arXiv subjects

Song Han

Publications and source records attributed to Song Han.

At least 217 records · Page 12Linked to original sources

arXiv2020

HAT: Hardware-Aware Transformers for Efficient Natural Language Processing

Transformers are ubiquitous in Natural Language Processing (NLP) tasks, but they are difficult to be deployed on hardware due to the intensive computation. To enable low-latency inference on resource-constrained hardware platforms, we propose to design Hardware-Aware Transformers (HAT) with neural architecture search. We first construct a large design space with $\textit{arbitrary encoder-decoder attention}$ and $\textit{heterogeneous layers}$. Then we train a $\textit{SuperTransformer}$ that covers all candidates in the design space, and efficiently produces many $\textit{SubTransformers}$ with weight sharing. Finally, we perform an evolutionary search with a hardware latency constraint to find a specialized $\textit{SubTransformer}$ dedicated to run fast on the target hardware. Extensive experiments on four machine translation tasks demonstrate that HAT can discover efficient models for different hardware (CPU, GPU, IoT device). When running WMT'14 translation task on Raspberry Pi-4, HAT can achieve $\textbf{3}\times$ speedup, $\textbf{3.7}\times$ smaller size over baseline Transformer; $\textbf{2.7}\times$ speedup, $\textbf{3.6}\times$ smaller size over Evolved Transformer with $\textbf{12,041}\times$ less search cost and no performance loss. HAT code is https://github.com/mit-han-lab/hardware-aware-transformers.git

cs.CL↗

arXiv2020

MicroNet for Efficient Language Modeling

It is important to design compact language models for efficient deployment. We improve upon recent advances in both the language modeling domain and the model-compression domain to construct parameter and computation efficient language models. We use an efficient transformer-based architecture with adaptive embedding and softmax, differentiable non-parametric cache, Hebbian softmax, knowledge distillation, network pruning, and low-bit quantization. In this paper, we provide the winning solution to the NeurIPS 2019 MicroNet Challenge in the language modeling track. Compared to the baseline language model provided by the MicroNet Challenge, our model is 90 times more parameter-efficient and 36 times more computation-efficient while achieving the required test perplexity of 35 on the Wikitext-103 dataset. We hope that this work will aid future research into efficient language models, and we have released our full source code at https://github.com/mit-han-lab/neurips-micronet.

cs.CL↗

arXiv2020

GCN-RL Circuit Designer: Transferable Transistor Sizing with Graph Neural Networks and Reinforcement Learning

Automatic transistor sizing is a challenging problem in circuit design due to the large design space, complex performance trade-offs, and fast technological advancements. Although there has been plenty of work on transistor sizing targeting on one circuit, limited research has been done on transferring the knowledge from one circuit to another to reduce the re-design overhead. In this paper, we present GCN-RL Circuit Designer, leveraging reinforcement learning (RL) to transfer the knowledge between different technology nodes and topologies. Moreover, inspired by the simple fact that circuit is a graph, we learn on the circuit topology representation with graph convolutional neural networks (GCN). The GCN-RL agent extracts features of the topology graph whose vertices are transistors, edges are wires. Our learning-based optimization consistently achieves the highest Figures of Merit (FoM) on four different circuits compared with conventional black-box optimization methods (Bayesian Optimization, Evolutionary Algorithms), random search, and human expert designs. Experiments on transfer learning between five technology nodes and two circuit topologies demonstrate that RL with transfer learning can achieve much higher FoMs than methods without knowledge transfer. Our transferable optimization method makes transistor sizing and design porting more effective and efficient.

