检索结果-内蒙古大学图书馆

30th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2024

作者： Liang, Zheheng Zheng, Yingying Bi, Sheng Yao, Chaosheng Wang, Jiayan Xu, Lijie Ji, Shuping Wang, Wei Duan, Shikai Information Center Guangdong Power Grid Limited Liability Company Guangzhou China Joint Laboratory on Cyberspace Security China Southern Power Grid Guangzhou China State Key Lab of Computer Science at Iscas China University of Cas Beijing China Guangzhou Power Supply Bureau Guangzhou China University of Toronto Toronto Canada Nanjing Institute of Software Technology China University of Cas Nanjing China Ant Group-Payment Business Group Hangzhou China

ISBN: (纸本)9798331515966

Streaming graph computation has been widely applied in many fields, e.g., social network analysis and online product recommendation. However, existing streaming graph computation approaches still present limitations on accuracy and efficiency. To improve the accuracy, some distributed systems use the sequential graph update method based on an incremental computation model. However, these systems cannot handle the dynamic graph update concurrently. The speculation-based parallel updating model can parallelize the graph computation, however, it is restricted due to ignoring the original messages when updating a graph. Streaming graph computation usually requires high accuracy and low latency. As such, it is challenging to utilize incremental computation while simultaneously supplying concurrent processing *** overcome these challenges, in this paper, we first analyze a number of classical graph algorithms and summarize three principles that graph algorithms should satisfy in streaming scenarios. Based on these principles, we propose GraphFlow, a streaming graph computation model. GraphFlow achieves fast and accurate computation by utilizing incremental state update and propagation. To reduce the impact of concurrent update conflicts, GraphFlow provides a fine-grained lock based parallel update strategy. We implement GraphFlow framework and evaluate its performance and concurrent update conflict probability on real-world datasets. Meanwhile, we compare GraphFlow with two existing representative graph processing systems. Experimental results show GraphFlow achieves low latency and outperforms other graph processing systems given large datasets. © 2024 IEEE.

关键词： Data flow graphs

来源：评论

学校读者我要写书评

暂无评论

Lattice HIBE with Faster Trapdoor Delegation and Applications 22nd

Lattice HIBE with Faster Trapdoor Delegation and Application...

引用

22nd International Conference on Information and Communications Security, ICICS 2020

作者： Tang, Guofeng Qiu, Tian TCA Lab of State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China New Jersey Institute of Technology NewarkNJ United States

ISBN: (纸本)9783030610777

In this paper, we propose a lattice-based HIBE scheme in the standard model with faster trapdoor delegation. It is proven secure under the Learning With Errors assumption. Inspired by Canetti et al.’s transformation (Eurocrypt’03), an HIBE can be converted into a forward-secure public-key encryption (FS-PKE) scheme, and the efficiency of key update relies on the efficiency of trapdoor delegation. For applications, our HIBE with faster delegation can be used to generate a lattice-based FS-PKE with faster key update. Furthermore, we also obtain a lattice-based forward-secure signature (FSS) scheme combining HIBE-like key-update technique with Zhang et al.’s short signature construction in the standard model (Crypto’16). © 2020, Springer Nature Switzerland AG.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Automated Order Dispatching Strategies Design Using Genetic Programming for Dynamic Ridesharing Problem

Automated Order Dispatching Strategies Design Using Genetic ...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Chong-Jiong Fan Ya-Hui Jia Wei-Neng Chen State Key Laboratory of Subtropical Building and Urban Science School of Computer Science and Engineering South China University of Technology Guangzhou China School of Future Technology South China University of Technology Guangzhou China Pazhou Lab Guangzhou China

Ridesharing is a popular transportation mode and has become an important part of smart city development, which helps alleviate the pressure of urban travel. The ridesharing problem (RSP) is mainly to match drivers to suitable passengers. In practice, passengers appear dynamically, and the departure and the destination locations of these subsequent orders are unknown, resulting in the dynamic RSP (DRSP). To solve this dynamic optimization problem, this paper develops a new genetic programming hyperheuristic (GPHH) method to evolve order dispatching rules (ODRs), which can guide drivers to match suitable passengers in real time. The proposed GPHH method contains a heuristic template for simulation-based hyper-heuristic optimization. The experiment results show that the proposed GPHH method outperforms the state-of-the-art methods. Further analysis revealed some valuable insights, such as the generalizability of the generated rules and the impact of some features on the results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks

arXiv

引用

arXiv 2023年

作者： Chen, Shuo Liu, Boxiao Liu, Zeshi You, Haihang State Key Lab of Processors Institute of Computing Technology Chinese Academy of Science Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Zhongguancun Laboratory Beijing China Sensetime Research Beijing China

