检索结果-内蒙古大学图书馆

Robust Model Aggregation for Heterogeneous Federated Learning: Analysis and Optimizations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Shao, Yumeng Li, Jun Shi, Long Wei, Kang Ding, Ming Li, Qianmu Li, Zengxiang Chen, Wen Jin, Shi The School of Electronic and Optical Engineering Nanjing University of Science and Technology Nanjing210094 China Data61 CSIRO Sydney Australia The Digital Economy Research Institute Nanjing University of Science and Technology Jiangsu Nanjing210094 China The Institute of High Performance Computing A*STAR Singapore The Digital Research Institute ENN Group China The Department of Electronic Engineering Shanghai Jiao Tong University Shanghai200240 China The National Mobile Communications Research Laboratory Southeast University Nanjing210096 China

Conventional synchronous federated learning (SFL) frameworks suffer from performance degradation in heterogeneous systems due to imbalanced local data size and diverse computing power on the client side. To address this problem, asynchronous FL (AFL) and semi-asynchronous FL have been proposed to recover the performance loss by allowing asynchronous aggregation. However, asynchronous aggregation incurs a new problem of inconsistency between local updates and global updates. Motivated by the issues of conventional SFL and AFL, we first propose a time-driven SFL (T-SFL) framework for heterogeneous systems. The core idea of T-SFL is that the server aggregates the models from different clients, each with varying numbers of iterations, at regular time intervals. To evaluate the learning performance of T-SFL, we provide an upper bound on the global loss function. Further, we optimize the aggregation weights to minimize the developed upper bound. Then, we develop a discriminative model selection (DMS) algorithm that removes local models from clients whose number of iterations falls below a predetermined threshold. In particular, this algorithm ensures that each client’s aggregation weight accurately reflects its true contribution to the global model update, thereby improving the efficiency and robustness of the system. To validate the effectiveness of T-SFL with the DMS algorithm, we conduct extensive experiments using several popular datasets including MNIST, Cifar-10, Fashion-MNIST, and SVHN. The experimental results demonstrate that T-SFL with the DMS algorithm can reduce the latency of conventional SFL by 50%, while achieving an average 3% improvement in learning accuracy over state-of-the-art AFL algorithms. Copyright © 2024, The Authors. All rights reserved.

关键词： Learning algorithms

A Comprehensive Cross-Model Framework for Benchmarking the performance of Quantum Hamiltonian Simulations

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chatterjee, Avimita Rappaport, Sonny Giri, Anish Johri, Sonika Proctor, Timothy Bernal Neira, David E. Sathe, Pratik Lubinski, Thomas Department of Computer Science & Engineering The Pennsylvania State University United States QED-C managed by SRI International United States Vanderbilt University United States Coherent Computing Inc CupertinoCA United States Quantum Performance Laboratory Sandia National Laboratories LivermoreCA94550 United States Research Institute of Advanced Computer Science Universities Space Research Association Mountain ViewCA United States Davidson School of Chemical Engineering Purdue University West LafayetteIN United States Los Alamos National Laboratory Los AlamosNM87545 United States Quantum Circuits Inc 25 Science Park New HavenCT06511 United States QED-C Technical Advisory Committee on Standards and Performance Metrics United States

Quantum Hamiltonian simulation is one of the most promising applications of quantum computing and forms the basis for many quantum algorithms. Benchmarking them is an important gauge of progress in quantum computing technology. We present a methodology and software framework to evaluate various facets of the performance of gate-based quantum computers on Trotterized quantum Hamiltonian evolution. We propose three distinct modes for benchmarking: (i) comparing simulation on a real device to that on a noiseless classical simulator, (ii) comparing simulation on a real device with exact diagonalization results, and (iii) using scalable mirror circuit techniques to assess hardware performance in scenarios beyond classical simulation methods. We demonstrate this framework on five Hamiltonian models from the HamLib library: the Fermi and Bose-Hubbard models, the transverse field Ising model, the Heisenberg model, and the Max3SAT problem. Experiments were conducted using Qiskit's Aer simulator, BlueQubit's CPU cluster and GPU simulators, and IBM's quantum hardware. Our framework, extendable to other Hamiltonians, provides comprehensive performance profiles that reveal hardware and algorithmic limitations and measure both fidelity and execution times, identifying crossover points where quantum hardware outperforms CPU/GPU simulators. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum computers

