems were achieving good performance primarily on smaller datasets that fit into GPU memory,” says Tim Kaler, the lead author and a postdoc in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL).

      By vast datasets, experts mean scales like the entire Bitcoin network, where certain patterns and data relationships could spell out trends or foul play. “There are nearly a billion Bitcoin transactions on the blockchain, and if we want to identify illicit activities inside such a joint network, then we are facing a graph of such a scale,” says co-author Jie Chen, senior research scientist and manager of IBM Research and the MIT-IBM Watson AI Lab. “We want to build a system that is able to handle that kind of graph and allows processing to be as efficient as possible, because every day we want to keep up with the pace of the new data that are generated.”

      Kaler and Chen’s co-authors include Nickolas Stathas MEng ’21 of Jump Trading, who developed SALIENT as part of his graduate work; former MIT-IBM Watson AI Lab intern and MIT graduate student Anne Ouyang; MIT CSAIL postdoc Alexandros-Stavros Iliopoulos; MIT CSAIL Research Scientist Tao B. Schardl; and Charles E. Leiserson, the Edwin Sibley Webster Professor of Electrical Engineering at MIT and a researcher with the MIT-IBM Watson AI Lab.     

      For this problem, the team took a systems-oriented approach in developing their method: SALIENT, says Kaler. To do this, the researchers implemented what they saw as important, basic optimizations of components that fit into existing machine-learning frameworks, such as PyTorch Geometric and the deep graph library (DGL), which are interfaces for building a machine-learning model. Stathas says the process is like swapping out engines to build a faster car. Their method was designed to fit into existing GNN architectures, so that domain experts could easily apply this work to their specified fields to expedite model training and tease out insights during inference faster. The trick, the team determined, was to keep all of the hardware (CPUs, data links, and GPUs) busy at all times: while the CPU samples the graph and prepares mini-batches of data that will then be transferred through the data link, the more critical GPU is working to train the machine-learning model or conduct inference. 

      The researchers began by analyzing the performance of a commonly used machine-learning library for GNNs (PyTorch Geometric), which showed a startlingly low utilization of available GPU resources. Applying simple optimizations, the researchers improved GPU utilization from 10 to 30 percent, resulting in a 1.4 to two times performance improvement relative to public benchmark codes. This fast baseline code could execute one complete pass over a large training dataset through the algorithm (an epoch) in 50.4 seconds.                          

      Seeking further performance improvements, the researchers set out to examine the bottlenecks that occur at the beginning of the data pipeline: the algorithms for graph sampling and mini-batch preparation. Unlike other neural networks, GNNs perform a neighborhood aggregation operation, which computes information about a node using information present in other nearby nodes in the graph — for example, in a social network graph, information from friends of friends of a user. As the number of layers in the GNN increase, the number of nodes the network has to reach out to for information can explode, exceeding the limits of a computer. Neighborhood sampling algorithms help by selecting a smaller random subset of nodes to gather; however, the researchers found that current implementations of this were too slow to keep up with the processing speed of modern GPUs. In response, they identified a mix of data structures, algorithmic optimizations, and so forth that improved sampling speed, ultimately improving the sampling operation alone by about three times, taking the per-epoch runtime from 50.4 to 34.6 seconds. They also found that sampling, at an appropriate rate, can be done during inference, improving overall energy efficiency and performance, a point that had been overlooked in the literature, the team notes.      

      In previous systems, this sampling step was a multi-process approach, creating extra data and unnecessary data movement between the processes. The researchers made their SALIENT method more nimble by creating a single process with lightweight threads that kept the data on the CPU in shared memory. Further, SALIENT takes advantage of a cache of modern processors, says Stathas, parallelizing feature slicing, which extracts relevant information from nodes of interest and their surrounding neighbors and edges, within the shared memory of the CPU core cache. This again reduced the overall per-epoch runtime from 34.6 to 27.8 seconds.

      The last bottleneck the researchers addressed was to pipeline mini-batch data transfers between the CPU and GPU using a prefetching step, which would prepare data just before it’s needed. The team calculated that this would maximize bandwidth usage in the data link and bring the method up to perfect utilization; however, they only saw around 90 percent. They identified and fixed a performance bug in a popular PyTorch library that caused unnecessary round-trip communications between the CPU and GPU. With this bug fixed, the team achieved a 16.5 second per-epoch runtime with SALIENT.

      “Our work showed, I think, that the devil is in the details,” says Kaler. “When you pay close attention to the details that impact performance when training a graph neural network, you can resolve a huge number of performance issues. With our solutions, we ended up being completely bottlenecked by GPU computation, which is the ideal goal of such a system.”

      SALIENT’s speed was evaluated on three standard datasets ogbn-arxiv, ogbn-products, and ogbn-papers100M, as well as in multi-machine settings, with different levels of fanout (amount of data that the CPU would prepare for the GPU), and across several architectures, including the most recent state-of-the-art one, GraphSAGE-RI. In each setting, SALIENT outperformed PyTorch Geometric, most notably on the large ogbn-papers100M dataset, containing 100 million nodes and over a billion edges Here, it was three times faster, running on one GPU, than the optimized baseline that was originally created for this work; with 16 GPUs, SALIENT was an additional eight times faster. 