Spiking Neural Networks (SNNs) have gained significant attention due to the energy-efficient and multiplication-free characteristics. Despite these advantages, deploying large-scale SNNs on edge hardware is challenging due to limited resource availability. Network pruning offers a viable approach to compress the network scale and reduce hardware resource requirements for model deployment. However, existing SNN pruning methods cause high pruning costs and performance loss because they lack efficiency in processing the sparse spike representation of SNNs. In this paper, inspired by the critical brain hypothesis in neuroscience and the high biological plausibility of SNNs, we explore and leverage criticality to facilitate efficient pruning in deep SNNs. We firstly explain criticality in SNNs from the perspective of maximizing feature information entropy. Second, We propose a low-cost metric for assess neuron criticality in feature transmission and design a pruning-regeneration method that incorporates this criticality into the pruning process. Experimental results demonstrate that our method achieves higher performance than the current state-of-the-art (SOTA) method with up to 95.26% reduction of pruning cost. The criticality-based regeneration process efficiently selects potential structures and facilitates consistent feature representation. Copyright © 2023, The Authors. All rights reserved.

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Learning Multi-intersection Traffic Signal Control via Coevolutionary Multi-Agent Reinforcement Learning

TechRxiv

引用

TechRxiv 2023年

作者： Chen, Wubing Yang, Shangdong Li, Wenbin Hu, Yujing Liu, Xiao Gao, Yang The Department of Computer Science and Technology National Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China The School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China The State Key Lab. for Novel Software Technology Nanjing University Nanjing210023 China Netease Fuxi AI Lab Netease Zhejiang Hangzhou310025 China

Effective management of multi-intersection traffic signal control (MTSC) is vital for intelligent transportation systems. Multi-agent reinforcement learning (MARL) has shown promise in achieving MTSC. However, existing MARL-based MTSC algorithms have primarily focused on capturing the spatial relationship between multi-intersection traffic signals but have overlooking the importance of the temporally stable traffic pattern. This pattern refers to the fixed positions and relatively stable traffic flow between intersections over short periods in real-world MTSC scenarios, which indicates that the learned spatial relationships between traffic signals should co-evolve over time. To this end, we propose a novel algorithm called Coevolutionary Multi-Agent Reinforcement Learning (CoevoMARL). CoevoMARL employs a graph neural network to capture the complex spatial interaction network among traffic signals. Furthermore, we propose a relationship-driven progressive LSTM (RDP-LSTM) that dynamically evolves the learned spatial interaction network over time by leveraging insights from the temporally stable traffic pattern. To accelerate convergence, we also propose the mutual information reward optimization (MIRO) technique, which strengthens the correlation between policy learning and high-performance samples by using a mutual information-based intrinsic reward. Experimental results on both synthetic and real-world datasets demonstrate the superiority of CoevoMARL over existing MTSC algorithms, providing valuable insights into incorporating the temporally stable traffic pattern. © 2023, CC BY.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Survey of Integrating Generative Artificial Intelligence and 6G Mobile Services: Architectures, Solutions, Technologies and Outlooks

引用

IEEE Transactions on Cognitive Communications and Networking 2025年第3期11卷 1334-1356页

作者： Liu, Yi-Jing Du, Hongyang Xu, Xinyi Zhang, Ruichen Feng, Gang Cao, Bin Niyato, Dusit Kim, Dong In Jamalipour, Abbas Letaief, Khaled B. Tafazolli, Rahim University of Electronic Science and Technology of China National Key Lab on Wireless Communications Chengdu China University of Hong Kong Department of Electrical and Electronic Engineering Pok Fu Lam Hong Kong Nanyang Technological University College of Computing and Data Science Singapore Singapore Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing China Sungkyunkwan University Department of Electrical and Computer Engineering Suwon Korea Republic of University of Sydney School of Electrical and Computer Engineering Sydney Australia Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong University of Surrey Institute for Communication Systems School of Computer Science and Electronic Engineering United Kingdom