DQPS: An Intelligent Multi-Hop Computation Offloading Scheme for Workflow Applications in Vehicular Edge computing Networks

学校读者我要写书评

暂无评论

IEEE Transactions on Consumer Electronics 2024年

作者： Lin, Bing Chen, Qiaoxin Chen, Xing Jia, Wen-Kang Lu, Yu Xiong, Neal N. Fujian Normal University College of Physics and Energy Fujian Provincial Key Laboratory of Quantum Manipulation and New Energy Materials Fuzhou350117 China Fujian Provincial Collaborative Innovation Center for Advanced High-Field Superconducting Materials and Engineering Fuzhou350117 China Peking University School of Computer Science 100871 China Xiamen University Department of Informatics and Communication Engineering Xiamen361005 China Fuzhou University College of Computer and Data Science Fuzhou350118 China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350118 China Fujian Normal University College of Photonic and Electronic Engineering Fuzhou350117 China Fujian Normal University Concord University College Fuzhou350117 China Sul Ross State University Department of Computer Mathematical and Physical Sciences AlpineTX79830 United States

Vehicular Edge computing (VEC) is a feasible solution for autonomous driving as it can offload latency-sensitive and computation-intensive tasks from vehicle terminals to roadside units (RSUs) for real-time processing. Due to the high computational resource the workflow applications (i.e., autonomous driving) required, the small vehicle-to-RSUs communication range, and the scarce available resources for each vehicle, it might be difficult to accomplish complex workflow applications through the single-hop offloading paradigm in the Internet of Vehicles (IoV). In this paper, we propose a reinforcement learning (RL) based multi-hop computation offloading scheme for workflow applications to reduce their execution latency in the VEC networks, which considers the data dependency in workflow applications as well as the trust relationship and communication interference among RSUs. Firstly, a preprocessing method is employed to merge the cut-edges in a workflow to reduce the offloading scale of tasks and compress the encoding dimension of offloading solutions. Then, a Deep Q-network algorithm using Phase-optimal State update (DQPS) is proposed to update the offloading policy distribution, in which the deviation of the phase-optimal state from the current state is estimated as the reward of RL to promote the algorithm's convergence to adapt the dynamic VEC networks. Simulation results show that DQPS has the best performance compared to other benchmark schemes. Moreover, the latency of the identical applications can be reduced by 2.5%-25.3% through our offloading scheme with a multi-hop model compared to that with the single-hop paradigm in IoV. © 1975-2011 IEEE.

关键词： Computation offloading

Security boundaries of an optical-power limiter for protecting quantum-key-distribution systems

学校读者我要写书评

暂无评论

Physical Review Applied 2024年第1期21卷 014026-014026页

作者： Qingquan Peng Binwu Gao Konstantin Zaitsev Dongyang Wang Jiangfang Ding Yingwen Liu Qin Liao Ying Guo Anqi Huang Junjie Wu Institute for Quantum Information and State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha 410073 China School of Automation Central South University Changsha 410083 China China Greatwall Research Institute China Greatwall Technology Group Co. Ltd. Shenzhen 518057 China Russian Quantum Center Skolkovo Moscow 121205 Russia NTI Center for Quantum Communications National University of Science and Technology MISiS Moscow 119049 Russia Vigo Quantum Communication Center University of Vigo 36310 Vigo Spain Escuela de Ingeniería de Telecomunicación Department of Signal Theory and Communications University of Vigo 36310 Vigo Spain atlanTTic Research Center University of Vigo 36310 Vigo Spain College of Computer Science and Electronic Engineering Hunan University Changsha 410082 China School of Computer Science Beijing University of Posts and Telecommunications Beijing 100876 China

Unauthorized light injection has always been a vital threat to the practical security of a quantum-key-distribution (QKD) system. An optical-power limiter (OPL) based on the thermo-optical defocusing effect has been proposed and implemented, limiting the injected hacking light. As a hardware countermeasure, the performance of the OPL under various light-injection attacks will be tested to clarify the security boundary before it is widely deployed. To investigate the security boundary of the OPL in quantum cryptography, we comprehensively test and analyze the behavior of the OPL under continuous-wave (cw) light-injection attacks and pulse-illumination attacks with pulse repetition rates of 0.5 Hz, 40 MHz, and 1 GHz. The test results illuminate the security boundary of the OPL, which allows one to properly employ the OPL in use cases. The methodology of testing and analysis proposed here is applicable to other power-limitation components in a QKD system.

