arXiv subjects

Guangyu Sun

Publications and source records attributed to Guangyu Sun.

At least 73 records · Page 4Linked to original sources

arXiv2023

FedPerfix: Towards Partial Model Personalization of Vision Transformers in Federated Learning

Personalized Federated Learning (PFL) represents a promising solution for decentralized learning in heterogeneous data environments. Partial model personalization has been proposed to improve the efficiency of PFL by selectively updating local model parameters instead of aggregating all of them. However, previous work on partial model personalization has mainly focused on Convolutional Neural Networks (CNNs), leaving a gap in understanding how it can be applied to other popular models such as Vision Transformers (ViTs). In this work, we investigate where and how to partially personalize a ViT model. Specifically, we empirically evaluate the sensitivity to data distribution of each type of layer. Based on the insights that the self-attention layer and the classification head are the most sensitive parts of a ViT, we propose a novel approach called FedPerfix, which leverages plugins to transfer information from the aggregated model to the local client as a personalization. Finally, we evaluate the proposed approach on CIFAR-100, OrganAMNIST, and Office-Home datasets and demonstrate its effectiveness in improving the model's performance compared to several advanced PFL methods.

cs.CV↗

arXiv2023

RPTQ: Reorder-based Post-training Quantization for Large Language Models

Large-scale language models (LLMs) have demonstrated impressive performance, but their deployment presents challenges due to their significant memory usage. This issue can be alleviated through quantization. In this paper, we identify that the challenge in quantizing activations in LLMs arises from varying ranges across channels, rather than solely the presence of outliers. To address this challenge, we introduce a quantization method called RPTQ, which utilizes a reorder-based approach. By rearranging the channels and quantizing them in clusters, RPTQ effectively mitigates the impact of range differences between channels. To minimize the overhead of the reorder operation, we fuse it into the layer norm operation and weights in linear layers. In our experiments, RPTQ achieved a significant breakthrough by utilizing 3-bit activation in LLMs for the first time, resulting in a substantial reduction in memory usage. For instance, quantizing OPT-175b can lead to a memory consumption reduction of up to 80%.

cs.CL↗

arXiv2023

Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance

Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures. Despite its effectiveness and convenience, the reliability of PTQ methods in the presence of some extrem cases such as distribution shift and data noise remains largely unexplored. This paper first investigates this problem on various commonly-used PTQ methods. We aim to answer several research questions related to the influence of calibration set distribution variations, calibration paradigm selection, and data augmentation or sampling strategies on PTQ reliability. A systematic evaluation process is conducted across a wide range of tasks and commonly-used PTQ paradigms. The results show that most existing PTQ methods are not reliable enough in term of the worst-case group performance, highlighting the need for more robust methods. Our findings provide insights for developing PTQ methods that can effectively handle distribution shift scenarios and enable the deployment of quantized DNNs in real-world applications.

cs.LG↗

arXiv2022

Anomaly Crossing: New Horizons for Video Anomaly Detection as Cross-domain Few-shot Learning

Video anomaly detection aims to identify abnormal events that occurred in videos. Since anomalous events are relatively rare, it is not feasible to collect a balanced dataset and train a binary classifier to solve the task. Thus, most previous approaches learn only from normal videos using unsupervised or semi-supervised methods. Obviously, they are limited in capturing and utilizing discriminative abnormal characteristics, which leads to compromised anomaly detection performance. In this paper, to address this issue, we propose a new learning paradigm by making full use of both normal and abnormal videos for video anomaly detection. In particular, we formulate a new learning task: cross-domain few-shot anomaly detection, which can transfer knowledge learned from numerous videos in the source domain to help solve few-shot abnormality detection in the target domain. Concretely, we leverage self-supervised training on the target normal videos to reduce the domain gap and devise a meta context perception module to explore the video context of the event in the few-shot setting. Our experiments show that our method significantly outperforms baseline methods on DoTA and UCF-Crime datasets, and the new task contributes to a more practical training paradigm for anomaly detection.