Generative artificial intelligence (GenAI) is rapidly driving a new phase of artificial intelligence revolution, marked by various applications such as ChatGPT, Sora and DeepSeek. With powerful capabilities in content generation, personalization and user interaction, GenAI can drive significant enhancements in various mobile services to satisfy individual user preferences. Meanwhile, mobile services offer substantial support for accessibility, functionality and intelligence of GenAI applications. However, current research on integrating GenAI and mobile services remains nascent, lacking necessary theoretical and technical support. In this survey, we break down a new vision to guide research on integrating GenAI and mobile services, aiming to improve 6G intelligence levels and enable 6G mobile networks to support the integration of GenAI and mobile services effectively. We begin by examining the necessity of integrating GenAI with 6G mobile services and exploring potential learning architectures of GenAI models within mobile networks. Next, we analyze potential solutions from two perspectives: how 6G mobile networks empower GenAI and how GenAI enables mobile services. We subsequently explore a promising use case, along with essential features and techniques, to facilitate the integration of GenAI and mobile services. Finally, we discuss future research directions, aiming at realizing intelligent 6G networks. © 2015 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

How to get better embeddings with code pre-trained models? An empirical study

arXiv

引用

arXiv 2023年

作者： Zhao, Yu Gong, Lina Zhang, Haoxiang Yu, Yaoshen Huang, Zhiqiu College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics State Key Lab for Novel Software Technology Nanjing University Key Laboratory of Safety-Critical Software Nanjing University of Aeronautics and Astronautics China Queen’s University KingstonON Canada

Pre-trained language models have demonstrated powerful capabilities in the field of natural language processing (NLP). Recently, code pretrained model (PTM), which draw from the experiences of the NLP field, have also achieved state-of-the-art results in many software engineering (SE) downstream tasks. These code PTMs take into account the differences between programming languages and natural languages during pre-training and make adjustments to pre-training tasks and input data. However, researchers in the SE community still inherit habits from the NLP field when using these code PTMs to generate embeddings for SE downstream classification tasks, such as generating semantic embeddings for code snippets through special tokens and inputting code and text information in the same way as pre-training the PTMs. In this paper, we empirically study five different PTMs (i.e. CodeBERT, CodeT5, PLBART, CodeGPT and CodeGen) with three different architectures (i.e. encoder-only, decoder-only and encoder-decoder) on four SE downstream classification tasks (i.e. code vulnerability detection, code clone detection, just-in-time defect prediction and function docstring mismatch detection) with respect to the two aforementioned aspects. Our experimental results indicate that (1) regardless of the architecture of the code PTMs used, embeddings obtained through special tokens do not sufficiently aggregate the semantic information of the entire code snippet;(2) the quality of code embeddings obtained by combing code data and text data in the same way as pretraining the PTMs is poor and cannot guarantee richer semantic information;(3) using the method that aggregates the vector representations of all code tokens, the decoder-only PTMs can obtain code embeddings with semantics as rich as or even better quality than those obtained from the encoder-only and encoder-decoder PTMs. Based on our findings, we recommend that researchers in the SE community (1) pay attention to the vector represen

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Cluster-guided Contrastive Class-imbalanced Graph Classification 39

Cluster-guided Contrastive Class-imbalanced Graph Classifica...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ju, Wei Mao, Zhengyang Yi, Siyu Qin, Yifang Gu, Yiyang Xiao, Zhiping Shen, Jianhao Qiao, Ziyue Zhang, Ming College of Computer Science Sichuan University Chengdu China School of Computer Science State Key Laboratory for Multimedia Information Processing PKU-Anker LLM Lab Peking University Beijing China College of Mathematics Sichuan University Chengdu China Paul G. Allen School of Computer Science and Engineering University of Washington Seattle WA United States Huawei Hisilicon Shanghai China School of Computing and Information Technology Great Bay University Dongguan China