eess.SP↗

arXiv2020

Once-for-All: Train One Network and Specialize it for Efficient Deployment

We address the challenging problem of efficient inference across many devices and resource constraints, especially on edge devices. Conventional approaches either manually design or use neural architecture search (NAS) to find a specialized neural network and train it from scratch for each case, which is computationally prohibitive (causing $CO_2$ emission as much as 5 cars' lifetime) thus unscalable. In this work, we propose to train a once-for-all (OFA) network that supports diverse architectural settings by decoupling training and search, to reduce the cost. We can quickly get a specialized sub-network by selecting from the OFA network without additional training. To efficiently train OFA networks, we also propose a novel progressive shrinking algorithm, a generalized pruning method that reduces the model size across many more dimensions than pruning (depth, width, kernel size, and resolution). It can obtain a surprisingly large number of sub-networks ($> 10^{19}$) that can fit different hardware platforms and latency constraints while maintaining the same level of accuracy as training independently. On diverse edge devices, OFA consistently outperforms state-of-the-art (SOTA) NAS methods (up to 4.0% ImageNet top1 accuracy improvement over MobileNetV3, or same accuracy but 1.5x faster than MobileNetV3, 2.6x faster than EfficientNet w.r.t measured latency) while reducing many orders of magnitude GPU hours and $CO_2$ emission. In particular, OFA achieves a new SOTA 80.0% ImageNet top-1 accuracy under the mobile setting ($<$600M MACs). OFA is the winning solution for the 3rd Low Power Computer Vision Challenge (LPCVC), DSP classification track and the 4th LPCVC, both classification track and detection track. Code and 50 pre-trained models (for many devices & many latency constraints) are released at https://github.com/mit-han-lab/once-for-all.

cs.LG↗

arXiv2020

Lite Transformer with Long-Short Range Attention

Transformer has become ubiquitous in natural language processing (e.g., machine translation, question answering); however, it requires enormous amount of computations to achieve high performance, which makes it not suitable for mobile applications that are tightly constrained by the hardware resources and battery. In this paper, we present an efficient mobile NLP architecture, Lite Transformer to facilitate deploying mobile NLP applications on edge devices. The key primitive is the Long-Short Range Attention (LSRA), where one group of heads specializes in the local context modeling (by convolution) while another group specializes in the long-distance relationship modeling (by attention). Such specialization brings consistent improvement over the vanilla transformer on three well-established language tasks: machine translation, abstractive summarization, and language modeling. Under constrained resources (500M/100M MACs), Lite Transformer outperforms transformer on WMT'14 English-French by 1.2/1.7 BLEU, respectively. Lite Transformer reduces the computation of transformer base model by 2.5x with 0.3 BLEU score degradation. Combining with pruning and quantization, we further compressed the model size of Lite Transformer by 18.2x. For language modeling, Lite Transformer achieves 1.8 lower perplexity than the transformer at around 500M MACs. Notably, Lite Transformer outperforms the AutoML-based Evolved Transformer by 0.5 higher BLEU for the mobile NLP setting without the costly architecture search that requires more than 250 GPU years. Code has been made available at https://github.com/mit-han-lab/lite-transformer.

cs.CL↗

arXiv2020

SpArch: Efficient Architecture for Sparse Matrix Multiplication

Generalized Sparse Matrix-Matrix Multiplication (SpGEMM) is a ubiquitous task in various engineering and scientific applications. However, inner product based SpGENN introduces redundant input fetches for mismatched nonzero operands, while outer product based approach suffers from poor output locality due to numerous partial product matrices. Inefficiency in the reuse of either inputs or outputs data leads to extensive and expensive DRAM access. To address this problem, this paper proposes an efficient sparse matrix multiplication accelerator architecture, SpArch, which jointly optimizes the data locality for both input and output matrices. We first design a highly parallelized streaming-based merger to pipeline the multiply and merge stage of partial matrices so that partial matrices are merged on chip immediately after produced. We then propose a condensed matrix representation that reduces the number of partial matrices by three orders of magnitude and thus reduces DRAM access by 5.4x. We further develop a Huffman tree scheduler to improve the scalability of the merger for larger sparse matrices, which reduces the DRAM access by another 1.8x. We also resolve the increased input matrix read induced by the new representation using a row prefetcher with near-optimal buffer replacement policy, further reducing the DRAM access by 1.5x. Evaluated on 20 benchmarks, SpArch reduces the total DRAM access by 2.8x over previous state-of-the-art. On average, SpArch achieves 4x, 19x, 18x, 17x, 1285x speedup and 6x, 164x, 435x, 307x, 62x energy savings over OuterSPACE, MKL, cuSPARSE, CUSP, and ARM Armadillo, respectively.

cs.AR↗

arXiv2019

Deep Leakage from Gradients

Exchanging gradients is a widely used method in modern multi-node machine learning system (e.g., distributed training, collaborative learning). For a long time, people believed that gradients are safe to share: i.e., the training data will not be leaked by gradient exchange. However, we show that it is possible to obtain the private training data from the publicly shared gradients. We name this leakage as Deep Leakage from Gradient and empirically validate the effectiveness on both computer vision and natural language processing tasks. Experimental results show that our attack is much stronger than previous approaches: the recovery is pixel-wise accurate for images and token-wise matching for texts. We want to raise people's awareness to rethink the gradient's safety. Finally, we discuss several possible strategies to prevent such deep leakage. The most effective defense method is gradient pruning.

