检索结果-内蒙古大学图书馆

2023 ACM/SIGMOD International Conference on Management of data, SIGMOD 2023

作者： Wang, Jue Chen, Ke Shou, Lidan Jiang, Dawei Chen, Gang Key Lab of Intelligent Computing Based Big Data of Zhejiang Province Zhejiang University Hangzhou China

ISBN: (纸本)9781450395076

Deep learning models, particularly pre-trained language models (PLMs), have become increasingly important for a variety of applications that require text/language processing. However, these models are resource-intensive and often require costly hardware such as dedicated GPU servers. In response to this issue, we present SMILE, a novel prototype system for efficient deployment and management of such models in the cloud. Our goal is to build a cloud platform from which tenants can easily derive their own custom models, and rent PLM processors to run inference services on these models at reduced costs. To facilitate this, we present a co-design of cost-effective storage and computation scheme for managing massive customized PLMs with constrained hardware resources via effective resource sharing and multiplexing. Our system consists of four core components: vPLM creator, vPLM storage appliance, vPLM trainer, and vPLM processor, which allow tenants to easily create, store, train, and use their customized PLM in the cloud without the need for dedicated hardware or maintenance. In particular, vPLM processors are virtualized from a physical machine, and are designed to have a multi-tenant nature, enabling efficient utilization of resources by precomputing the intermediate representation of PLMs and using adapters to provide customization instead of training the entire model. This allows tenants to host their PLMs in the cloud at minor costs. In our demonstration, we show that over 10,000 models can be hosted on one single machine without compromising the inference speed and accuracy. Overall, our system provides a convenient and cost-effective solution for tenants to host and manage PLMs in the cloud for their customized tasks. © 2023 ACM.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Complementary label Queries for Efficient Active Learning 23

Complementary Label Queries for Efficient Active Learning

引用

6th International Conference on Image and Graphics Processing, ICIGP 2023

作者： Liu, Shengyuan Hu, Tianlei Chen, Ke Mao, Yunqing Key Lab of Intelligent Computing Based Big Data of Zhejiang Province Zhejiang University China Co. Ltd. China

ISBN: (纸本)9781450398572

Many active learning methods are based on the assumption that a learner simply asks for the true labels of some training data from annotators. Unfortunately, it is expensive to exactly annotate instances in real-world classification tasks. To mitigate this problem, we propose a novel active learning setting, named active learning with complementary labels (ALCL). The ALCL learners only ask yes/no questions in some classes. After receiving answers from annotators, ALCL learners get a few supervised data and more training instances with complementary labels, which only specify one of the classes to which the pattern does not belong. There are two challenging issues in ALCL: the first is how to learn from these complementary labels, and another is how to sample instances to be queried. For the first issue, we propose a novel method that redistributes the weights of instances based on the balance of category contribution to learn from ordinary labels and complementary labels. For the second issue, we propose a weighting mechanism to improve existing uncertainty-based sampling strategies under this novel setup. Experiments on various datasets demonstrate the feasibility of ALCL and the superiority of our approaches. © 2023 ACM.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Complex integrity constraint discovery: measuring trust in modern intelligent railroad systems

引用

Journal of zhejiang University-Science A(Applied Physics & Engineering) 2022年第10期23卷 832-837页

作者： Wen-tao HU Da-wei JIANG Sai WU Ke CHEN Gang CHEN Key Lab of Intelligent Computing Based Big Data of Zhejiang Province Zhejiang UniversityHangzhou 310027China

1Introduction data are at the heart of intelligent rail systems in the high-speed transportation sector(Zhou et al.,2020;Ho et al.,2021;Hu et al.,2021;Chen et al.,2022).The core of modern intelligent railroad systems typically includes rail transportation and equipment monitoring models learned from large datasets,which are often optimized for specific data and workloads(Zhu et al.,2019;Tan et al.,2020).While these intelligent railroad systems have been widely adopted and successful,their reliability and proper function will change as the data used *** the data used(on which the system operates)deviates from the fundamental constraints of the initial data(on which the system is trained)then,in that case,the system performance degrades,and the results inferred by the system model become unreliable,so the system model must be retrained and redeployed to re-store reliable inference results(Sharma and Chandel,2013).The mechanism for assessing the trustworthiness of intelligent rail system inferences is of paramount importance,especially for rail systems performing safety-critical or high-impact operations.

