arXiv subjects

Quan Chen

Publications and source records attributed to Quan Chen.

At least 127 records · Page 7Linked to original sources

arXiv2022

DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization

Image color harmonization algorithm aims to automatically match the color distribution of foreground and background images captured in different conditions. Previous deep learning based models neglect two issues that are critical for practical applications, namely high resolution (HR) image processing and model comprehensibility. In this paper, we propose a novel Deep Comprehensible Color Filter (DCCF) learning framework for high-resolution image harmonization. Specifically, DCCF first downsamples the original input image to its low-resolution (LR) counter-part, then learns four human comprehensible neural filters (i.e. hue, saturation, value and attentive rendering filters) in an end-to-end manner, finally applies these filters to the original input image to get the harmonized result. Benefiting from the comprehensible neural filters, we could provide a simple yet efficient handler for users to cooperate with deep model to get the desired results with very little effort when necessary. Extensive experiments demonstrate the effectiveness of DCCF learning framework and it outperforms state-of-the-art post-processing method on iHarmony4 dataset on images' full-resolutions by achieving 7.63% and 1.69% relative improvements on MSE and PSNR respectively.

cs.CV↗

arXiv2022

SALO: An Efficient Spatial Accelerator Enabling Hybrid Sparse Attention Mechanisms for Long Sequences

The attention mechanisms of transformers effectively extract pertinent information from the input sequence. However, the quadratic complexity of self-attention w.r.t the sequence length incurs heavy computational and memory burdens, especially for tasks with long sequences. Existing accelerators face performance degradation in these tasks. To this end, we propose SALO to enable hybrid sparse attention mechanisms for long sequences. SALO contains a data scheduler to map hybrid sparse attention patterns onto hardware and a spatial accelerator to perform the efficient attention computation. We show that SALO achieves 17.66x and 89.33x speedup on average compared to GPU and CPU implementations, respectively, on typical workloads, i.e., Longformer and ViL.

cs.AR↗

arXiv2022

Dynamics of Associative Polymers with High Density of Reversible Bonds

We design and synthesize unentangled associative polymers carrying unprecedented high fractions of stickers, up to eight per Kuhn segment, that can form strong pairwise hydrogen bonding of $\sim20k_BT$ without microphase separation. The reversible bonds significantly slow down the polymer dynamics but nearly do not change the shape of linear viscoelastic spectra. Moreover, the structural relaxation time of associative polymers increases exponentially with the fraction of stickers and exhibits a universal yet non-Arrhenius dependence on the distance from polymer glass transition temperature. These results cannot be understood within the framework of the classic sticky-Rouse model but are rationalized by a renormalized Rouse model, which highlights an unexpected influence of reversible bonds on the structural relaxation rather than the shape of viscoelastic spectra for associative polymers with high concentrations of stickers.

cond-mat.soft↗

arXiv2022

Multilayer Perceptron Based Stress Evolution Analysis under DC Current Stressing for Multi-segment Wires

Electromigration (EM) is one of the major concerns in the reliability analysis of very large scale integration (VLSI) systems due to the continuous technology scaling. Accurately predicting the time-to-failure of integrated circuits (IC) becomes increasingly important for modern IC design. However, traditional methods are often not sufficiently accurate, leading to undesirable over-design especially in advanced technology nodes. In this paper, we propose an approach using multilayer perceptrons (MLP) to compute stress evolution in the interconnect trees during the void nucleation phase. The availability of a customized trial function for neural network training holds the promise of finding dynamic mesh-free stress evolution on complex interconnect trees under time-varying temperatures. Specifically, we formulate a new objective function considering the EM-induced coupled partial differential equations (PDEs), boundary conditions (BCs), and initial conditions to enforce the physics-based constraints in the spatial-temporal domain. The proposed model avoids meshing and reduces temporal iterations compared with conventional numerical approaches like FEM. Numerical results confirm its advantages on accuracy and computational performance.

cs.LG↗

arXiv2022

A Space-Time Neural Network for Analysis of Stress Evolution under DC Current Stressing

The electromigration (EM)-induced reliability issues in very large scale integration (VLSI) circuits have attracted increased attention due to the continuous technology scaling. Traditional EM models often lead to overly pessimistic prediction incompatible with the shrinking design margin in future technology nodes. Motivated by the latest success of neural networks in solving differential equations in physical problems, we propose a novel mesh-free model to compute EM-induced stress evolution in VLSI circuits. The model utilizes a specifically crafted space-time physics-informed neural network (STPINN) as the solver for EM analysis. By coupling the physics-based EM analysis with dynamic temperature incorporating Joule heating and via effect, we can observe stress evolution along multi-segment interconnect trees under constant, time-dependent and space-time-dependent temperature during the void nucleation phase. The proposed STPINN method obviates the time discretization and meshing required in conventional numerical stress evolution analysis and offers significant computational savings. Numerical comparison with competing schemes demonstrates a 2x ~ 52x speedup with a satisfactory accuracy.

