检索结果-内蒙古大学图书馆

Targeted Pareto Optimization for Subset Selection With Monotone Objective Function and Cardinality Constraint

学校读者我要写书评

暂无评论

IEEE Transactions on Evolutionary Computation 2024年 1-1页

作者： Shang, Ke Wu, Guotong Pang, Lie Meng Ishibuchi, Hisao National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science and Engineering Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

Subset selection, a fundamental problem in various domains, is to choose a subset of elements from a large candidate set under a given objective or multiple objectives. Pareto optimization for subset selection (POSS) has emerged as a powerful paradigm for addressing subset selection problems. Recently, some POSS variants have been proposed to further improve its performance. In this paper, we propose a new POSS variant, named Targeted Pareto Optimization for Subset Selection (TPOSS). TPOSS differs from POSS in four aspects: problem formulation, population initialization, mutation, and environmental selection. The main idea of TPOSS is to focus the search on the target region of subset selection with respect to the subset cardinality in order to improve the search efficiency. We conduct comprehensive experiments to compare TPOSS with six state-of-the-art algorithms on three subset selection tasks (i.e., sparse regression, unsupervised feature selection, and hypervolume subset selection) where the size of the candidate sets ranges from 20 to 400. Experimental results show that with respect to the objective value of the best feasible subset, TPOSS outperforms the other algorithms on all the three tasks, which suggests the potential of TPOSS to enhance subset selection in various domains. IEEE

关键词： Linear programming

Reducing Traffic Wastage in Video Streaming via Bandwidth-Efficient Bitrate Adaptation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Su, Hairong Wang, Shibo Yang, Shusen Huang, Tianchi Ren, Xuebin National Engineering Laboratory for Big Data Analytics Xi'an Jiaotong University China Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi'an Jiaotong University China R&D department Sony

Bitrate adaptation (also known as ABR) is a crucial technique to improve the quality of experience (QoE) for video streaming applications. However, existing ABR algorithms suffer from severe traffic wastage, which refers to the traffic cost of downloading the video segments that users do not finally consume, for example, due to early departure or video skipping. In this paper, we carefully formulate the dynamics of buffered data volume (BDV), a strongly correlated indicator of traffic wastage, which, to the best of our knowledge, is the first time to rigorously clarify the effect of downloading plans on potential wastage. To reduce wastage while keeping a high QoE, we present a bandwidth-efficient bitrate adaptation algorithm (named BEABR), achieving consistently low BDV without distinct QoE losses. Specifically, we design a precise, time-aware transmission delay prediction model over the Transformer architecture, and develop a fine-grained buffer control scheme. Through extensive experiments conducted on emulated and real network environments including WiFi, 4G, and 5G, we demonstrate that BE-ABR performs well in both QoE and bandwidth savings, enabling a 60.87% wastage reduction and a comparable, or even better, QoE, compared to the state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Bandwidth

Intersecting-boundary-sensitive fingerprinting for tampering detection of DNN models 24

学校读者我要写书评

暂无评论

Intersecting-boundary-sensitive fingerprinting for tampering...

Proceedings of the 41st International Conference on Machine Learning

作者： Xiaofan Bai Chaoxiang He Xiaojing Ma Bin Benjamin Zhu Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security Microsoft School of Computer Science and Technology Huazhong University of Science and Technology and National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab.

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 labels. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 labels. The IBSF code is available at: https://***/CGCL-codes/IBSF.

关键词：

Quantum-inspired Hash Function Based on Parity-dependent Quantum Walks with Memory

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Qing Tang, Xueming Lu, Songfeng Yang, Hao Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

In this paper, we develop a generic controlled alternate quantum walk model (called CQWM-P) by combining parity-dependent quantum walks with distinct arbitrary memory lengths and then construct a quantum-inspired hash function (called QHFM-P) based on this model. Numerical simulation shows that QHFM-P has near-ideal statistical performance and is on a par with the state-of-the-art hash functions based on discrete quantum walks in terms of sensitivity of hash value to message, diffusion and confusion properties, uniform distribution property, and collision resistance property. Stability test illustrates that the statistical properties of the proposed hash function are robust with respect to the coin parameters, and theoretical analysis indicates that QHFM-P has the same computational complexity as that of its peers. © 2023, CC BY.