      While other systems had slightly different hardware and experimental setups, so it wasn’t always a direct comparison, SALIENT still outperformed them. Among systems that achieved similar accuracy, representative performance numbers include 99 seconds using one GPU and 32 CPUs, and 13 seconds using 1,536 CPUs. In contrast, SALIENT’s runtime using one GPU and 20 CPUs was 16.5 seconds and was just two seconds with 16 GPUs and 320 CPUs. “If you look at the bottom-line numbers that prior work reports, our 16 GPU runtime (two seconds) is an order of magnitude faster than other numbers that have been reported previously on this dataset,” says Kaler. The researchers attributed their performance improvements, in part, to their approach of optimizing their code for a single machine before moving to the distributed setting. Stathas says that the lesson here is that for your money, “it makes more sense to use the hardware you have efficiently, and to its extreme, before you start scaling up to multiple computers,” which can provide significant savings on cost and carbon emissions that can come with model training.

      This new capacity will now allow researchers to tackle and dig deeper into bigger and bigger graphs. For example, the Bitcoin network that was mentioned earlier contained 100,000 nodes; the SALIENT system can capably handle a graph 1,000 times (or three orders of magnitude) larger.

      “In the future, we would be looking at not just running this graph neural network training system on the existing algorithms that we implemented for classifying or predicting the properties of each node, but we also want to do more in-depth tasks, such as identifying common patterns in a graph (subgraph patterns), [which] may be actually interesting for indicating financial crimes,” says Chen. “We also want to identify nodes in a graph that are similar in a sense that they possibly would be corresponding to the same bad actor in a financial crime. These tasks would require developing additional algorithms, and possibly also neural network architectures.”

      This research was supported by the MIT-IBM Watson AI Lab and in part by the U.S. Air Force Research Laboratory and the U.S. Air Force Artificial Intelligence Accelerator. More

    • 88 Shares149 Views

      in Data Management & Statistics

      Breaking the scaling limits of analog computing

      by

      As machine-learning models become larger and more complex, they require faster and more energy-efficient hardware to perform computations. Conventional digital computers are struggling to keep up.

      An analog optical neural network could perform the same tasks as a digital one, such as image classification or speech recognition, but because computations are performed using light instead of electrical signals, optical neural networks can run many times faster while consuming less energy.

      However, these analog devices are prone to hardware errors that can make computations less precise. Microscopic imperfections in hardware components are one cause of these errors. In an optical neural network that has many connected components, errors can quickly accumulate.

      Even with error-correction techniques, due to fundamental properties of the devices that make up an optical neural network, some amount of error is unavoidable. A network that is large enough to be implemented in the real world would be far too imprecise to be effective.

      MIT researchers have overcome this hurdle and found a way to effectively scale an optical neural network. By adding a tiny hardware component to the optical switches that form the network’s architecture, they can reduce even the uncorrectable errors that would otherwise accumulate in the device.

      Their work could enable a super-fast, energy-efficient, analog neural network that can function with the same accuracy as a digital one. With this technique, as an optical circuit becomes larger, the amount of error in its computations actually decreases.  

      “This is remarkable, as it runs counter to the intuition of analog systems, where larger circuits are supposed to have higher errors, so that errors set a limit on scalability. This present paper allows us to address the scalability question of these systems with an unambiguous ‘yes,’” says lead author Ryan Hamerly, a visiting scientist in the MIT Research Laboratory for Electronics (RLE) and Quantum Photonics Laboratory and senior scientist at NTT Research.

      Hamerly’s co-authors are graduate student Saumil Bandyopadhyay and senior author Dirk Englund, an associate professor in the MIT Department of Electrical Engineering and Computer Science (EECS), leader of the Quantum Photonics Laboratory, and member of the RLE. The research is published today in Nature Communications.

      Multiplying with light

      An optical neural network is composed of many connected components that function like reprogrammable, tunable mirrors. These tunable mirrors are called Mach-Zehnder Inferometers (MZI). Neural network data are encoded into light, which is fired into the optical neural network from a laser.

      A typical MZI contains two mirrors and two beam splitters. Light enters the top of an MZI, where it is split into two parts which interfere with each other before being recombined by the second beam splitter and then reflected out the bottom to the next MZI in the array. Researchers can leverage the interference of these optical signals to perform complex linear algebra operations, known as matrix multiplication, which is how neural networks process data.

      But errors that can occur in each MZI quickly accumulate as light moves from one device to the next. One can avoid some errors by identifying them in advance and tuning the MZIs so earlier errors are cancelled out by later devices in the array.

      “It is a very simple algorithm if you know what the errors are. But these errors are notoriously difficult to ascertain because you only have access to the inputs and outputs of your chip,” says Hamerly. “This motivated us to look at whether it is possible to create calibration-free error correction.”

      Hamerly and his collaborators previously demonstrated a mathematical technique that went a step further. They could successfully infer the errors and correctly tune the MZIs accordingly, but even this didn’t remove all the error.

      Due to the fundamental nature of an MZI, there are instances where it is impossible to tune a device so all light flows out the bottom port to the next MZI. If the device loses a fraction of light at each step and the array is very large, by the end there will only be a tiny bit of power left.

      “Even with error correction, there is a fundamental limit to how good a chip can be. MZIs are physically unable to realize certain settings they need to be configured to,” he says.

      So, the team developed a new type of MZI. The researchers added an additional beam splitter to the end of the device, calling it a 3-MZI because it has three beam splitters instead of two. Due to the way this additional beam splitter mixes the light, it becomes much easier for an MZI to reach the setting it needs to send all light from out through its bottom port.