cs.CV↗

arXiv2022

Latency-aware Spatial-wise Dynamic Networks

Spatial-wise dynamic convolution has become a promising approach to improving the inference efficiency of deep networks. By allocating more computation to the most informative pixels, such an adaptive inference paradigm reduces the spatial redundancy in image features and saves a considerable amount of unnecessary computation. However, the theoretical efficiency achieved by previous methods can hardly translate into a realistic speedup, especially on the multi-core processors (e.g. GPUs). The key challenge is that the existing literature has only focused on designing algorithms with minimal computation, ignoring the fact that the practical latency can also be influenced by scheduling strategies and hardware properties. To bridge the gap between theoretical computation and practical efficiency, we propose a latency-aware spatial-wise dynamic network (LASNet), which performs coarse-grained spatially adaptive inference under the guidance of a novel latency prediction model. The latency prediction model can efficiently estimate the inference latency of dynamic networks by simultaneously considering algorithms, scheduling strategies, and hardware properties. We use the latency predictor to guide both the algorithm design and the scheduling optimization on various hardware platforms. Experiments on image classification, object detection and instance segmentation demonstrate that the proposed framework significantly improves the practical inference efficiency of deep networks. For example, the average latency of a ResNet-101 on the ImageNet validation set could be reduced by 36% and 46% on a server GPU (Nvidia Tesla-V100) and an edge device (Nvidia Jetson TX2 GPU) respectively without sacrificing the accuracy. Code is available at https://github.com/LeapLabTHU/LASNet.

cs.CV↗

arXiv2022

GNNear: Accelerating Full-Batch Training of Graph Neural Networks with Near-Memory Processing

Recently, Graph Neural Networks (GNNs) have become state-of-the-art algorithms for analyzing non-euclidean graph data. However, to realize efficient GNN training is challenging, especially on large graphs. The reasons are many-folded: 1) GNN training incurs a substantial memory footprint. Full-batch training on large graphs even requires hundreds to thousands of gigabytes of memory. 2) GNN training involves both memory-intensive and computation-intensive operations, challenging current CPU/GPU platforms. 3) The irregularity of graphs can result in severe resource under-utilization and load-imbalance problems. This paper presents a GNNear accelerator to tackle these challenges. GNNear adopts a DIMM-based memory system to provide sufficient memory capacity. To match the heterogeneous nature of GNN training, we offload the memory-intensive Reduce operations to in-DIMM Near-Memory-Engines (NMEs), making full use of the high aggregated local bandwidth. We adopt a Centralized-Acceleration-Engine (CAE) to process the computation-intensive Update operations. We further propose several optimization strategies to deal with the irregularity of input graphs and improve GNNear's performance. Comprehensive evaluations on 16 GNN training tasks demonstrate that GNNear achieves 30.8$\times$/2.5$\times$ geomean speedup and 79.6$\times$/7.3$\times$(geomean) higher energy efficiency compared to Xeon E5-2698-v4 CPU and NVIDIA V100 GPU.

cs.LG↗

arXiv2022

GNNSampler: Bridging the Gap between Sampling Algorithms of GNN and Hardware

Sampling is a critical operation in Graph Neural Network (GNN) training that helps reduce the cost. Previous literature has explored improving sampling algorithms via mathematical and statistical methods. However, there is a gap between sampling algorithms and hardware. Without consideration of hardware, algorithm designers merely optimize sampling at the algorithm level, missing the great potential of promoting the efficiency of existing sampling algorithms by leveraging hardware features. In this paper, we pioneer to propose a unified programming model for mainstream sampling algorithms, termed GNNSampler, covering the critical processes of sampling algorithms in various categories. Second, to leverage the hardware feature, we choose the data locality as a case study, and explore the data locality among nodes and their neighbors in a graph to alleviate irregular memory access in sampling. Third, we implement locality-aware optimizations in GNNSampler for various sampling algorithms to optimize the general sampling process. Finally, we emphatically conduct experiments on large graph datasets to analyze the relevance among training time, accuracy, and hardware-level metrics. Extensive experiments show that our method is universal to mainstream sampling algorithms and helps significantly reduce the training time, especially in large-scale graphs.

cs.LG↗

arXiv2022

Energon: Towards Efficient Acceleration of Transformers Using Dynamic Sparse Attention