cs.LG↗

arXiv2019

Point-Voxel CNN for Efficient 3D Deep Learning

We present Point-Voxel CNN (PVCNN) for efficient, fast 3D deep learning. Previous work processes 3D data using either voxel-based or point-based NN models. However, both approaches are computationally inefficient. The computation cost and memory footprints of the voxel-based models grow cubically with the input resolution, making it memory-prohibitive to scale up the resolution. As for point-based networks, up to 80% of the time is wasted on structuring the sparse data which have rather poor memory locality, not on the actual feature extraction. In this paper, we propose PVCNN that represents the 3D input data in points to reduce the memory consumption, while performing the convolutions in voxels to reduce the irregular, sparse data access and improve the locality. Our PVCNN model is both memory and computation efficient. Evaluated on semantic and part segmentation datasets, it achieves much higher accuracy than the voxel-based baseline with 10x GPU memory reduction; it also outperforms the state-of-the-art point-based models with 7x measured speedup on average. Remarkably, the narrower version of PVCNN achieves 2x speedup over PointNet (an extremely efficient model) on part and scene segmentation benchmarks with much higher accuracy. We validate the general effectiveness of PVCNN on 3D object detection: by replacing the primitives in Frustrum PointNet with PVConv, it outperforms Frustrum PointNet++ by 2.4% mAP on average with 1.5x measured speedup and GPU memory reduction.

cs.CV↗

arXiv2019

Training Kinetics in 15 Minutes: Large-scale Distributed Training on Videos

Deep video recognition is more computationally expensive than image recognition, especially on large-scale datasets like Kinetics [1]. Therefore, training scalability is essential to handle a large amount of videos. In this paper, we study the factors that impact the training scalability of video networks. We recognize three bottlenecks, including data loading (data movement from disk to GPU), communication (data movement over networking), and computation FLOPs. We propose three design guidelines to improve the scalability: (1) fewer FLOPs and hardware-friendly operator to increase the computation efficiency; (2) fewer input frames to reduce the data movement and increase the data loading efficiency; (3) smaller model size to reduce the networking traffic and increase the networking efficiency. With these guidelines, we designed a new operator Temporal Shift Module (TSM) that is efficient and scalable for distributed training. TSM model can achieve 1.8x higher throughput compared to previous I3D models. We scale up the training of the TSM model to 1,536 GPUs, with a mini-batch of 12,288 video clips/98,304 images, without losing the accuracy. With such hardware-aware model design, we are able to scale up the training on Summit supercomputer and reduce the training time on Kinetics dataset from 49 hours 55 minutes to 14 minutes 13 seconds, achieving a top-1 accuracy of 74.0%, which is 1.6x and 2.9x faster than previous 3D video models with higher accuracy. The code and more details can be found here: http://tsm-hanlab.mit.edu.

cs.CV↗

arXiv2019

MLSys: The New Frontier of Machine Learning Systems

Machine learning (ML) techniques are enjoying rapidly increasing adoption. However, designing and implementing the systems that support ML models in real-world deployments remains a significant obstacle, in large part due to the radically different development and deployment profile of modern ML methods, and the range of practical concerns that come with broader adoption. We propose to foster a new systems machine learning research community at the intersection of the traditional systems and ML communities, focused on topics such as hardware systems for ML, software systems for ML, and ML optimized for metrics beyond predictive accuracy. To do this, we describe a new conference, MLSys, that explicitly targets research at the intersection of systems and machine learning with a program committee split evenly between experts in systems and ML, and an explicit focus on topics at the intersection of the two.

cs.LG↗

arXiv2019

ChainSplitter: Towards Blockchain-based Industrial IoT Architecture for Supporting Hierarchical Storage