      Importantly, the additional beam splitter is only a few micrometers in size and is a passive component, so it doesn’t require any extra wiring. Adding additional beam splitters doesn’t significantly change the size of the chip.

      Bigger chip, fewer errors

      When the researchers conducted simulations to test their architecture, they found that it can eliminate much of the uncorrectable error that hampers accuracy. And as the optical neural network becomes larger, the amount of error in the device actually drops — the opposite of what happens in a device with standard MZIs.

      Using 3-MZIs, they could potentially create a device big enough for commercial uses with error that has been reduced by a factor of 20, Hamerly says.

      The researchers also developed a variant of the MZI design specifically for correlated errors. These occur due to manufacturing imperfections — if the thickness of a chip is slightly wrong, the MZIs may all be off by about the same amount, so the errors are all about the same. They found a way to change the configuration of an MZI to make it robust to these types of errors. This technique also increased the bandwidth of the optical neural network so it can run three times faster.

      Now that they have showcased these techniques using simulations, Hamerly and his collaborators plan to test these approaches on physical hardware and continue driving toward an optical neural network they can effectively deploy in the real world.

      This research is funded, in part, by a National Science Foundation graduate research fellowship and the U.S. Air Force Office of Scientific Research. More

    • 75 Shares159 Views

      in Data Management & Statistics

      A far-sighted approach to machine learning

      by

      Picture two teams squaring off on a football field. The players can cooperate to achieve an objective, and compete against other players with conflicting interests. That’s how the game works.

      Creating artificial intelligence agents that can learn to compete and cooperate as effectively as humans remains a thorny problem. A key challenge is enabling AI agents to anticipate future behaviors of other agents when they are all learning simultaneously.

      Because of the complexity of this problem, current approaches tend to be myopic; the agents can only guess the next few moves of their teammates or competitors, which leads to poor performance in the long run. 

      Researchers from MIT, the MIT-IBM Watson AI Lab, and elsewhere have developed a new approach that gives AI agents a farsighted perspective. Their machine-learning framework enables cooperative or competitive AI agents to consider what other agents will do as time approaches infinity, not just over a few next steps. The agents then adapt their behaviors accordingly to influence other agents’ future behaviors and arrive at an optimal, long-term solution.

      This framework could be used by a group of autonomous drones working together to find a lost hiker in a thick forest, or by self-driving cars that strive to keep passengers safe by anticipating future moves of other vehicles driving on a busy highway.

      “When AI agents are cooperating or competing, what matters most is when their behaviors converge at some point in the future. There are a lot of transient behaviors along the way that don’t matter very much in the long run. Reaching this converged behavior is what we really care about, and we now have a mathematical way to enable that,” says Dong-Ki Kim, a graduate student in the MIT Laboratory for Information and Decision Systems (LIDS) and lead author of a paper describing this framework.

      The senior author is Jonathan P. How, the Richard C. Maclaurin Professor of Aeronautics and Astronautics and a member of the MIT-IBM Watson AI Lab. Co-authors include others at the MIT-IBM Watson AI Lab, IBM Research, Mila-Quebec Artificial Intelligence Institute, and Oxford University. The research will be presented at the Conference on Neural Information Processing Systems.

      Play video

      In this demo video, the red robot, which has been trained using the researchers’ machine-learning system, is able to defeat the green robot by learning more effective behaviors that take advantage of the constantly changing strategy of its opponent.

      More agents, more problems

      The researchers focused on a problem known as multiagent reinforcement learning. Reinforcement learning is a form of machine learning in which an AI agent learns by trial and error. Researchers give the agent a reward for “good” behaviors that help it achieve a goal. The agent adapts its behavior to maximize that reward until it eventually becomes an expert at a task.

      But when many cooperative or competing agents are simultaneously learning, things become increasingly complex. As agents consider more future steps of their fellow agents, and how their own behavior influences others, the problem soon requires far too much computational power to solve efficiently. This is why other approaches only focus on the short term.

      “The AIs really want to think about the end of the game, but they don’t know when the game will end. They need to think about how to keep adapting their behavior into infinity so they can win at some far time in the future. Our paper essentially proposes a new objective that enables an AI to think about infinity,” says Kim.

      But since it is impossible to plug infinity into an algorithm, the researchers designed their system so agents focus on a future point where their behavior will converge with that of other agents, known as equilibrium. An equilibrium point determines the long-term performance of agents, and multiple equilibria can exist in a multiagent scenario. Therefore, an effective agent actively influences the future behaviors of other agents in such a way that they reach a desirable equilibrium from the agent’s perspective. If all agents influence each other, they converge to a general concept that the researchers call an “active equilibrium.”

      The machine-learning framework they developed, known as FURTHER (which stands for FUlly Reinforcing acTive influence witH averagE Reward), enables agents to learn how to adapt their behaviors as they interact with other agents to achieve this active equilibrium.

      FURTHER does this using two machine-learning modules. The first, an inference module, enables an agent to guess the future behaviors of other agents and the learning algorithms they use, based solely on their prior actions.

      This information is fed into the reinforcement learning module, which the agent uses to adapt its behavior and influence other agents in a way that maximizes its reward.

      “The challenge was thinking about infinity. We had to use a lot of different mathematical tools to enable that, and make some assumptions to get it to work in practice,” Kim says.