eess.SP↗

arXiv2022

VELTAIR: Towards High-Performance Multi-tenant Deep Learning Services via Adaptive Compilation and Scheduling

Deep learning (DL) models have achieved great success in many application domains. As such, many industrial companies such as Google and Facebook have acknowledged the importance of multi-tenant DL services. Although the multi-tenant service has been studied in conventional workloads, it is not been deeply studied on deep learning service, especially on general-purpose hardware. In this work, we systematically analyze the opportunities and challenges of providing multi-tenant deep learning services on the general-purpose CPU architecture from the aspects of scheduling granularity and code generation. We propose an adaptive granularity scheduling scheme to both guarantee resource usage efficiency and reduce the scheduling conflict rate. We also propose an adaptive compilation strategy, by which we can dynamically and intelligently pick a program with proper exclusive and shared resource usage to reduce overall interference-induced performance loss. Compared to the existing works, our design can serve more requests under the same QoS target in various scenarios (e.g., +71%, +62%, +45% for light, medium, and heavy workloads, respectively), and reduce the averaged query latency by 50%.

cs.DC↗

arXiv2022

The Serverless Computing Survey: A Technical Primer for Design Architecture

The development of cloud infrastructures inspires the emergence of cloud-native computing. As the most promising architecture for deploying microservices, serverless computing has recently attracted more and more attention in both industry and academia. Due to its inherent scalability and flexibility, serverless computing becomes attractive and more pervasive for ever-growing Internet services. Despite the momentum in the cloud-native community, the existing challenges and compromises still wait for more advanced research and solutions to further explore the potentials of the serverless computing model. As a contribution to this knowledge, this article surveys and elaborates the research domains in the serverless context by decoupling the architecture into four stack layers: Virtualization, Encapsule, System Orchestration, and System Coordination. Inspired by the security model, we highlight the key implications and limitations of these works in each layer, and make suggestions for potential challenges to the field of future serverless computing.

cs.DC↗

arXiv2021

A categorical Connes' $χ(M)$

Popa introduced the tensor category $\tildeχ(M)$ of approximately inner, centrally trivial bimodules of a $\rm{II}_{1}$ factor $M$, generalizing Connes' $χ(M)$. We extend Popa's notions to define the $\rm W^*$-tensor category $\operatorname{End}_{\rm loc}(\mathcal{C})$ of local endofunctors on a $\rm W^*$-category $\mathcal{C}$. We construct a unitary braiding on $\operatorname{End}_{\rm loc}(\mathcal{C})$, giving a new construction of a braided tensor category associated to an arbitrary $\rm W^*$-category. For the $\rm W^*$-category of finite modules over a $\rm{II}_{1}$ factor, this yields a unitary braiding on Popa's $\tildeχ(M)$, which extends Jones' $κ$ invariant for $χ(M)$. Given a finite depth inclusion $M_{0}\subseteq M_{1}$ of non-Gamma $\rm{II}_1$ factors, we show that the braided unitary tensor category $\tildeχ(M_{\infty})$ is equivalent to the Drinfeld center of the standard invariant, where $M_{\infty}$ is the inductive limit of the associated Jones tower. This implies that for any pair of finite depth non-Gamma subfactors $N_{0}\subseteq N_{1}$ and $M_{0}\subseteq M_{1}$, if the standard invariants are not Morita equivalent, then the inductive limit factors $N_{\infty}$ and $M_{\infty}$ are not stably isomorphic.

math.OA↗

arXiv2021

Federated Learning on Non-IID Data Silos: An Experimental Study

Due to the increasing privacy concerns and data regulations, training data have been increasingly fragmented, forming distributed databases of multiple "data silos" (e.g., within different organizations and countries). To develop effective machine learning services, there is a must to exploit data from such distributed databases without exchanging the raw data. Recently, federated learning (FL) has been a solution with growing interests, which enables multiple parties to collaboratively train a machine learning model without exchanging their local data. A key and common challenge on distributed databases is the heterogeneity of the data distribution among the parties. The data of different parties are usually non-independently and identically distributed (i.e., non-IID). There have been many FL algorithms to address the learning effectiveness under non-IID data settings. However, there lacks an experimental study on systematically understanding their advantages and disadvantages, as previous studies have very rigid data partitioning strategies among parties, which are hardly representative and thorough. In this paper, to help researchers better understand and study the non-IID data setting in federated learning, we propose comprehensive data partitioning strategies to cover the typical non-IID data cases. Moreover, we conduct extensive experiments to evaluate state-of-the-art FL algorithms. We find that non-IID does bring significant challenges in learning accuracy of FL algorithms, and none of the existing state-of-the-art FL algorithms outperforms others in all cases. Our experiments provide insights for future studies of addressing the challenges in "data silos".