The fast developing Industrial Internet of Things (IIoT) technologies provide a promising opportunity to build large-scale systems to connect numerous heterogeneous devices into the Internet. Most existing IIoT infrastructures are based on a centralized architecture, which is easier for management but cannot effectively support immutable and verifiable services among multiple parties. Blockchain technology provides many desired features for large-scale IIoT infrastructures, such as decentralization, trustworthiness, trackability, and immutability. This paper presents a blockchain-based IIoT architecture to support immutable and verifiable services. However, when applying blockchain technology to the IIoT infrastructure, the required storage space posts a grant challenge to resource-constrained IIoT infrastructures. To address the storage issue, this paper proposes a hierarchical blockchain storage structure, \textit{ChainSplitter}. Specially, the proposed architecture features a hierarchical storage structure where the majority of the blockchain is stored in the clouds, while the most recent blocks are stored in the overlay network of the individual IIoT networks. The proposed architecture seamlessly binds local IIoT networks, the blockchain overlay network, and the cloud infrastructure together through two connectors, the \textit{blockchain connector} and the \textit{cloud connector}, to construct the hierarchical blockchain storage. The blockchain connector in the overlay network builds blocks in blockchain from data generated in IIoT networks, and the cloud connector resolves the blockchain synchronization issues between the overlay network and the clouds. We also provide a case study to show the efficiency of the proposed hierarchical blockchain storage in a practical Industrial IoT case.

cs.CR↗

arXiv2019

TSM: Temporal Shift Module for Efficient Video Understanding

The explosive growth in video streaming gives rise to challenges on performing video understanding at high accuracy and low computation cost. Conventional 2D CNNs are computationally cheap but cannot capture temporal relationships; 3D CNN based methods can achieve good performance but are computationally intensive, making it expensive to deploy. In this paper, we propose a generic and effective Temporal Shift Module (TSM) that enjoys both high efficiency and high performance. Specifically, it can achieve the performance of 3D CNN but maintain 2D CNN's complexity. TSM shifts part of the channels along the temporal dimension; thus facilitate information exchanged among neighboring frames. It can be inserted into 2D CNNs to achieve temporal modeling at zero computation and zero parameters. We also extended TSM to online setting, which enables real-time low-latency online video recognition and video object detection. TSM is accurate and efficient: it ranks the first place on the Something-Something leaderboard upon publication; on Jetson Nano and Galaxy Note8, it achieves a low latency of 13ms and 35ms for online video recognition. The code is available at: https://github.com/mit-han-lab/temporal-shift-module.

cs.CV↗

arXiv2019

Design Automation for Efficient Deep Learning Computing

Efficient deep learning computing requires algorithm and hardware co-design to enable specialization: we usually need to change the algorithm to reduce memory footprint and improve energy efficiency. However, the extra degree of freedom from the algorithm makes the design space much larger: it's not only about designing the hardware but also about how to tweak the algorithm to best fit the hardware. Human engineers can hardly exhaust the design space by heuristics. It's labor consuming and sub-optimal. We propose design automation techniques for efficient neural networks. We investigate automatically designing specialized fast models, auto channel pruning, and auto mixed-precision quantization. We demonstrate such learning-based, automated design achieves superior performance and efficiency than rule-based human design. Moreover, we shorten the design cycle by 200x than previous work, so that we can afford to design specialized neural network models for different hardware platforms.

cs.LG↗

arXiv2019

Defensive Quantization: When Efficiency Meets Robustness

Neural network quantization is becoming an industry standard to efficiently deploy deep learning models on hardware platforms, such as CPU, GPU, TPU, and FPGAs. However, we observe that the conventional quantization approaches are vulnerable to adversarial attacks. This paper aims to raise people's awareness about the security of the quantized models, and we designed a novel quantization methodology to jointly optimize the efficiency and robustness of deep learning models. We first conduct an empirical study to show that vanilla quantization suffers more from adversarial attacks. We observe that the inferior robustness comes from the error amplification effect, where the quantization operation further enlarges the distance caused by amplified noise. Then we propose a novel Defensive Quantization (DQ) method by controlling the Lipschitz constant of the network during quantization, such that the magnitude of the adversarial noise remains non-expansive during inference. Extensive experiments on CIFAR-10 and SVHN datasets demonstrate that our new quantization method can defend neural networks against adversarial examples, and even achieves superior robustness than their full-precision counterparts while maintaining the same hardware efficiency as vanilla quantization approaches. As a by-product, DQ can also improve the accuracy of quantized models without adversarial attack.