      Winning in the long run

      They tested their approach against other multiagent reinforcement learning frameworks in several different scenarios, including a pair of robots fighting sumo-style and a battle pitting two 25-agent teams against one another. In both instances, the AI agents using FURTHER won the games more often.

      Since their approach is decentralized, which means the agents learn to win the games independently, it is also more scalable than other methods that require a central computer to control the agents, Kim explains.

      The researchers used games to test their approach, but FURTHER could be used to tackle any kind of multiagent problem. For instance, it could be applied by economists seeking to develop sound policy in situations where many interacting entitles have behaviors and interests that change over time.

      Economics is one application Kim is particularly excited about studying. He also wants to dig deeper into the concept of an active equilibrium and continue enhancing the FURTHER framework.

      This research is funded, in part, by the MIT-IBM Watson AI Lab. More

    • 50 Shares199 Views

      in Data Management & Statistics

      Deep learning with light

      by

      Ask a smart home device for the weather forecast, and it takes several seconds for the device to respond. One reason this latency occurs is because connected devices don’t have enough memory or power to store and run the enormous machine-learning models needed for the device to understand what a user is asking of it. The model is stored in a data center that may be hundreds of miles away, where the answer is computed and sent to the device.

      MIT researchers have created a new method for computing directly on these devices, which drastically reduces this latency. Their technique shifts the memory-intensive steps of running a machine-learning model to a central server where components of the model are encoded onto light waves.

      The waves are transmitted to a connected device using fiber optics, which enables tons of data to be sent lightning-fast through a network. The receiver then employs a simple optical device that rapidly performs computations using the parts of a model carried by those light waves.

      This technique leads to more than a hundredfold improvement in energy efficiency when compared to other methods. It could also improve security, since a user’s data do not need to be transferred to a central location for computation.

      This method could enable a self-driving car to make decisions in real-time while using just a tiny percentage of the energy currently required by power-hungry computers. It could also allow a user to have a latency-free conversation with their smart home device, be used for live video processing over cellular networks, or even enable high-speed image classification on a spacecraft millions of miles from Earth.

      “Every time you want to run a neural network, you have to run the program, and how fast you can run the program depends on how fast you can pipe the program in from memory. Our pipe is massive — it corresponds to sending a full feature-length movie over the internet every millisecond or so. That is how fast data comes into our system. And it can compute as fast as that,” says senior author Dirk Englund, an associate professor in the Department of Electrical Engineering and Computer Science (EECS) and member of the MIT Research Laboratory of Electronics.

      Joining Englund on the paper is lead author and EECS grad student Alexander Sludds; EECS grad student Saumil Bandyopadhyay, Research Scientist Ryan Hamerly, as well as others from MIT, the MIT Lincoln Laboratory, and Nokia Corporation. The research is published today in Science.

      Lightening the load

      Neural networks are machine-learning models that use layers of connected nodes, or neurons, to recognize patterns in datasets and perform tasks, like classifying images or recognizing speech. But these models can contain billions of weight parameters, which are numeric values that transform input data as they are processed. These weights must be stored in memory. At the same time, the data transformation process involves billions of algebraic computations, which require a great deal of power to perform.

      The process of fetching data (the weights of the neural network, in this case) from memory and moving them to the parts of a computer that do the actual computation is one of the biggest limiting factors to speed and energy efficiency, says Sludds.

      “So our thought was, why don’t we take all that heavy lifting — the process of fetching billions of weights from memory — move it away from the edge device and put it someplace where we have abundant access to power and memory, which gives us the ability to fetch those weights quickly?” he says.

      The neural network architecture they developed, Netcast, involves storing weights in a central server that is connected to a novel piece of hardware called a smart transceiver. This smart transceiver, a thumb-sized chip that can receive and transmit data, uses technology known as silicon photonics to fetch trillions of weights from memory each second.

      It receives weights as electrical signals and imprints them onto light waves. Since the weight data are encoded as bits (1s and 0s) the transceiver converts them by switching lasers; a laser is turned on for a 1 and off for a 0. It combines these light waves and then periodically transfers them through a fiber optic network so a client device doesn’t need to query the server to receive them.

      “Optics is great because there are many ways to carry data within optics. For instance, you can put data on different colors of light, and that enables a much higher data throughput and greater bandwidth than with electronics,” explains Bandyopadhyay.

      Trillions per second

      Once the light waves arrive at the client device, a simple optical component known as a broadband “Mach-Zehnder” modulator uses them to perform super-fast, analog computation. This involves encoding input data from the device, such as sensor information, onto the weights. Then it sends each individual wavelength to a receiver that detects the light and measures the result of the computation.

      The researchers devised a way to use this modulator to do trillions of multiplications per second, which vastly increases the speed of computation on the device while using only a tiny amount of power.   

      “In order to make something faster, you need to make it more energy efficient. But there is a trade-off. We’ve built a system that can operate with about a milliwatt of power but still do trillions of multiplications per second. In terms of both speed and energy efficiency, that is a gain of orders of magnitude,” Sludds says.

      They tested this architecture by sending weights over an 86-kilometer fiber that connects their lab to MIT Lincoln Laboratory. Netcast enabled machine-learning with high accuracy — 98.7 percent for image classification and 98.8 percent for digit recognition — at rapid speeds.

      “We had to do some calibration, but I was surprised by how little work we had to do to achieve such high accuracy out of the box. We were able to get commercially relevant accuracy,” adds Hamerly.