In recent years, transformer models have revolutionized Natural Language Processing (NLP) and shown promising performance on Computer Vision (CV) tasks. Despite their effectiveness, transformers' attention operations are hard to accelerate due to the complicated data movement and quadratic computational complexity, prohibiting the real-time inference on resource-constrained edge-computing platforms. To tackle this challenge, we propose Energon, an algorithm-architecture co-design approach that accelerates various transformers using dynamic sparse attention. With the observation that attention results only depend on a few important query-key pairs, we propose a Mix-Precision Multi-Round Filtering (MP-MRF) algorithm to dynamically identify such pairs at runtime. We adopt low bitwidth in each filtering round and only use high-precision tensors in the attention stage to reduce overall complexity. By this means, we significantly mitigate the computational cost with negligible accuracy loss. To enable such an algorithm with lower latency and better energy efficiency, we also propose an Energon co-processor architecture. Elaborated pipelines and specialized optimizations jointly boost the performance and reduce power consumption. Extensive experiments on both NLP and CV benchmarks demonstrate that Energon achieves $168\times$ and $8.7\times$ geo-mean speedup and up to $10^4\times$ and $10^3\times$ energy reduction compared with Intel Xeon 5220 CPU and NVIDIA V100 GPU. Compared to state-of-the-art attention accelerators SpAtten and $A^3$, Energon also achieves $1.7\times, 1.25\times$ speedup and $1.6 \times, 1.5\times $ higher energy efficiency.

cs.AR↗

arXiv2021

PTQ-SL: Exploring the Sub-layerwise Post-training Quantization

Network quantization is a powerful technique to compress convolutional neural networks. The quantization granularity determines how to share the scaling factors in weights, which affects the performance of network quantization. Most existing approaches share the scaling factors layerwisely or channelwisely for quantization of convolutional layers. Channelwise quantization and layerwise quantization have been widely used in various applications. However, other quantization granularities are rarely explored. In this paper, we will explore the sub-layerwise granularity that shares the scaling factor across multiple input and output channels. We propose an efficient post-training quantization method in sub-layerwise granularity (PTQ-SL). Then we systematically experiment on various granularities and observe that the prediction accuracy of the quantized neural network has a strong correlation with the granularity. Moreover, we find that adjusting the position of the channels can improve the performance of sub-layerwise quantization. Therefore, we propose a method to reorder the channels for sub-layerwise quantization. The experiments demonstrate that the sub-layerwise quantization with appropriate channel reordering can outperform the channelwise quantization.

cs.CV↗

arXiv2021

BlockGNN: Towards Efficient GNN Acceleration Using Block-Circulant Weight Matrices

In recent years, Graph Neural Networks (GNNs) appear to be state-of-the-art algorithms for analyzing non-euclidean graph data. By applying deep-learning to extract high-level representations from graph structures, GNNs achieve extraordinary accuracy and great generalization ability in various tasks. However, with the ever-increasing graph sizes, more and more complicated GNN layers, and higher feature dimensions, the computational complexity of GNNs grows exponentially. How to inference GNNs in real time has become a challenging problem, especially for some resource-limited edge-computing platforms. To tackle this challenge, we propose BlockGNN, a software-hardware co-design approach to realize efficient GNN acceleration. At the algorithm level, we propose to leverage block-circulant weight matrices to greatly reduce the complexity of various GNN models. At the hardware design level, we propose a pipelined CirCore architecture, which supports efficient block-circulant matrices computation. Basing on CirCore, we present a novel BlockGNN accelerator to compute various GNNs with low latency. Moreover, to determine the optimal configurations for diverse deployed tasks, we also introduce a performance and resource model that helps choose the optimal hardware parameters automatically. Comprehensive experiments on the ZC706 FPGA platform demonstrate that on various GNN tasks, BlockGNN achieves up to $8.3\times$ speedup compared to the baseline HyGCN architecture and $111.9\times$ energy reduction compared to the Intel Xeon CPU platform.

cs.AI↗

arXiv2021

Emergent O(4) symmetry at the phase transition from plaquette-singlet to antiferromagnetic order in quasi-two-dimensional quantum magnets