关键词： Hash functions

An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive Modeling 38

学校读者我要写书评

暂无评论

An Autoencoder-Like Nonnegative Matrix Co-Factorization for ...

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Yu, Shenbao Pan, Yinghui Zeng, Yifeng Doshi, Prashant Liu, Guoquan Poh, Kim-Leng Lin, Mingwei College of Computer and Cyber Security Fujian Normal University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Computer and Information Sciences Northumbria University United Kingdom Intelligent Thought and Action Lab School of Computing University of Georgia United States Financial Technology Research Institute Fudan University China College of Design and Engineering National University of Singapore Singapore

Student cognitive modeling (SCM) is a fundamental task in intelligent education, with applications ranging from personalized learning to educational resource allocation. By exploiting students' response logs, SCM aims to predict their exercise performance as well as estimate knowledge proficiency in a subject. data mining approaches such as matrix factorization can obtain high accuracy in predicting student performance on exercises, but the knowledge proficiency is unknown or poorly estimated. The situation is further exacerbated if only sparse interactions exist between exercises and students (or knowledge concepts). To solve this dilemma, we root monotonicity (a fundamental psychometric theory on educational assessments) in a co-factorization framework and present an autoencoder-like nonnegative matrix co-factorization (AE-NMCF), which improves the accuracy of estimating the student's knowledge proficiency via an encoder-decoder learning pipeline. The resulting estimation problem is nonconvex with nonnegative constraints. We introduce a projected gradient method based on block coordinate descent with Lipschitz constants and guarantee the method's theoretical convergence. Experiments on several real-world data sets demonstrate the efficacy of our approach in terms of both performance prediction accuracy and knowledge estimation ability, when compared with existing student cognitive models. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

SMPC Task Decomposition: A Theory for Accelerating Secure Multi-party Computation Task

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Feng, Yuanqing Bai, Tao Lu, Songfeng Tang, Xueming Wu, Junjun Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China

Today, we are in the era of big data, and data are becoming more and more important, especially private data. Secure Multi-party Computation (SMPC) technology enables parties to perform computing tasks without revealing original data. However, the underlying implementation of SMPC is too heavy, such as garbled circuit (GC) and oblivious transfer(OT). Every time a piece of data is added, the resources consumed by GC and OT will increase a lot. Therefore, it is unacceptable to process large-scale data in a single SMPC task. In this work, we propose a novel theory called SMPC Task Decomposition (SMPCTD), which can securely decompose a single SMPC task into multiple SMPC sub-tasks and multiple local tasks without leaking the original data. After decomposition, the computing time, memory and communication consumption drop sharply. We then decompose three machine learning (ML) SMPC tasks using our theory and implement them based on a hybrid protocol framework called ABY. Furthermore, we use incremental computation technique to expand the amount of data involved in these three SMPC tasks. The experimental results show that after decomposing these three SMPC tasks, the time, memory and communication consumption are not only greatly reduced, but also stabilized within a certain range. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Each Fake News is Fake in its Own Way: An Attribution Multi-Granularity Benchmark for Multimodal Fake News Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Guo, Hao Ma, Zihan Zeng, Zhi Luo, Minnan Zeng, Weixin Tang, Jiuyang Zhao, Xiang Laboratory for Big Data and Decision Nation University of Defence Technology China School of Computer Science and Technology Xi’an Jiaotong University China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an Jiaotong University China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University China

Social platforms, while facilitating access to information, have also become saturated with a plethora of fake news, resulting in negative consequences. Automatic multimodal fake news detection is a worthwhile pursuit. Existing multimodal fake news datasets only provide binary labels of real or fake. However, real news is alike, while each fake news is fake in its own way. These datasets fail to reflect the mixed nature of various types of multimodal fake news. To bridge the gap, we construct an attributing multi-granularity multimodal fake news detection dataset AMG, revealing the inherent fake pattern. Furthermore, we propose a multi-granularity clue alignment model MGCA to achieve multimodal fake news detection and attribution. Experimental results demonstrate that AMG is a challenging dataset, and its attribution setting opens up new avenues for future research. © 2024, CC BY-NC-ND.