      Moving forward, the researchers want to iterate on the smart transceiver chip to achieve even better performance. They also want to miniaturize the receiver, which is currently the size of a shoe box, down to the size of a single chip so it could fit onto a smart device like a cell phone.

      “Using photonics and light as a platform for computing is a really exciting area of research with potentially huge implications on the speed and efficiency of our information technology landscape,” says Euan Allen, a Royal Academy of Engineering Research Fellow at the University of Bath, who was not involved with this work. “The work of Sludds et al. is an exciting step toward seeing real-world implementations of such devices, introducing a new and practical edge-computing scheme whilst also exploring some of the fundamental limitations of computation at very low (single-photon) light levels.”

      The research is funded, in part, by NTT Research, the National Science Foundation, the Air Force Office of Scientific Research, the Air Force Research Laboratory, and the Army Research Office. More

    • 50 Shares179 Views

      in Data Management & Statistics

      Learning on the edge

      by

      Microcontrollers, miniature computers that can run simple commands, are the basis for billions of connected devices, from internet-of-things (IoT) devices to sensors in automobiles. But cheap, low-power microcontrollers have extremely limited memory and no operating system, making it challenging to train artificial intelligence models on “edge devices” that work independently from central computing resources.

      Training a machine-learning model on an intelligent edge device allows it to adapt to new data and make better predictions. For instance, training a model on a smart keyboard could enable the keyboard to continually learn from the user’s writing. However, the training process requires so much memory that it is typically done using powerful computers at a data center, before the model is deployed on a device. This is more costly and raises privacy issues since user data must be sent to a central server.

      To address this problem, researchers at MIT and the MIT-IBM Watson AI Lab developed a new technique that enables on-device training using less than a quarter of a megabyte of memory. Other training solutions designed for connected devices can use more than 500 megabytes of memory, greatly exceeding the 256-kilobyte capacity of most microcontrollers (there are 1,024 kilobytes in one megabyte).

      The intelligent algorithms and framework the researchers developed reduce the amount of computation required to train a model, which makes the process faster and more memory efficient. Their technique can be used to train a machine-learning model on a microcontroller in a matter of minutes.

      This technique also preserves privacy by keeping data on the device, which could be especially beneficial when data are sensitive, such as in medical applications. It also could enable customization of a model based on the needs of users. Moreover, the framework preserves or improves the accuracy of the model when compared to other training approaches.

      “Our study enables IoT devices to not only perform inference but also continuously update the AI models to newly collected data, paving the way for lifelong on-device learning. The low resource utilization makes deep learning more accessible and can have a broader reach, especially for low-power edge devices,” says Song Han, an associate professor in the Department of Electrical Engineering and Computer Science (EECS), a member of the MIT-IBM Watson AI Lab, and senior author of the paper describing this innovation.

      Joining Han on the paper are co-lead authors and EECS PhD students Ji Lin and Ligeng Zhu, as well as MIT postdocs Wei-Ming Chen and Wei-Chen Wang, and Chuang Gan, a principal research staff member at the MIT-IBM Watson AI Lab. The research will be presented at the Conference on Neural Information Processing Systems.

      Han and his team previously addressed the memory and computational bottlenecks that exist when trying to run machine-learning models on tiny edge devices, as part of their TinyML initiative.

      Lightweight training

      A common type of machine-learning model is known as a neural network. Loosely based on the human brain, these models contain layers of interconnected nodes, or neurons, that process data to complete a task, such as recognizing people in photos. The model must be trained first, which involves showing it millions of examples so it can learn the task. As it learns, the model increases or decreases the strength of the connections between neurons, which are known as weights.

      The model may undergo hundreds of updates as it learns, and the intermediate activations must be stored during each round. In a neural network, activation is the middle layer’s intermediate results. Because there may be millions of weights and activations, training a model requires much more memory than running a pre-trained model, Han explains.

      Han and his collaborators employed two algorithmic solutions to make the training process more efficient and less memory-intensive. The first, known as sparse update, uses an algorithm that identifies the most important weights to update at each round of training. The algorithm starts freezing the weights one at a time until it sees the accuracy dip to a set threshold, then it stops. The remaining weights are updated, while the activations corresponding to the frozen weights don’t need to be stored in memory.

      “Updating the whole model is very expensive because there are a lot of activations, so people tend to update only the last layer, but as you can imagine, this hurts the accuracy. For our method, we selectively update those important weights and make sure the accuracy is fully preserved,” Han says.

      Their second solution involves quantized training and simplifying the weights, which are typically 32 bits. An algorithm rounds the weights so they are only eight bits, through a process known as quantization, which cuts the amount of memory for both training and inference. Inference is the process of applying a model to a dataset and generating a prediction. Then the algorithm applies a technique called quantization-aware scaling (QAS), which acts like a multiplier to adjust the ratio between weight and gradient, to avoid any drop in accuracy that may come from quantized training.

      The researchers developed a system, called a tiny training engine, that can run these algorithmic innovations on a simple microcontroller that lacks an operating system. This system changes the order of steps in the training process so more work is completed in the compilation stage, before the model is deployed on the edge device.

      “We push a lot of the computation, such as auto-differentiation and graph optimization, to compile time. We also aggressively prune the redundant operators to support sparse updates. Once at runtime, we have much less workload to do on the device,” Han explains.

      A successful speedup

      Their optimization only required 157 kilobytes of memory to train a machine-learning model on a microcontroller, whereas other techniques designed for lightweight training would still need between 300 and 600 megabytes.