Recent experiments [J. Guo et al., Phys. Rev. Lett.124,206602 (2020)] on thermodynamic properties of the frustrated layered quantum magnet SrCu$_2$(BO$_3$)$_2$ -- the Shastry-Sutherland material -- have provided strong evidence for a low-temperature phase transition between plaquette-singlet and antiferromagnetic order as a function of pressure. Further motivated by the recently discovered unusual first-order quantum phase transition with an apparent emergent O(4) symmetry of the antiferromagnetic and plaquette-singlet order parameters in a two-dimensional "checkerboard J-Q" quantum spin model [B. Zhao et al., Nat. Phys. 15, 678 (2019)], we here study the same model in the presence of weak inter-layer couplings. Our focus is on the evolution of the emergent symmetry as the system crosses over from two to three dimensions and the phase transition extends from strictly zero temperature in two dimensions up to finite temperature as expected in SrCu$_2$(BO$_3$)$_2$. Using quantum Monte Carlo simulations, we map out the phase boundaries of the plaquette-singlet and antiferromagnetic phases, with particular focus on the triple point where these two order phases meet the paramagnetic phase for given strength of the inter-layer coupling. All transitions are first-order in the neighborhood of the triple points. We show that the emergent O(4) symmetry of the coexistence state breaks down clearly when the interlayer coupling becomes sufficiently large, but for a weak coupling, of the magnitude expected experimentally, the enlarged symmetry can still be observed at the triple point up to significant length scales. Thus, it is likely that the plaquette-singlet to antiferromagnetic transition in SrCu$_2$(BO$_3$)$_2$ exhibits remnants of emergent O(4) symmetry, which should be observable due to additional weakly gapped Goldstone modes.

cond-mat.str-el↗

arXiv2021

Agatha: Smart Contract for DNN Computation

Smart contract is one of the core features of Ethereum and has inspired many blockchain descendants. Since its advent, the verification paradigm of smart contract has been improving toward high scalability. It shifts from the expensive on-chain verification to the orchestration of off-chain VM (virtual machine) execution and on-chain arbitration with the pinpoint protocol. The representative projects are TrueBit, Arbitrum, YODA, ACE, and Optimism. Inspired by visionaries in academia and industry, we consider the DNN computation to be promising but on the next level of complexity for the verification paradigm of smart contract. Unfortunately, even for the state-of-the-art verification paradigm, off-chain VM execution of DNN computation has an orders-of-magnitude slowdown compared to the native off-chain execution. To enable the native off-chain execution of verifiable DNN computation, we present Agatha system, which solves the significant challenges of misalignment and inconsistency: (1) Native DNN computation has a graph-based computation paradigm misaligned with previous VM-based execution and arbitration; (2) Native DNN computation may be inconsistent cross platforms which invalidates the verification paradigm. In response, we propose the graph-based pinpoint protocol (GPP) which enables the pinpoint protocol on computational graphs, and bridges the native off-chain execution and the contract arbitration. We also develop a technique named Cross-evaluator Consistent Execution (XCE), which guarantees cross-platform consistency and forms the correctness foundation of GPP. We showcase Agatha for the DNN computation of popular models (MobileNet, ResNet50 and VGG16) on Ethereum. Agatha achieves a negligible on-chain overhead, and an off-chain execution overhead of 3.0%, which represents an off-chain latency reduction of at least 602x compared to the state-of-the-art verification paradigm.

cs.CR↗

arXiv2020

Customizing Trusted AI Accelerators for Efficient Privacy-Preserving Machine Learning

The use of trusted hardware has become a promising solution to enable privacy-preserving machine learning. In particular, users can upload their private data and models to a hardware-enforced trusted execution environment (e.g. an enclave in Intel SGX-enabled CPUs) and run machine learning tasks in it with confidentiality and integrity guaranteed. To improve performance, AI accelerators have been widely employed for modern machine learning tasks. However, how to protect privacy on an AI accelerator remains an open question. To address this question, we propose a solution for efficient privacy-preserving machine learning based on an unmodified trusted CPU and a customized trusted AI accelerator. We carefully leverage cryptographic primitives to establish trust and protect the channel between the CPU and the accelerator. As a case study, we demonstrate our solution based on the open-source versatile tensor accelerator. The result of evaluation shows that the proposed solution provides efficient privacy-preserving machine learning at a small design cost and moderate performance overhead.

cs.AR↗

arXiv2020

ENAS4D: Efficient Multi-stage CNN Architecture Search for Dynamic Inference

Dynamic inference is a feasible way to reduce the computational cost of convolutional neural network(CNN), which can dynamically adjust the computation for each input sample. One of the ways to achieve dynamic inference is to use multi-stage neural network, which contains a sub-network with prediction layer at each stage. The inference of a input sample can exit from early stage if the prediction of the stage is confident enough. However, design a multi-stage CNN architecture is a non-trivial task. In this paper, we introduce a general framework, ENAS4D, which can efficiently search for optimal multi-stage CNN architecture for dynamic inference in a well-designed search space. Firstly, we propose a method to construct the search space with multi-stage convolution. The search space include different numbers of layers, different kernel sizes and different numbers of channels for each stage and the resolution of input samples. Then, we train a once-for-all network that supports to sample diverse multi-stage CNN architecture. A specialized multi-stage network can be obtained from the once-for-all network without additional training. Finally, we devise a method to efficiently search for the optimal multi-stage network that trades the accuracy off the computational cost taking the advantage of once-for-all network. The experiments on the ImageNet classification task demonstrate that the multi-stage CNNs searched by ENAS4D consistently outperform the state-of-the-art method for dyanmic inference. In particular, the network achieves 74.4% ImageNet top-1 accuracy under 185M average MACs.