关键词： constraint intelligent operations

来源：评论

学校读者我要写书评

暂无评论

LeapGNN: Accelerating Distributed GNN Training Leveraging Feature-Centric Model Migration 23

LeapGNN: Accelerating Distributed GNN Training Leveraging Fe...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Chen, Weijian He, Shuibing Qu, Haoyang Zhang, Xuechen The State Key Laboratory of Blockchain and Data Security Zhejiang University China Zhejiang Lab China Institute of Blockchain and Data Security China Zhejiang Key Laboratory of Big Data Intelligent Computing China Washington State University Vancouver United States

ISBN: (纸本)9781939133458

Distributed training of graph neural networks (GNNs) has become a crucial technique for processing large graphs. Prevalent GNN frameworks are model-centric, necessitating the transfer of massive graph vertex features to GNN models, which leads to a significant communication bottleneck. Recognizing that the model size is often significantly smaller than the feature size, we propose LeapGNN, a feature-centric framework that reverses this paradigm by bringing GNN models to vertex features. To make it truly effective, we first propose a micrograph-based training strategy that leverages a refined structure to enhance locality, combined with the model migration technique, to minimize remote feature retrieval. Then, we devise a feature pre-gathering approach that merges multiple fetch operations into a single one to eliminate redundant feature transmissions. Finally, we employ a micrograph-based merging method that adjusts the number of micrographs for each worker to minimize kernel switches and synchronization overhead. Our experimental results demonstrate that LeapGNN achieves a performance speedup of up to 4.2× compared to the state-of-the-art method, namely P3 © 2025 FAST. All Rights Reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Uncertainty-aware complementary label queries for active learning

引用

Frontiers of Information Technology & Electronic Engineering 2023年第10期24卷 1497-1503页

作者： Shengyuan LIU Ke CHEN Tianlei HU Yunqing MAO Key Lab of Intelligent Computing Based Big Data of Zhejiang Province Zhejiang UniversityHangzhou 310027China State Key Laboratory of Blockchain and Data Security Zhejiang UniversityHangzhou 310027China City Cloud Technology(China)Co. Ltd.Hangzhou 310000China

Many active learning methods assume that a learner can simply ask for the full annotations of some training data from *** methods mainly try to cut the annotation costs by minimizing the number of annotation ***,annotating instances exactly in many realworld classification tasks is still *** reduce the cost of a single annotation action,we try to tackle a novel active learning setting,named active learning with complementary labels(ALCL).ALCL learners ask only yes/no questions in some *** receiving answers from annotators,ALCL learners obtain a few supervised instances and more training instances with complementary labels,which specify only one of the classes to which the pattern does not *** are two challenging issues in ALCL:one is how to sample instances to be queried,and the other is how to learn from these complementary labels and ordinary accurate *** the first issue,we propose an uncertainty-based sampling strategy under this novel setup.

关键词： complementary instance ordinary

来源：评论

学校读者我要写书评

暂无评论

Dual Enhancement for Multi-label Learning with Missing labels 21

Dual Enhancement for Multi-Label Learning with Missing Label...

引用

4th International Conference on Machine Learning and Machine Intelligence, MLMI 2021

作者： Liu, Shengyuan Wang, Haobo Hu, Tianlei Chen, Ke Key Lab of Intelligent Computing Based Big Data of Zhejiang Province College of Computer Science and Technology Zhejiang University China

ISBN: (纸本)9781450384247

The goal of multi-label learning with missing labels (MLML) is assigning each testing instance multiple labels given training instances that have a partial set of labels. The most challenging issue is to complete the missing labels by leveraging input signals and given labels. Existing methods usually complete missing entries by utilizing label correlation, which, however, overlook knowledge from the object itself. To tackle this problem, we propose a dual enhancement framework that enhances missing entries from the label- perspective and instance-perspective. First, we develop a Long Short-Term Memory (LSTM) network that utilizes sequential label correlations to complete missing labels. Second, we expand the training dataset via a MixUp procedure to further enhance the label confidence. Extensive experiments on three multi-label image datasets clearly verify the superiority of our proposed method to the baselines. © 2021 ACM.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerators 31

GoPIM: GCN-Oriented Pipeline Optimization for PIM Accelerato...

引用

31st IEEE International Symposium on High Performance Computer Architecture, HPCA 2025

作者： Yang, Siling He, Shuibing Wang, Wenjiong Yin, Yanlong Wu, Tong Chen, Weijian Zhang, Xuechen Sun, Xian-He Feng, Dan The State Key Laboratory of Blockchain and Data Security Zhejiang University China Zhejiang Lab China Institute of Blockchain and Data Security China Zhejiang Key Laboratory of Big Data Intelligent Computing China Washington State University Vancouver United States Illinois Institute of Technology United States Huazhong University of Science and Technology China Wuhan National Laboratory for Optoelectronics China