      They tested their framework by training a computer vision model to detect people in images. After only 10 minutes of training, it learned to complete the task successfully. Their method was able to train a model more than 20 times faster than other approaches.

      Now that they have demonstrated the success of these techniques for computer vision models, the researchers want to apply them to language models and different types of data, such as time-series data. At the same time, they want to use what they’ve learned to shrink the size of larger models without sacrificing accuracy, which could help reduce the carbon footprint of training large-scale machine-learning models.

      “AI model adaptation/training on a device, especially on embedded controllers, is an open challenge. This research from MIT has not only successfully demonstrated the capabilities, but also opened up new possibilities for privacy-preserving device personalization in real-time,” says Nilesh Jain, a principal engineer at Intel who was not involved with this work. “Innovations in the publication have broader applicability and will ignite new systems-algorithm co-design research.”

      “On-device learning is the next major advance we are working toward for the connected intelligent edge. Professor Song Han’s group has shown great progress in demonstrating the effectiveness of edge devices for training,” adds Jilei Hou, vice president and head of AI research at Qualcomm. “Qualcomm has awarded his team an Innovation Fellowship for further innovation and advancement in this area.”

      This work is funded by the National Science Foundation, the MIT-IBM Watson AI Lab, the MIT AI Hardware Program, Amazon, Intel, Qualcomm, Ford Motor Company, and Google. More

    • 100 Shares119 Views

      in Data Management & Statistics

      Neurodegenerative disease can progress in newly identified patterns

      by

      Neurodegenerative diseases — like amyotrophic lateral sclerosis (ALS, or Lou Gehrig’s disease), Alzheimer’s, and Parkinson’s — are complicated, chronic ailments that can present with a variety of symptoms, worsen at different rates, and have many underlying genetic and environmental causes, some of which are unknown. ALS, in particular, affects voluntary muscle movement and is always fatal, but while most people survive for only a few years after diagnosis, others live with the disease for decades. Manifestations of ALS can also vary significantly; often slower disease development correlates with onset in the limbs and affecting fine motor skills, while the more serious, bulbar ALS impacts swallowing, speaking, breathing, and mobility. Therefore, understanding the progression of diseases like ALS is critical to enrollment in clinical trials, analysis of potential interventions, and discovery of root causes.

      However, assessing disease evolution is far from straightforward. Current clinical studies typically assume that health declines on a downward linear trajectory on a symptom rating scale, and use these linear models to evaluate whether drugs are slowing disease progression. However, data indicate that ALS often follows nonlinear trajectories, with periods where symptoms are stable alternating with periods when they are rapidly changing. Since data can be sparse, and health assessments often rely on subjective rating metrics measured at uneven time intervals, comparisons across patient populations are difficult. These heterogenous data and progression, in turn, complicate analyses of invention effectiveness and potentially mask disease origin.

      Now, a new machine-learning method developed by researchers from MIT, IBM Research, and elsewhere aims to better characterize ALS disease progression patterns to inform clinical trial design.

      “There are groups of individuals that share progression patterns. For example, some seem to have really fast-progressing ALS and others that have slow-progressing ALS that varies over time,” says Divya Ramamoorthy PhD ’22, a research specialist at MIT and lead author of a new paper on the work that was published this month in Nature Computational Science. “The question we were asking is: can we use machine learning to identify if, and to what extent, those types of consistent patterns across individuals exist?”

      Their technique, indeed, identified discrete and robust clinical patterns in ALS progression, many of which are non-linear. Further, these disease progression subtypes were consistent across patient populations and disease metrics. The team additionally found that their method can be applied to Alzheimer’s and Parkinson’s diseases as well.

      Joining Ramamoorthy on the paper are MIT-IBM Watson AI Lab members Ernest Fraenkel, a professor in the MIT Department of Biological Engineering; Research Scientist Soumya Ghosh of IBM Research; and Principal Research Scientist Kenney Ng, also of IBM Research. Additional authors include Kristen Severson PhD ’18, a senior researcher at Microsoft Research and former member of the Watson Lab and of IBM Research; Karen Sachs PhD ’06 of Next Generation Analytics; a team of researchers with Answer ALS; Jonathan D. Glass and Christina N. Fournier of the Emory University School of Medicine; the Pooled Resource Open-Access ALS Clinical Trials Consortium; ALS/MND Natural History Consortium; Todd M. Herrington of Massachusetts General Hospital (MGH) and Harvard Medical School; and James D. Berry of MGH.

      Play video

      MIT Professor Ernest Fraenkel describes early stages of his research looking at root causes of amyotrophic lateral sclerosis (ALS).

      Reshaping health decline

      After consulting with clinicians, the team of machine learning researchers and neurologists let the data speak for itself. They designed an unsupervised machine-learning model that employed two methods: Gaussian process regression and Dirichlet process clustering. These inferred the health trajectories directly from patient data and automatically grouped similar trajectories together without prescribing the number of clusters or the shape of the curves, forming ALS progression “subtypes.” Their method incorporated prior clinical knowledge in the way of a bias for negative trajectories — consistent with expectations for neurodegenerative disease progressions — but did not assume any linearity. “We know that linearity is not reflective of what’s actually observed,” says Ng. “The methods and models that we use here were more flexible, in the sense that, they capture what was seen in the data,” without the need for expensive labeled data and prescription of parameters.