cs.CV↗

arXiv2020

Deep Learning Detection of Inaccurate Smart Electricity Meters: A Case Study

Detecting inaccurate smart meters and targeting them for replacement can save significant resources. For this purpose, a novel deep-learning method was developed based on long short-term memory (LSTM) and a modified convolutional neural network (CNN) to predict electricity usage trajectories based on historical data. From the significant difference between the predicted trajectory and the observed one, the meters that cannot measure electricity accurately are located. In a case study, a proof of principle was demonstrated in detecting inaccurate meters with high accuracy for practical usage to prevent unnecessary replacement and increase the service life span of smart meters.

eess.SP↗

arXiv2020

Quantum phases of SrCu2(BO3)2 from high-pressure thermodynamics

We report heat capacity measurements of SrCu$_2$(BO$_3$)$_2$ under high pressure along with simulations of relevant quantum spin models and map out the $(P,T)$ phase diagram of the material. We find a first-order quantum phase transition between the low-pressure quantum dimer paramagnet and a phase with signatures of a plaquette-singlet state below T = $2$ K. At higher pressures, we observe a transition into a previously unknown antiferromagnetic state below $4$ K. Our findings can be explained within the two-dimensional Shastry-Sutherland quantum spin model supplemented by weak inter-layer couplings. The possibility to tune SrCu$_2$(BO$_3$)$_2$ between the plaquette-singlet and antiferromagnetic states opens opportunities for experimental tests of quantum field theories and lattice models involving fractionalized excitations, emergent symmetries, and gauge fluctuations.

cond-mat.str-el↗

arXiv2019

S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Search

Recently, dynamic inference has emerged as a promising way to reduce the computational cost of deep convolutional neural network (CNN). In contrast to static methods (e.g. weight pruning), dynamic inference adaptively adjusts the inference process according to each input sample, which can considerably reduce the computational cost on "easy" samples while maintaining the overall model performance. In this paper, we introduce a general framework, S2DNAS, which can transform various static CNN models to support dynamic inference via neural architecture search. To this end, based on a given CNN model, we first generate a CNN architecture space in which each architecture is a multi-stage CNN generated from the given model using some predefined transformations. Then, we propose a reinforcement learning based approach to automatically search for the optimal CNN architecture in the generated space. At last, with the searched multi-stage network, we can perform dynamic inference by adaptively choosing a stage to evaluate for each sample. Unlike previous works that introduce irregular computations or complex controllers in the inference or re-design a CNN model from scratch, our method can generalize to most of the popular CNN architectures and the searched dynamic network can be directly deployed using existing deep learning frameworks in various hardware devices.

cs.CV↗

arXiv2019

Characterizing Membership Privacy in Stochastic Gradient Langevin Dynamics

Bayesian deep learning is recently regarded as an intrinsic way to characterize the weight uncertainty of deep neural networks~(DNNs). Stochastic Gradient Langevin Dynamics~(SGLD) is an effective method to enable Bayesian deep learning on large-scale datasets. Previous theoretical studies have shown various appealing properties of SGLD, ranging from the convergence properties to the generalization bounds. In this paper, we study the properties of SGLD from a novel perspective of membership privacy protection (i.e., preventing the membership attack). The membership attack, which aims to determine whether a specific sample is used for training a given DNN model, has emerged as a common threat against deep learning algorithms. To this end, we build a theoretical framework to analyze the information leakage (w.r.t. the training dataset) of a model trained using SGLD. Based on this framework, we demonstrate that SGLD can prevent the information leakage of the training dataset to a certain extent. Moreover, our theoretical analysis can be naturally extended to other types of Stochastic Gradient Markov Chain Monte Carlo (SG-MCMC) methods. Empirical results on different datasets and models verify our theoretical findings and suggest that the SGLD algorithm can not only reduce the information leakage but also improve the generalization ability of the DNN models in real-world applications.

cs.LG↗