关键词： Optical quantum information processing Photonics Quantum communication Quantum cryptography Devices

Graph adversarial self-supervised learning 21

学校读者我要写书评

暂无评论

Graph adversarial self-supervised learning

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Longqi Yang Liangliang Zhang Wenjing Yang Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha China and Defense Innovation Institute Beijing China Institute of Systems Engineering AMS Beijing China Institute for Quantum Information & State Key Laboratory of High Performance Computing College of Computer Science and Technology National University of Defense Technology Changsha China

ISBN: (纸本)9781713845393

This paper studies a long-standing problem of learning the representations of a whole graph without human supervision. The recent self-supervised learning methods train models to be invariant to the transformations (views) of the inputs. However, designing these views requires the experience of human experts. Inspired by adversarial training, we propose an adversarial self-supervised learning (GASSL) framework for learning unsupervised representations of graph data without any handcrafted views. GASSL automatically generates challenging views by adding perturbations to the input and are adversarially trained with respect to the encoder. Our method optimizes the min-max problem and utilizes a gradient accumulation strategy to accelerate the training process. Experimental on ten graph classification datasets show that the proposed approach is superior to state-of-the-art self-supervised learning baselines, which are competitive with supervised models.

关键词：

HFN: Heterogeneous Feature Network for Multivariate Time Series Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhan, Jun Wu, Chengkun Yang, Canqun Miao, Qiucheng Ma, Xiandong College of Computer Science National University of Defense Technology Changsha410073 China State Key Laboratory of High Performance Computing College of Computer Science National University of Defense Technology Changsha410073 China National SuperComputing Center Tianjin China School of Engineering Lancaster University LancasterLA1 4YW United Kingdom

Network or physical attacks on industrial equipment or computer systems may cause massive losses. Therefore, a quick and accurate anomaly detection (AD) based on monitoring data, especially the multivariate time-series (MTS) data, is of great significance. As the key step of anomaly detection for MTS data, learning the relations among different variables has been explored by many approaches. However, most of the existing approaches do not consider the heterogeneity between variables, that is, different types of variables (continuous numerical variables, discrete categorical variables or hybrid variables) may have different and distinctive edge distributions. In this paper, we propose a novel semi-supervised anomaly detection framework based on a heterogeneous feature network (HFN) for MTS, learning heterogeneous structure information from a mass of unlabeled time-series data to improve the accuracy of anomaly detection, and using attention coefficient to provide an explanation for the detected anomalies. Specifically, we first combine the embedding similarity subgraph generated by sensor embedding and feature value similarity subgraph generated by sensor values to construct a time-series heterogeneous graph, which fully utilizes the rich heterogeneous mutual information among variables. Then, a prediction model containing nodes and channel attentions is jointly optimized to obtain better time-series representations. This approach fuses the state-of-the-art technologies of heterogeneous graph structure learning (HGSL) and representation learning. The experiments on four sensor datasets from real-world applications demonstrate that our approach detects the anomalies more accurately than those baseline approaches, thus providing a basis for the rapid positioning of anomalies. Copyright © 2022, The Authors. All rights reserved.

关键词： Anomaly detection

Scalable Multi-view Regression Clustering for Large-scale Data

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zhao, Xiaowei Fan, Jie Chang, Xiaojun Nie, Feiping Zhang, Qiang Guo, Jun Xidian University State Key Laboratory of Electromechanical Integrated Manufacturing of High-Performance Electronic Equipment Shaanxi Xi’an710071 China Xidian University Center for Complex Systems School of Mechano-Electronic Engineering Shaanxi Xi’an710071 China Northwest University School of Information Science and Technology Shaanxi Xi’an710127 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China Mohamed bin Zayed University of Artificial Intelligence Department of Computer Vision MBZUAI Abu Dhabi United Arab Emirates Xi’an710072 China