ISBN: (纸本)157735897X

This paper studies the problem of class-imbalanced graph classification, which aims at effectively classifying the graph categories in scenarios with imbalanced class distributions. While graph neural networks (GNNs) have achieved remarkable success, their modeling ability on imbalanced graph-structured data remains suboptimal, which typically leads to predictions biased towards the majority classes. On the other hand, existing class-imbalanced learning methods in vision may overlook the rich graph semantic substructures of the majority classes and excessively emphasize learning from the minority classes. To address these challenges, we propose a simple yet powerful approach called C³GNN that integrates the idea of clustering into contrastive learning to enhance class-imbalanced graph classification. Technically, C³GNN clusters graphs from each majority class into multiple subclasses, with sizes comparable to the minority class, mitigating class imbalance. It also employs the Mixup technique to generate synthetic samples, enriching the semantic diversity of each subclass. Furthermore, supervised contrastive learning is used to hierarchically learn effective graph representations, enabling the model to thoroughly explore semantic substructures in majority classes while avoiding excessive focus on minority classes. Extensive experiments on real-world graph benchmark datasets verify the superior performance of our proposed method against competitive baselines. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Fairness-Aware Incentive Mechanism for Multi-Server Federated Learning in Edge-Enabled Wireless Networks with Differential Privacy

引用

IEEE Transactions on Mobile Computing 2025年

作者： Yang, Yu Peng, Kai Wang, Shangguang Xu, Xiaolong Xiao, Peiyun Leung, Victor C.M Huaqiao University College of Engineering Quanzhou362021 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Nanjing University of Information Science and Technology School of Software Nanjing China Nanjing University State Key Lab. for Novel Software Technology Nanjing210093 China Shenzhen University College of the Computer Science and Software Engineering Shenzhen518060 China University of British Columbia Department of Electrical and Computer Engineering VancouverBCV6T 1Z4 Canada

As a distributed machine learning method, federated learning (FL) can collaboratively train a global model with multiple devices without sharing the original data, thus protecting certain privacy. However, due to the strong heterogeneity of edge nodes (ENs) participating in FL, the quality of data uploaded to the parameter server (PS) varies significantly. Without an appropriate incentive mechanism, low-quality contributors may receive disproportionately high rewards, while high-quality contributors may lack sufficient motivation, leading to inefficient participation and suboptimal global model performance. Consequently, it is critical to develop an effective incentive mechanism to promote fairness for the FL process. To address the issues of existing FL incentive mechanisms lacking privacy protection performance analysis, we propose a fairness-aware incentive mechanism for multi-server FL in edge-enabled wireless differential privacy (DP) networks. Specifically, the wireless channel noise is used to provide DP protection for the local model gradients uploaded by ENs. Next, the interaction between the PSs and ENs is modeled as a Stackelberg game. Furthermore, we solve the Stackelberg game process using backward induction and theoretically propose optimal strategies for both the PSs and ENs. Finally, extensive numerical simulations using real datasets demonstrate the superior performance of our theoretical analysis of the proposed scheme. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adversarial Examples in the Physical World: A Survey

arXiv

引用

arXiv 2023年

作者： Wang, Jiakai Liu, Xianglong Hu, Jin Wang, Donghua Wu, Siyang Jiang, Tingsong Guo, Yuanfang Liu, Aishan Liu, Aishan Zhou, Jiantao Zhongguancun Laboratory Beijing China The College of Computer Science and Technology Zhejiang University Hangzhou China The State Key Lab of Software Development Environment Beihang University Beijing100191 China The Defense Innovation Institute Chinese Academy of Military Science Beijing China The Department of Computer and Information Science Faculty of Science and Technology University of Macau China

Deep neural networks (DNNs) have demonstrated high vulnerability to adversarial examples, raising broad security concerns about their applications. Besides the attacks in the digital world, the practical implications of adversarial examples in the physical world present significant challenges and safety concerns. However, current research on physical adversarial examples (PAEs) lacks a comprehensive understanding of their unique characteristics, leading to limited significance and understanding. In this paper, we address this gap by thoroughly examining the characteristics of PAEs within a practical workflow encompassing training, manufacturing, and re-sampling processes. By analyzing the links between physical adversarial attacks, we identify manufacturing and re-sampling as the primary sources of distinct attributes and particularities in PAEs. Leveraging this knowledge, we develop a comprehensive analysis and classification framework for PAEs based on their specific characteristics, covering over 100 studies on physical-world adversarial examples. Furthermore, we investigate defense strategies against PAEs and identify open challenges and opportunities for future research. We aim to provide a fresh, thorough, and systematic understanding of PAEs, thereby promoting the development of robust adversarial learning and its application in open-world scenarios. © 2023, CC BY.

关键词：

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：