      Primarily, they applied the model to five longitudinal datasets from ALS clinical trials and observational studies. These used the gold standard to measure symptom development: the ALS functional rating scale revised (ALSFRS-R), which captures a global picture of patient neurological impairment but can be a bit of a “messy metric.” Additionally, performance on survivability probabilities, forced vital capacity (a measurement of respiratory function), and subscores of ALSFRS-R, which looks at individual bodily functions, were incorporated.

      New regimes of progression and utility

      When their population-level model was trained and tested on these metrics, four dominant patterns of disease popped out of the many trajectories — sigmoidal fast progression, stable slow progression, unstable slow progression, and unstable moderate progression — many with strong nonlinear characteristics. Notably, it captured trajectories where patients experienced a sudden loss of ability, called a functional cliff, which would significantly impact treatments, enrollment in clinical trials, and quality of life.

      The researchers compared their method against other commonly used linear and nonlinear approaches in the field to separate the contribution of clustering and linearity to the model’s accuracy. The new work outperformed them, even patient-specific models, and found that subtype patterns were consistent across measures. Impressively, when data were withheld, the model was able to interpolate missing values, and, critically, could forecast future health measures. The model could also be trained on one ALSFRS-R dataset and predict cluster membership in others, making it robust, generalizable, and accurate with scarce data. So long as 6-12 months of data were available, health trajectories could be inferred with higher confidence than conventional methods.

      The researchers’ approach also provided insights into Alzheimer’s and Parkinson’s diseases, both of which can have a range of symptom presentations and progression. For Alzheimer’s, the new technique could identify distinct disease patterns, in particular variations in the rates of conversion of mild to severe disease. The Parkinson’s analysis demonstrated a relationship between progression trajectories for off-medication scores and disease phenotypes, such as the tremor-dominant or postural instability/gait difficulty forms of Parkinson’s disease.

      The work makes significant strides to find the signal amongst the noise in the time-series of complex neurodegenerative disease. “The patterns that we see are reproducible across studies, which I don’t believe had been shown before, and that may have implications for how we subtype the [ALS] disease,” says Fraenkel. As the FDA has been considering the impact of non-linearity in clinical trial designs, the team notes that their work is particularly pertinent.

      As new ways to understand disease mechanisms come online, this model provides another tool to pick apart illnesses like ALS, Alzheimer’s, and Parkinson’s from a systems biology perspective.

      “We have a lot of molecular data from the same patients, and so our long-term goal is to see whether there are subtypes of the disease,” says Fraenkel, whose lab looks at cellular changes to understand the etiology of diseases and possible targets for cures. “One approach is to start with the symptoms … and see if people with different patterns of disease progression are also different at the molecular level. That might lead you to a therapy. Then there’s the bottom-up approach, where you start with the molecules” and try to reconstruct biological pathways that might be affected. “We’re going [to be tackling this] from both ends … and finding if something meets in the middle.”

      This research was supported, in part, by the MIT-IBM Watson AI Lab, the Muscular Dystrophy Association, Department of Veterans Affairs of Research and Development, the Department of Defense, NSF Gradate Research Fellowship Program, Siebel Scholars Fellowship, Answer ALS, the United States Army Medical Research Acquisition Activity, National Institutes of Health, and the NIH/NINDS. More

    • 163 Shares199 Views

      in Data Management & Statistics

      New program to support translational research in AI, data science, and machine learning

      by

      The MIT School of Engineering and Pillar VC today announced the MIT-Pillar AI Collective, a one-year pilot program funded by a gift from Pillar VC that will provide seed grants for projects in artificial intelligence, machine learning, and data science with the goal of supporting translational research. The program will support graduate students and postdocs through access to funding, mentorship, and customer discovery.

      Administered by the MIT Deshpande Center for Technological Innovation, the MIT-Pillar AI Collective will center on the market discovery process, advancing projects through market research, customer discovery, and prototyping. Graduate students and postdocs will aim to emerge from the program having built minimum viable products, with support from Pillar VC and experienced industry leaders.

      “We are grateful for this support from Pillar VC and to join forces to converge the commercialization of translational research in AI, data science, and machine learning, with an emphasis on identifying and cultivating prospective entrepreneurs,” says Anantha Chandrakasan, dean of the MIT School of Engineering and Vannevar Bush Professor of Electrical Engineering and Computer Science. “Pillar’s focus on mentorship for our graduate students and postdoctoral researchers, and centering the program within the Deshpande Center, will undoubtedly foster big ideas in AI and create an environment for prospective companies to launch and thrive.” 

      Founded by Jamie Goldstein ’89, Pillar VC is committed to growing companies and investing in personal and professional development, coaching, and community.

      “Many of the most promising companies of the future are living at MIT in the form of transformational research in the fields of data science, AI, and machine learning,” says Goldstein. “We’re honored by the chance to help unlock this potential and catalyze a new generation of founders by surrounding students and postdoctoral researchers with the resources and mentorship they need to move from the lab to industry.”

      The program will launch with the 2022-23 academic year. Grants will be open only to MIT faculty and students, with an emphasis on funding for graduate students in their final year, as well as postdocs. Applications must be submitted by MIT employees with principal investigator status. A selection committee composed of three MIT representatives will include Devavrat Shah, faculty director of the Deshpande Center, the Andrew (1956) and Erna Viterbi Professor in the Department of Electrical Engineering and Computer Science and the Institute for Data, Systems, and Society; the chair of the selection committee; and a representative from the MIT Schwarzman College of Computing. The committee will also include representation from Pillar VC. Funding will be provided for up to nine research teams.