cs.LG↗

arXiv2021

Boosting Image Outpainting with Semantic Layout Prediction

The objective of image outpainting is to extend image current border and generate new regions based on known ones. Previous methods adopt generative adversarial networks (GANs) to synthesize realistic images. However, the lack of explicit semantic representation leads to blurry and abnormal image pixels when the outpainting areas are complex and with various objects. In this work, we decompose the outpainting task into two stages. Firstly, we train a GAN to extend regions in semantic segmentation domain instead of image domain. Secondly, another GAN model is trained to synthesize real images based on the extended semantic layouts. The first model focuses on low frequent context such as sizes, classes and other semantic cues while the second model focuses on high frequent context like color and texture. By this design, our approach can handle semantic clues more easily and hence works better in complex scenarios. We evaluate our framework on various datasets and make quantitative and qualitative analysis. Experiments demonstrate that our method generates reasonable extended semantic layouts and images, outperforming state-of-the-art models.

cs.CV↗

arXiv2021

Characterizing and Demystifying the Implicit Convolution Algorithm on Commercial Matrix-Multiplication Accelerators

Many of today's deep neural network accelerators, e.g., Google's TPU and NVIDIA's tensor core, are built around accelerating the general matrix multiplication (i.e., GEMM). However, supporting convolution on GEMM-based accelerators is not trivial. The naive method explicitly lowers the convolution to GEMM, commonly known as im2col, which introduces significant performance and memory overhead. Existing implicit im2col algorithms require unscalable hardware and are inefficient in supporting important convolution variants such as strided convolution. In this paper, we propose a memory-efficient and hardware-friendly implicit im2col algorithm used by Google's TPU, which dynamically converts a convolution into a GEMM with practically zero performance and memory overhead, fully unleashing the power of GEMM engines. Through comprehensive experimental results, we quantitatively argue that this algorithm has been adopted in commercial closed-source platforms, and we are the first to describe its high-level idea and implementation details. Finally, we show that our algorithm can also be generally applied to Nvidia's Tensor Cores (TC), matching and out-performing the measured performance on TCs.

cs.DC↗

arXiv2021

A Fast Method for Steady-State Memristor Crossbar Array Circuit Simulation

In this work we propose an effective preconditioning technique to accelerate the steady-state simulation of large-scale memristor crossbar arrays (MCAs). We exploit the structural regularity of MCAs to develop a specially-crafted preconditioner that can be efficiently evaluated utilizing tensor products and block matrix inversion. Numerical experiments demonstrate the efficacy of the proposed technique compared to mainstream preconditioners.

cs.ET↗

arXiv2021

Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selection

Federated learning (FL) is a distributed machine learning paradigm that allows clients to collaboratively train a model over their own local data. FL promises the privacy of clients and its security can be strengthened by cryptographic methods such as additively homomorphic encryption (HE). However, the efficiency of FL could seriously suffer from the statistical heterogeneity in both the data distribution discrepancy among clients and the global distribution skewness. We mathematically demonstrate the cause of performance degradation in FL and examine the performance of FL over various datasets. To tackle the statistical heterogeneity problem, we propose a pluggable system-level client selection method named Dubhe, which allows clients to proactively participate in training, meanwhile preserving their privacy with the assistance of HE. Experimental results show that Dubhe is comparable with the optimal greedy method on the classification accuracy, with negligible encryption and communication overhead.

cs.CR↗

arXiv2021

Pagurus: Eliminating Cold Startup in Serverless Computing with Inter-Action Container Sharing

Serverless computing provides fine-grain resource sharing between Cloud tenants through containers. Each function invocation (action) runs in an individual container. When there is not an already started container for a user function, a new container has to be created for it. However, the long cold startup time of a container results in the long response latency of the action. Our investigation shows that the containers for some user actions share most of the software packages. If an action that requires a new container can ``borrow'' a similar warm container from other actions, the long cold startup can be eliminated. Based on the above finding, we propose Pagurus, a runtime container management system for eliminating the cold startup in serverless computing. Pagurus is comprised of an inter-action container scheduler and an intra-action container scheduler for each action. The inter-action container scheduler schedules shared containers among actions. The intra-action container scheduler deals with the management of the container lifecycle. Our experimental results show that Pagurus effectively eliminates the time-consuming container cold startup. An action may start to run in 10ms with Pagurus, even if there is not warm container for it.