ISBN: (纸本)9798331506476

Graph convolutional networks (GCNs) are popular for a variety of graph learning tasks. ReRAM-based processing-in-memory (PIM) accelerators are promising to expedite GCN training owing to their in-situ computing capability. However, existing accelerators can be severely underutilized even with pipelines, due to the oversight of the skewed execution times of various GCN stages and the ignorance of skewed degrees of graph vertices. In this work, we propose GOPIM, a GCN-oriented pipeline optimization for PIM accelerators to expedite GCN training. First, GOPIM proposes an ML-based scheme that allocates crossbar resources to the most needed stages to streamline the overall pipeline. Second, GOPIM utilizes a selective vertex updating technique that evenly distributes vertices on crossbars by interleaved mapping. These techniques collectively reduce the overall execution time without losing much accuracy. We also provide a practical architecture design for GOPIM. Our experimental results show that, GoPIM achieves up to 191 × speedup and 16.1 × energy saving, compared to the state-of-the-art work. © 2025 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Byzantine-Robust Learning on Heterogeneous data via Gradient Splitting

arXiv

引用

arXiv 2023年

作者： Liu, Yuchen Chen, Chen Lyu, Lingjuan Wu, Fangzhao Wu, Sai Chen, Gang Key Lab of Intelligent Computing Based Big Data of Zhejiang Province Zhejiang University Hangzhou China Sony AI United States Microsoft United States

Federated learning has exhibited vulnerabilities to Byzantine attacks, where the Byzantine attackers can send arbitrary gradients to a central server to destroy the convergence and performance of the global model. A wealth of robust AGgregation Rules (AGRs) have been proposed to defend against Byzantine attacks. However, Byzantine clients can still circumvent robust AGRs when data is non-Identically and Independently Distributed (non-IID). In this paper, we first reveal the root causes of performance degradation of current robust AGRs in non-IID settings: the curse of dimensionality and gradient heterogeneity. In order to address this issue, we propose GAS, a GrAdient Splitting approach that can successfully adapt existing robust AGRs to non-IID settings. We also provide a detailed convergence analysis when the existing robust AGRs are combined with GAS. Experiments on various real-world datasets verify the efficacy of our proposed GAS. The implementation code is provided in https://***/YuchenLiu-a/byzantine-gas. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

SPA: a graph spectral alignment perspective for domain adaptation 23

SPA: a graph spectral alignment perspective for domain adapt...

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Zhiqing Xiao Haobo Wang Ying Jin Lei Feng Gang Chen Fei Huang Junbo Zhao College of Computer Science and Technology Zhejiang University and Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University School of Software Technology Zhejiang University and Key Lab of Intelligent Computing based Big Data of Zhejiang Province Zhejiang University CUHK-SenseTime Joint Lab The Chinese University of Hong Kong School of Computer Science and Engineering Nanyang Technological University Alibaba Group

Unsupervised domain adaptation (UDA) is a pivotal form in machine learning to extend the in-domain model to the distinctive target domains where the data distributions differ. Most prior works focus on capturing the inter-domain transferability but largely overlook rich intra-domain structures, which empirically results in even worse discriminability. In this work, we introduce a novel graph SPectral Alignment (SPA) framework to tackle the tradeoff. The core of our method is briefly condensed as follows: (i)-by casting the DA problem to graph primitives, SPA composes a coarse graph alignment mechanism with a novel spectral regularizer towards aligning the domain graphs in eigenspaces; (ii)-we further develop a finegrained message propagation module — upon a novel neighbor-aware self-training mechanism — in order for enhanced discriminability in the target domain. On standardized benchmarks, the extensive experiments of SPA demonstrate that its performance has surpassed the existing cutting-edge DA methods. Coupled with dense model analysis, we conclude that our approach indeed possesses superior efficacy, robustness, discriminability, and transferability. Code and data are available at: https://***/CrownX/SPA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reliability Analysis of Heterogeneous Sensor-Cloud Systems against Targeted Attacks

引用

China Communications 2022年第8期19卷 181-197页

作者： Hao Peng Zhen Qian Guangquan Xu Kejie Mao Kangtian Li Dandan Zhao Department of Computer Science and Engineering Zhejiang Normal UniversityJinhua Zhejiang 321004China Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal UniversityJinhua Zhejiang 321004China The Big Data School Qingdao Huanghai UniversityQingdao Shandong 266427China College of Intelligence and Computing Tianjin UniversityTianjin 300072China

based on the wide application of cloud computing and wireless sensor networks in various fields,the Sensor-Cloud System(SCS)plays an indispensable role between the physical world and the network ***,due to the close connection and interdependence between the physical resource network and computing resource network,there are security problems such as cascading failures between systems in the *** this paper,we propose a model with two interdependent networks to represent a sensor-cloud ***,based on the percolation theory,we have carried out a formulaic theoretical analysis of the whole process of cascading *** the system’s subnetwork presents a steady state where there is no further collapse,we can obtain the largest remaining connected subgroup components and the penetration ***,this result is the critical maximum that the coupled SCS can *** verify the correctness of the theoretical results,we further carried out actual simulation *** results show that a scale-free network priority attack’s percolation threshold is always less than that of ER network which is priority ***,when the scale-free network is attacked first,adding the power law exponentλcan be more intuitive and more effective to improve the network’s reliability.

关键词： sensor-cloud systems targeted attacks heterogeneous networks reliability analysis system security

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：