      “The Deshpande Center will serve as the perfect home for the new collective, given its focus on moving innovative technologies from the lab to the marketplace in the form of breakthrough products and new companies,” adds Chandrakasan. 

      “The Deshpande Center has a 20-year history of guiding new technologies toward commercialization, where they can have a greater impact,” says Shah. “This new collective will help the center expand its own impact by helping more projects realize their market potential and providing more support to researchers in the fast-growing fields of AI, machine learning, and data science.” More

    • 100 Shares99 Views

      in Data Management & Statistics

      Q&A: Global challenges surrounding the deployment of AI

      by

      The AI Policy Forum (AIPF) is an initiative of the MIT Schwarzman College of Computing to move the global conversation about the impact of artificial intelligence from principles to practical policy implementation. Formed in late 2020, AIPF brings together leaders in government, business, and academia to develop approaches to address the societal challenges posed by the rapid advances and increasing applicability of AI.

      The co-chairs of the AI Policy Forum are Aleksander Madry, the Cadence Design Systems Professor; Asu Ozdaglar, deputy dean of academics for the MIT Schwarzman College of Computing and head of the Department of Electrical Engineering and Computer Science; and Luis Videgaray, senior lecturer at MIT Sloan School of Management and director of MIT AI Policy for the World Project. Here, they discuss talk some of the key issues facing the AI policy landscape today and the challenges surrounding the deployment of AI. The three are co-organizers of the upcoming AI Policy Forum Summit on Sept. 28, which will further explore the issues discussed here.

      Q: Can you talk about the ­ongoing work of the AI Policy Forum and the AI policy landscape generally?

      Ozdaglar: There is no shortage of discussion about AI at different venues, but conversations are often high-level, focused on questions of ethics and principles, or on policy problems alone. The approach the AIPF takes to its work is to target specific questions with actionable policy solutions and engage with the stakeholders working directly in these areas. We work “behind the scenes” with smaller focus groups to tackle these challenges and aim to bring visibility to some potential solutions alongside the players working directly on them through larger gatherings.

      Q: AI impacts many sectors, which makes us naturally worry about its trustworthiness. Are there any emerging best practices for development and deployment of trustworthy AI?

      Madry: The most important thing to understand regarding deploying trustworthy AI is that AI technology isn’t some natural, preordained phenomenon. It is something built by people. People who are making certain design decisions.

      We thus need to advance research that can guide these decisions as well as provide more desirable solutions. But we also need to be deliberate and think carefully about the incentives that drive these decisions. 

      Now, these incentives stem largely from the business considerations, but not exclusively so. That is, we should also recognize that proper laws and regulations, as well as establishing thoughtful industry standards have a big role to play here too.

      Indeed, governments can put in place rules that prioritize the value of deploying AI while being keenly aware of the corresponding downsides, pitfalls, and impossibilities. The design of such rules will be an ongoing and evolving process as the technology continues to improve and change, and we need to adapt to socio-political realities as well.

      Q: Perhaps one of the most rapidly evolving domains in AI deployment is in the financial sector. From a policy perspective, how should governments, regulators, and lawmakers make AI work best for consumers in finance?

      Videgaray: The financial sector is seeing a number of trends that present policy challenges at the intersection of AI systems. For one, there is the issue of explainability. By law (in the U.S. and in many other countries), lenders need to provide explanations to customers when they take actions deleterious in whatever way, like denial of a loan, to a customer’s interest. However, as financial services increasingly rely on automated systems and machine learning models, the capacity of banks to unpack the “black box” of machine learning to provide that level of mandated explanation becomes tenuous. So how should the finance industry and its regulators adapt to this advance in technology? Perhaps we need new standards and expectations, as well as tools to meet these legal requirements.

      Meanwhile, economies of scale and data network effects are leading to a proliferation of AI outsourcing, and more broadly, AI-as-a-service is becoming increasingly common in the finance industry. In particular, we are seeing fintech companies provide the tools for underwriting to other financial institutions — be it large banks or small, local credit unions. What does this segmentation of the supply chain mean for the industry? Who is accountable for the potential problems in AI systems deployed through several layers of outsourcing? How can regulators adapt to guarantee their mandates of financial stability, fairness, and other societal standards?

      Q: Social media is one of the most controversial sectors of the economy, resulting in many societal shifts and disruptions around the world. What policies or reforms might be needed to best ensure social media is a force for public good and not public harm?

      Ozdaglar: The role of social media in society is of growing concern to many, but the nature of these concerns can vary quite a bit — with some seeing social media as not doing enough to prevent, for example, misinformation and extremism, and others seeing it as unduly silencing certain viewpoints. This lack of unified view on what the problem is impacts the capacity to enact any change. All of that is additionally coupled with the complexities of the legal framework in the U.S. spanning the First Amendment, Section 230 of the Communications Decency Act, and trade laws.

      However, these difficulties in regulating social media do not mean that there is nothing to be done. Indeed, regulators have begun to tighten their control over social media companies, both in the United States and abroad, be it through antitrust procedures or other means. In particular, Ofcom in the U.K. and the European Union is already introducing new layers of oversight to platforms. Additionally, some have proposed taxes on online advertising to address the negative externalities caused by current social media business model. So, the policy tools are there, if the political will and proper guidance exists to implement them. More