检索结果-内蒙古大学图书馆

ScalabFS: A scalable BFS accelerator on HBM-enhanced FPGAs

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Li, Kexin Liu, Chenhao Shao, Zhiyuan Wang, Zeke Wu, Minkang Chen, Jiajie Liao, Xiaofei Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan30074 China Collaborative Innovation Center of Artificial Intelligence Zhejiang University China

High Bandwidth Memory (HBM) provides massive aggregated memory bandwidth by exposing multiple memory channels to the processing units. To achieve high performance, an accelerator built on top of an FPGA configured with HBM (i.e., FPGA-HBM platform) needs to scale its performance according to the available memory channels. In this paper, we propose an accelerator for BFS (Breadth-First Search) algorithm, named as ScalabFS, that builds multiple processing elements to sufficiently exploit the high bandwidth of HBM to improve efficiency. We implement the prototype system of ScalabFS and conduct BFS in both real-world and synthetic scale-free graphs on Xilinx Alveo U280 FPGA card real hardware. The experimental results show that ScalabFS scales its performance almost linearly according to the available memory pseudo channels (PCs) from the HBM2 subsystem of U280. By fully using the 32 PCs and building 64 processing elements (PEs) on U280, ScalabFS achieves a performance up to 19.7 GTEPS (Giga Traversed Edges Per Second). When conducting BFS in sparse real-world graphs, ScalabFS achieves equivalent GTEPS to Gunrock running on the state-of-art Nvidia V100 GPU that features 64-PC HBM2 (twice memory bandwidth than U280). Copyright © 2021, The Authors. All rights reserved.

关键词： Field programmable gate arrays (FPGA)

From Continuity to Editability: Inverting GANs with Consecutive Images

学校读者我要写书评

暂无评论

From Continuity to Editability: Inverting GANs with Consecut...

International Conference on Computer Vision (ICCV)

作者： Yangyang Xu Yong Du Wenpeng Xiao Xuemiao Xu Shengfeng He South China University of Technology Ocean University of China Guangdong Provincial Key Lab of Computational Intelligence and Cyberspace Information State Key Laboratory of Subtropical Building Science Ministry of Education Key Laboratory of Big Data and Intelligent Robot

ISBN: (纸本)9781665428132

Existing GAN inversion methods are stuck in a paradox that the inverted codes can either achieve high-fidelity reconstruction, or retain the editing capability. Having only one of them clearly cannot realize real image editing. In this paper, we resolve this paradox by introducing consecutive images (e.g., video frames or the same person with different poses) into the inversion process. The rationale behind our solution is that the continuity of consecutive images leads to inherent editable directions. This inborn property is used for two unique purposes: 1) regularizing the joint inversion process, such that each of the inverted codes is semantically accessible from one of the other and fastened in an editable domain; 2) enforcing inter-image coherence, such that the fidelity of each inverted code can be maximized with the complement of other images. Extensive experiments demonstrate that our alternative significantly outperforms state-of-the-art methods in terms of reconstruction fidelity and editability on both the real image dataset and synthesis dataset. Furthermore, our method provides the first support of video-based GAN inversion and an interesting application of unsupervised semantic transfer from consecutive images. Source code can be found at: https://***/cnnlstm/InvertingGANs_with_ConsecutiveImgs.

关键词： Computer vision Codes Image resolution Semantics Coherence Image reconstruction

EdgeDis: Enabling Fast, Economical, and Reliable data Dissemination for Mobile Edge Computing

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Bo He, Qiang Chen, Feifei Lyu, Lingjuan Bouguettaya, Athman Yang, Yun The College of Arts Business Law Education and Information Technology Victoria University MelbourneVIC3122 Australia The National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab. Cluster and Grid Computing Lab. School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China The Department of Computing Technologies Swinburne University of Technology MelbourneVIC3122 Australia The School of Information Technology Deakin University Geelong Australia SONY AI Inc. Tokyo108-0075 Japan The School of Computer Science University of Sydney CamperdownNSW2006 Australia