In recent years, unsupervised linear regression has attracted attention for its ability to directly capture the mapping relationship between samples and targets. However, existing algorithms can only utilize limited information from a single view, which often leads to unsatisfactory results. To address this problem, we propose a regression clustering model based on multi-view information fusion, called Scalable Multi-view Regression Clustering. This model consists of two parts: intra-view information fusion and inter-view information fusion. In the first part, to capture the local correlations among samples, we propose constructing view-specific bipartite graphs. Unlike traditional single-view and multi-view clustering algorithms, we treat the weights of the bipartite graph as additional features of the samples, thereby directly incorporating the local manifold structure of the samples at the feature level. Furthermore, since the original features of the samples also contain valuable information, we perform unsupervised linear regression separately on the samples represented by the original features and those represented by the bipartite graph weights in each view. The results are then integrated in a weighted manner. In the second part, we propose adaptively weighting the clustering results from each view to capture complementary information across views, thereby enhancing clustering performance. This strategy not only avoids the bipartite graph alignment issue in multi-view clustering but also enables clustering with linear time complexity, making it effective for handling large-scale data. An iterative optimization algorithm is developed to update all variables alternately. Experiments conducted on benchmark datasets demonstrate the superiority of our proposed model. © 2025 IEEE. All rights reserved.

关键词： Multiple linear regression

Application-level Benchmarking of Quantum computers using Nonlocal Game Strategies

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Furches, Jim Chehade, Sarah Hamilton, Kathleen Wiebe, Nathan Marrero, Carlos Ortiz College of Computing Georgia Institute of Technology AtlantaGA30332 United States Physical Detection Systems and Deployment Division Pacific Northwest National Laboratory RichlandWA99354 United States Quantum Computational Science Group Oak Ridge National Laboratory Oak RidgeTN37830 United States Department of Computer Science University of Toronto ONM5S 1A1 Canada High Performance Computing Group Pacific Northwest National Laboratory RichlandWA99354 United States Canadian Institute for Advanced Research TorontoONM5G 1M1 Canada Department of Electrical & Computer Engineering North Carolina State University RaleighNC27607 United States

In a nonlocal game, two noncommunicating players cooperate to convince a referee that they possess a strategy that does not violate the rules of the game. Quantum strategies allow players to optimally win some games by performing joint measurements on a shared entangled state, but computing these strategies can be challenging. We present a variational quantum algorithm to compute quantum strategies for nonlocal games by encoding the rules of a nonlocal game into a Hamiltonian. We show how this algorithm can generate a short-depth optimal quantum strategy for a graph coloring game with a quantum advantage. This quantum strategy is then evaluated on fourteen different quantum hardware platforms to demonstrate its utility as a benchmark. Finally, we discuss potential sources of errors that can explain the observed decreased performance of the executed task and derive an expression for the number of samples required to accurately estimate the win rate in the presence of noise. Copyright © 2023, The Authors. All rights reserved.

关键词： Hamiltonians

New Perspectives on Recommender Systems for Industries

学校读者我要写书评

暂无评论

New Perspectives on Recommender Systems for Industries

Artificial Intelligence for Industries (AI4I)

作者： Mouzhi Ge Giovanni Pilato Fabio Persia Daniela D’Auria Faculty of European Campus Rottal-Inn Deggendorf Institute of Technology Deggendorf Germany National Research Council of Italy Institute for High Performance Computing and Networking Palermo italy Department of Information Engineering Computer Science and Mathematics University of L’Aquila L’Aquila italy Faculty of Computer Science Free University of Bozen-Bolzano Bozen-Bolzano italy

Nowadays, recommender systems are increasingly being exploited in many industrial applications, including virtual museums and movie streaming platforms. In the last few years, some new perspectives provided by research paradigms such as deep learning or quantum computing, have arisen. As a result, this paper identifies four new perspectives on recommender systems: e-health, tourism, deep-learning-based, and recommender systems exploiting quantum computing. After discussing them, the paper provides the current state of the art and highlights the possible future directions for industries.

关键词： Industries Deep learning Training Quantum computing Scalability Computational modeling Virtual museums