cs.DC↗

arXiv2021

Q-system completion is a 3-functor

Q-systems are unitary versions of Frobenius algebra objects which appeared in the theory of subfactors. In recent joint work with R. Hernández Palomares and C. Jones, the authors defined a notion of Q-system completion for C*/W* 2-categories, which is a unitary version of a higher idempotent completion in the spirit of Douglas--Reutter and Gaiotto--Johnson-Freyd. In this article, we prove that Q-system completion is a dagger 3-functor on the dagger 3-category of C*/W* 2-categories. We also prove that Q-system completion satisfies a universal property analogous to the universal property satisfied by idempotent completion for 1-categories.

math.QA↗

arXiv2021

FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation

Learning convolutional neural networks (CNNs) with low bitwidth is challenging because performance may drop significantly after quantization. Prior arts often discretize the network weights by carefully tuning hyper-parameters of quantization (e.g. non-uniform stepsize and layer-wise bitwidths), which are complicated and sub-optimal because the full-precision and low-precision models have a large discrepancy. This work presents a novel quantization pipeline, Frequency-Aware Transformation (FAT), which has several appealing benefits. (1) Rather than designing complicated quantizers like existing works, FAT learns to transform network weights in the frequency domain before quantization, making them more amenable to training in low bitwidth. (2) With FAT, CNNs can be easily trained in low precision using simple standard quantizers without tedious hyper-parameter tuning. Theoretical analysis shows that FAT improves both uniform and non-uniform quantizers. (3) FAT can be easily plugged into many CNN architectures. When training ResNet-18 and MobileNet-V2 in 4 bits, FAT plus a simple rounding operation already achieves 70.5% and 69.2% top-1 accuracy on ImageNet without bells and whistles, outperforming recent state-of-the-art by reducing 54.9X and 45.7X computations against full-precision models. We hope FAT provides a novel perspective for model quantization. Code is available at \url{https://github.com/ChaofanTao/FAT_Quantization}.

cs.CV↗

arXiv2020

Edge Computing Assisted Autonomous Flight for UAV: Synergies between Vision and Communications

Autonomous flight for UAVs relies on visual information for avoiding obstacles and ensuring a safe collision-free flight. In addition to visual clues, safe UAVs often need connectivity with the ground station. In this paper, we study the synergies between vision and communications for edge computing-enabled UAV flight. By proposing a framework of Edge Computing Assisted Autonomous Flight (ECAAF), we illustrate that vision and communications can interact with and assist each other with the aid of edge computing and offloading, and further speed up the UAV mission completion. ECAAF consists of three functionalities that are discussed in detail: edge computing for 3D map acquisition, radio map construction from the 3D map, and online trajectory planning. During ECAAF, the interactions of communication capacity, video offloading, 3D map quality, and channel state of the trajectory form a positive feedback loop. Simulation results verify that the proposed method can improve mission performance by enhancing connectivity. Finally, we conclude with some future research directions.

cs.NI↗

arXiv2020

DLFusion: An Auto-Tuning Compiler for Layer Fusion on Deep Neural Network Accelerator

Many hardware vendors have introduced specialized deep neural networks (DNN) accelerators owing to their superior performance and efficiency. As such, how to generate and optimize the code for the hardware accelerator becomes an important yet less explored problem. In this paper, we perform the compiler-stage optimization study using a novel and representative Cambricon DNN accelerator and demonstrate that the code optimization knobs play an important role in unleashing the potential of hardware computational horsepower. However, even only two studied code optimization knobs, namely the number of cores and layer fusion scheme, present an enormous search space that prevents the naive brute-force search. This work introduces a joint, auto-tuning optimization framework to address this challenge. We first use a set of synthesized DNN layers to study the interplay between the hardware performance and layer characteristics. Based on the insights, we extract the operation count and feature map channel size as each layer's characteristics and derive a joint optimization strategy to decide the performance-optimal core number and fusion scheme. We evaluate the performance of the proposed approach using a set of representative DNN models and show that it achieves the minimal of 3.6x and the maximal of 7.9x performance speedup compared to no optimization baseline. We also show that the achieved speedup is close to the oracle case that is based on a reduced brute-force search but with much less search time.

cs.DC↗