Mobile edge computing (MEC) enables web data caching in close geographic proximity to end users. Popular data can be cached on edge servers located less than hundreds of meters away from end users. This ensures bounded latency guarantees for various latency-sensitive web applications. However, transmitting a large volume of data out of the cloud onto many geographically-distributed web servers individually can be expensive. In addition, web content dissemination may be interrupted by various intentional and accidental events in the volatile MEC environment, which undermines dissemination efficiency and subsequently incurs extra transmission costs. To tackle the above challenges, we present a novel scheme named EdgeDis that coordinates data dissemination by distributed consensus among those servers. We analyze EdgeDis’s validity theoretically and evaluate its performance experimentally. Results demonstrate that compared with baseline and state-of-the-art schemes, EdgeDis: 1) is 5.97x - 7.52x faster;2) reduces dissemination costs by 48.21% to 91.87%;and 3) reduces performance loss caused by dissemination failures by up to 97.30% in time and 96.35% in costs. © 2023, CC BY-NC-SA.

关键词： Efficiency

Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. The School of Information Technology Jiangxi University of Finance and Economics Nanchang330013 China The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Lab. School of Electrical and Electronic Engineering Nanyang Technology University Singapore The Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The China-Singapore International Joint Research Institute Singapore

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. One possible reason is that fully fine-tuned ViT-based models may disrupt the pre-trained features [1], [2] and overfit to some data-specific patterns [3]. To alleviate this issue, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. The code and trained model have been released at: https://***/LoveSiameseCat/FAViT. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

Towards Unified Token Learning for Vision-Language Tracking

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Yaozong Zhong, Bineng Liang, Qihua Li, Guorong Ji, Rongrong Li, Xianxian The Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China The Guangxi Key Laboratory of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China The School of Computer Science and Technology Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China Media Analytics and Computing Lab Department of Artificial Intelligence School of Informatics Xiamen University 361005 China

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed MMTrack, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticated prior designs, making them over-specialize on the features of specific architectures or mechanisms. In contrast, our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target in an auto-regressive manner. The design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling and allowing our tracker to use a simple cross-entropy loss as unified optimization objective for VL tracking task. Extensive experiments on TNL2K, LaSOT, LaSOText and OTB99-Lang benchmarks show that our approach achieves promising results, compared to other state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

Graph-based multi-hop reasoning for long text generation

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhao, Liang Xu, Jingjing Lin, Junyang Zhang, Yichang Yang, Hongxia Sun, Xu Center for Data Science Beijing Institute of Big Data Research Peking University China MOE Key Lab of Computational Linguistics School of EECS Peking University China Alibaba Group

Long text generation is an important but challenging task. The main problem lies in learning sentence-level semantic dependencies which traditional generative models often suffer from. To address this problem, we propose a Multi-hop Reasoning Generation (MRG) approach that incorporates multi-hop reasoning over a knowledge graph to learn semantic dependencies among sentences. MRG consists of two parts, a graph-based multi-hop reasoning module and a path-aware sentence realization module. The reasoning module is responsible for searching skeleton paths from a knowledge graph to imitate the imagination process in the human writing for semantic transfer. Based on the inferred paths, the sentence realization module then generates a complete sentence. Unlike previous black-box models, MRG explicitly infers the skeleton path, which provides explanatory views to understand how the proposed model works. We conduct experiments on three representative tasks, including story generation, review generation, and product description generation. Automatic and manual evaluation show that our proposed method can generate more informative and coherent long text than strong baselines, such as pre-trained models (e.g. GPT-2) and knowledge-enhanced models. Copyright © 2020, The Authors. All rights reserved.

关键词： Knowledge graph

Multi-Interactive Attention Network for fine-grained feature learning in CTR prediction

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Kai Qian, Hao Cui, Qing Liu, Qi Li, Longfei Zhou, Jun Ma, Jianhui Chen, Enhong Anhui Province Key Lab of Big Data Analysis and Application School of Data Science University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China Ant Group Hangzhou China