cs.LG↗

arXiv2019

HAQ: Hardware-Aware Automated Quantization with Mixed Precision

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency, which raises a great challenge to find the optimal bitwidth for each layer: it requires domain experts to explore the vast design space trading off among accuracy, latency, energy, and model size, which is both time-consuming and sub-optimal. Conventional quantization algorithm ignores the different hardware architectures and quantizes all the layers in a uniform way. In this paper, we introduce the Hardware-Aware Automated Quantization (HAQ) framework which leverages the reinforcement learning to automatically determine the quantization policy, and we take the hardware accelerator's feedback in the design loop. Rather than relying on proxy signals such as FLOPs and model size, we employ a hardware simulator to generate direct feedback signals (latency and energy) to the RL agent. Compared with conventional methods, our framework is fully automated and can specialize the quantization policy for different neural network architectures and hardware architectures. Our framework effectively reduced the latency by 1.4-1.95x and the energy consumption by 1.9x with negligible loss of accuracy compared with the fixed bitwidth (8 bits) quantization. Our framework reveals that the optimal policies on different hardware architectures (i.e., edge and cloud architectures) under different resource constraints (i.e., latency, energy and model size) are drastically different. We interpreted the implication of different quantization policies, which offer insights for both neural network architecture design and hardware architecture design.

cs.CV↗

arXiv2019

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. $10^4$ GPU hours) makes it difficult to \emph{directly} search the architectures on large-scale tasks (e.g. ImageNet). Differentiable NAS can reduce the cost of GPU hours via a continuous representation of network architecture but suffers from the high GPU memory consumption issue (grow linearly w.r.t. candidate set size). As a result, they need to utilize~\emph{proxy} tasks, such as training on a smaller dataset, or learning with only a few blocks, or training just for a few epochs. These architectures optimized on proxy tasks are not guaranteed to be optimal on the target task. In this paper, we present \emph{ProxylessNAS} that can \emph{directly} learn the architectures for large-scale target tasks and target hardware platforms. We address the high memory consumption issue of differentiable NAS and reduce the computational cost (GPU hours and GPU memory) to the same level of regular training while still allowing a large candidate set. Experiments on CIFAR-10 and ImageNet demonstrate the effectiveness of directness and specialization. On CIFAR-10, our model achieves 2.08\% test error with only 5.7M parameters, better than the previous state-of-the-art architecture AmoebaNet-B, while using 6$\times$ fewer parameters. On ImageNet, our model achieves 3.1\% better top-1 accuracy than MobileNetV2, while being 1.2$\times$ faster with measured GPU latency. We also apply ProxylessNAS to specialize neural architectures for hardware with direct hardware metrics (e.g. latency) and provide insights for efficient CNN architecture design.

cs.LG↗

arXiv2019

Fully Distributed Packet Scheduling Framework for Handling Disturbances in Lossy Real-Time Wireless Networks

Along with the rapid growth of Industrial Internet-of-Things (IIoT) applications and their penetration into many industry sectors, real-time wireless networks (RTWNs) have been playing a more critical role in providing real-time, reliable and secure communication services for such applications. A key challenge in RTWN management is how to ensure real-time Quality of Services (QoS) especially in the presence of unexpected disturbances and lossy wireless links. Most prior work takes centralized approaches for handling disturbances, which are slow and subject to single-point failure, and do not scale. To overcome these drawbacks, this paper presents a fully distributed packet scheduling framework called FD-PaS. FD-PaS aims to provide guaranteed fast response to unexpected disturbances while achieving minimum performance degradation for meeting the timing and reliability requirements of all critical tasks. To combat the scalability challenge, FD-PaS incorporates several key advances in both algorithm design and data link layer protocol design to enable individual nodes to make on-line decisions locally without any centralized control. Our extensive simulation and testbed results have validated the correctness of the FD-PaS design and demonstrated its effectiveness in providing fast response for handling disturbances while ensuring the designated QoS requirements.

cs.NI↗

arXiv2019

AMC: AutoML for Model Compression and Acceleration on Mobile Devices

Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets. Conventional model compression techniques rely on hand-crafted heuristics and rule-based policies that require domain experts to explore the large design space trading off among model size, speed, and accuracy, which is usually sub-optimal and time-consuming. In this paper, we propose AutoML for Model Compression (AMC) which leverage reinforcement learning to provide the model compression policy. This learning-based compression policy outperforms conventional rule-based compression policy by having higher compression ratio, better preserving the accuracy and freeing human labor. Under 4x FLOPs reduction, we achieved 2.7% better accuracy than the handcrafted model compression policy for VGG-16 on ImageNet. We applied this automated, push-the-button compression pipeline to MobileNet and achieved 1.81x speedup of measured inference latency on an Android phone and 1.43x speedup on the Titan XP GPU, with only 0.1% loss of ImageNet Top-1 accuracy.

cs.CV↗