关键词： Fake detection

Fu-W:A Hyperspectral Image Classification Algorithm Combining Mini Graph Convolutional Networks and Convolutional neural network 23

学校读者我要写书评

暂无评论

Fu-W:A Hyperspectral Image Classification Algorithm Combinin...

6th International Conference on Big data Technologies, ICBDT 2023

作者： Shi, Jiechuan Liu, Kun Yuan, Hao Wang, Can Yang, Bo School of Information Science and Engineering University of Jinan Jinan250022 China China High-resolution Earth Observation System Shandong Center of Data and Application University of Jinan Jinan250022 China Shandong Provincial Key Laboratory of Network Based Intelligent Computing University of Jinan Jinan250022 China

ISBN: (纸本)9798400707667

Convolutional Neural Network (CNN) is a widely used neural network in deep learning, and Graph Convolutional Network (GCN) is one of the most effective semi -supervised methods. It spread node information in a conversion way. In this article, we have studied the differences between CNN and GCN in the classification of high -spectrum image. Because the traditional GCN algorithm needs to build an adjacent matrix on all data, the calculation cost is very high, especially in large -scale remote sensing problems. MinigCNS uses a small -batch learning method to solve the problem of CCN calculation costs, and then it has not solved the problem of low efficiency of single model classification. This article studies the advantages of minigcns and CNN, and proposes a weighted fusion network FU-W, which weighs the minigcns and CNN weighted integration to break the bottleneck of single model performance. We experimented with the fusion algorithm on the two high -spectrum data sets, and its overall accuracy can reach 88.8%in Indian Pines. The experiment proves the superiority of the fusion strategy for a single CNN or GCN model. © 2023 ACM.

关键词： Convolutional neural networks

A Cloud Computing User Experience Focused Load Balancing Method Based on Modified CMA-ES Algorithm 18th

学校读者我要写书评

暂无评论

A Cloud Computing User Experience Focused Load Balancing Met...

18th International Conference on Green, Pervasive, and Cloud Computing, GPC 2023

作者： Luo, Jihai Dong, Chen Chen, Zhenyi Xu, Li Chen, Tianci College of Computer and Data Science - Fuzhou University Xueyuan Road Fujian Fuzhou360108 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Department of Computer Science and Engineering University of South Florida TampaFL33620 United States College of Computer and Cyber Security Fujian Normal University Fuzhou350007 China

ISBN: (纸本)9789819998951

The development of the software and hardware has brought about the abundance and overflow of computing resources. Many Internet companies can lease idle computing resources based on the peak and valley cycles of usage load to provide IaaS service. After the surging development, more and more companies are gradually paying attention to the specific user experience in cloud computing. But there are few works about that aspect in load balance problem. Therefore, we consider the load balancing resource allocation problem, from the perspective of user experience, mainly based on geographical distance and regional Equilibrium, combined with user usage habits, in multiple service periods. A detailed mathematical definition has been established for this problem. This article proposes a mathematical model for the problem, along with an modified CMA-ES (Covariance Matrix Adaptation Evolution Strategy) algorithm, called WS-ESS-CMA-ES algorithm, to allocate computing resources and solve the above problem. The process of using the proposed algorithm to solve the problem of cloud computing resource allocation in real scenarios is simulated, and compared with some other algorithms. The experiment results show that our algorithm performs well. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2024.

关键词： Cloud computing