In the Click-Through Rate (CTR) prediction scenario, user's sequential behaviors are well utilized to capture the user interest in the recent literature. However, despite being extensively studied, these sequential methods still suffer from three limitations. First, existing methods mostly utilize attention on the behavior of users, which is not always suitable for CTR prediction, because users often click on new products that are irrelevant to any historical behaviors. Second, in the real scenario, there are numerous users that have operations a long time ago, but turn relatively inactive in recent times. Thus, it is hard to precisely capture user's current preferences through early behaviors. Third, multiple representations of user's historical behaviors in different feature subspaces are largely ignored. To remedy these issues, we propose a Multi-Interactive Attention Network (MIAN) to comprehensively extract the latent relationship among all kinds of fine-grained features (e.g., gender, age and occupation in user-profile). Specifically, MIAN contains a Multi-Interactive Layer (MIL) that integrates three local interaction modules to capture multiple representations of user preference through sequential behaviors and simultaneously utilize the fine-grained user-specific as well as context information. In addition, we design a Global Interaction Module (GIM) to learn the high-order interactions and balance the different impacts of multiple features. Finally, Offline experiment results from three datasets, together with an Online A/B test in a large-scale recommendation system, demonstrate the effectiveness of our proposed approach. © 2020, CC BY.

关键词： User profile

Multi-resource fair allocation for cloud federation 21

学校读者我要写书评

暂无评论

Multi-resource fair allocation for cloud federation

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on data science and Systems, HPCC/SmartCity/DSS 2019

作者： Zhang, Gengwei Lu, Runhao Wu, Weigang School of Data and Computer Science Sun Yet-Sen University Guangzhou China Guangdong Province Key Lab. of Big Data Analysis and Processing Sun Yet-Sen University Guangzhou China

ISBN: (纸本)9781728120584

Since the number of tasks submitted by user changes with time, the cloud data center cannot meet all resource requests in time when the load is high, and the idle resources are not effectively utilized at low load. Cloud federation can be established to share resources between different Cloud Service Providers (CSPs), enabling load balance between clouds. CSPs in the cloud federation are independent and their individual benefit need to be guaranteed when sharing resources with others. In this paper, we establish a two-level asynchronous scheduling model within and between the clouds, and introduce high priority queues in the cloud to prioritize the tasks sent by the federation scheduler. Due to the heterogeneity of resource requirements of user tasks, we design two multi-resource fair scheduling algorithms for cloud and federation. Within the cloud, we add the dynamically adjusted weighting factor to the Dominant Resource Fairness (DRF) to increase the priority of user whose task is outsourced. We define the dominant share and dominant contribution of the cloud. The priority of the cloud is the difference between the dominant share and the dominant contribution, which ensure the incentive and fairness of the cloud. Based on the open source container management system Kubernetes, we develop a cloud federation prototype system to implement our algorithm, and conduct performance evaluations through experiments. The results show that, compared with the existing fair allocation algorithm, the multi-resource fair allocation mechanism proposed in this paper can guarantee users' QoS of each CSP. © 2019 IEEE.

关键词： Scheduling

DSGD-CECA: Decentralized SGD with Communication-Optimal Exact Consensus Algorithm

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ding, Lisang Jin, Kexin Ying, Bicheng Yuan, Kun Yin, Wotao Department of Mathematics University of California Los AngelesCA United States Department of Mathematics Princeton University PrincetonNJ United States Google Inc. Los AngelesCA United States Center for Machine Learning Research Peking University Beijing China AI for Science Institute Beijing China National Engineering Labratory for Big Data Analytics and Applications Beijing China Decision Intelligence Lab. Alibaba US BellevueWA United States

Decentralized Stochastic Gradient Descent (SGD) is an emerging neural network training approach that enables multiple agents to train a model collaboratively and simultaneously. Rather than using a central parameter server to collect gradients from all the agents, each agent keeps a copy of the model parameters and communicates with a small number of other agents to exchange model updates. Their communication, governed by the communication topology and gossip weight matrices, facilitates the exchange of model updates. The state-of-the-art approach uses the dynamic one-peer exponential-2 topology, achieving faster training times and improved scalability than the ring, grid, torus, and hypercube topologies. However, this approach requires a power-of-2 number of agents, which is impractical at scale. In this paper, we remove this restriction and propose Decentralized SGD with Communication-optimal Exact Consensus Algorithm (DSGD-CECA), which works for any number of agents while still achieving state-of-the-art properties. In particular, DSGD-CECA incurs a unit per-iteration communication overhead and an Õ(n3) transient iteration complexity. Our proof is based on newly discovered properties of gossip weight matrices and a novel approach to combine them with DSGD’s convergence analysis. Numerical experiments show the efficiency of DSGD-CECA. Copyright © 2023, The Authors. All rights reserved.

关键词： Stochastic systems