Inf. Sci.最新文献_第3页

Fully distributed event-triggered cooperative output regulation for switched multi-agent systems with combined switching mechanism 具有组合交换机制的交换多智能体系统的全分布式事件触发协同输出调节

Inf. Sci. Pub Date : 2023-04-01 DOI: 10.2139/ssrn.4290226

Guangxu He, Jun Zhao

引用次数: 1

Steering the interpretability of decision trees using lasso regression - an evolutionary perspective 使用套索回归控制决策树的可解释性——一种进化的观点

Inf. Sci. Pub Date : 2023-04-01 DOI: 10.2139/ssrn.4331060

M. Czajkowski, K. Jurczuk, M. Kretowski

引用次数: 2

Ensuring confidentiality of cyber-physical systems using event-based cryptography 使用基于事件的加密技术确保网络物理系统的机密性

Inf. Sci. Pub Date : 2023-04-01 DOI: 10.1016/J.IFACOL.2020.12.2288

Públio M. Lima, L. K. Carvalho, M. V. Moreira

引用次数: 5

Three-way conflict analysis and resolution based on q-rung orthopair fuzzy information 基于q阶正交模糊信息的三方冲突分析与解决

Inf. Sci. Pub Date : 2023-04-01 DOI: 10.2139/ssrn.4278353

Teng Li, Junsheng Qiao, Weiping Ding

引用次数: 2

Are Neural Architecture Search Benchmarks Well Designed? A Deeper Look Into Operation Importance 神经架构搜索基准设计得好吗?对操作重要性的深入探讨

Inf. Sci. Pub Date : 2023-03-29 DOI: 10.48550/arXiv.2303.16938

Vasco Lopes, Bruno Degardin, L. Alexandre

{"title":"Are Neural Architecture Search Benchmarks Well Designed? A Deeper Look Into Operation Importance","authors":"Vasco Lopes, Bruno Degardin, L. Alexandre","doi":"10.48550/arXiv.2303.16938","DOIUrl":"https://doi.org/10.48550/arXiv.2303.16938","url":null,"abstract":"Neural Architecture Search (NAS) benchmarks significantly improved the capability of developing and comparing NAS methods while at the same time drastically reduced the computational overhead by providing meta-information about thousands of trained neural networks. However, tabular benchmarks have several drawbacks that can hinder fair comparisons and provide unreliable results. These usually focus on providing a small pool of operations in heavily constrained search spaces -- usually cell-based neural networks with pre-defined outer-skeletons. In this work, we conducted an empirical analysis of the widely used NAS-Bench-101, NAS-Bench-201 and TransNAS-Bench-101 benchmarks in terms of their generability and how different operations influence the performance of the generated architectures. We found that only a subset of the operation pool is required to generate architectures close to the upper-bound of the performance range. Also, the performance distribution is negatively skewed, having a higher density of architectures in the upper-bound range. We consistently found convolution layers to have the highest impact on the architecture's performance, and that specific combination of operations favors top-scoring architectures. These findings shed insights on the correct evaluation and comparison of NAS methods using NAS benchmarks, showing that directly searching on NAS-Bench-201, ImageNet16-120 and TransNAS-Bench-101 produces more reliable results than searching only on CIFAR-10. Furthermore, with this work we provide suggestions for future benchmark evaluations and design. The code used to conduct the evaluations is available at https://github.com/VascoLopes/NAS-Benchmark-Evaluation.","PeriodicalId":13641,"journal":{"name":"Inf. Sci.","volume":"5 1","pages":"119695"},"PeriodicalIF":0.0,"publicationDate":"2023-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85578187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Improving the Transferability of Adversarial Examples via Direction Tuning 通过方向调整提高对抗性样例的可转移性

Inf. Sci. Pub Date : 2023-03-27 DOI: 10.48550/arXiv.2303.15109

Xiangyuan Yang, Jie Lin, Han Zhang, Xinyu Yang, Peng Zhao

{"title":"Improving the Transferability of Adversarial Examples via Direction Tuning","authors":"Xiangyuan Yang, Jie Lin, Han Zhang, Xinyu Yang, Peng Zhao","doi":"10.48550/arXiv.2303.15109","DOIUrl":"https://doi.org/10.48550/arXiv.2303.15109","url":null,"abstract":"In the transfer-based adversarial attacks, adversarial examples are only generated by the surrogate models and achieve effective perturbation in the victim models. Although considerable efforts have been developed on improving the transferability of adversarial examples generated by transfer-based adversarial attacks, our investigation found that, the big deviation between the actual and steepest update directions of the current transfer-based adversarial attacks is caused by the large update step length, resulting in the generated adversarial examples can not converge well. However, directly reducing the update step length will lead to serious update oscillation so that the generated adversarial examples also can not achieve great transferability to the victim models. To address these issues, a novel transfer-based attack, namely direction tuning attack, is proposed to not only decrease the update deviation in the large step length, but also mitigate the update oscillation in the small sampling step length, thereby making the generated adversarial examples converge well to achieve great transferability on victim models. In addition, a network pruning method is proposed to smooth the decision boundary, thereby further decreasing the update oscillation and enhancing the transferability of the generated adversarial examples. The experiment results on ImageNet demonstrate that the average attack success rate (ASR) of the adversarial examples generated by our method can be improved from 87.9% to 94.5% on five victim models without defenses, and from 69.1% to 76.2% on eight advanced defense methods, in comparison with that of latest gradient-based attacks.","PeriodicalId":13641,"journal":{"name":"Inf. Sci.","volume":"27 1","pages":"119491"},"PeriodicalIF":0.0,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82767151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

An Empirical Analysis of the Shift and Scale Parameters in BatchNorm BatchNorm中位移和尺度参数的实证分析

Inf. Sci. Pub Date : 2023-03-22 DOI: 10.48550/arXiv.2303.12818

Y. Peerthum, M. Stamp

{"title":"An Empirical Analysis of the Shift and Scale Parameters in BatchNorm","authors":"Y. Peerthum, M. Stamp","doi":"10.48550/arXiv.2303.12818","DOIUrl":"https://doi.org/10.48550/arXiv.2303.12818","url":null,"abstract":"Batch Normalization (BatchNorm) is a technique that improves the training of deep neural networks, especially Convolutional Neural Networks (CNN). It has been empirically demonstrated that BatchNorm increases performance, stability, and accuracy, although the reasons for such improvements are unclear. BatchNorm includes a normalization step as well as trainable shift and scale parameters. In this paper, we empirically examine the relative contribution to the success of BatchNorm of the normalization step, as compared to the re-parameterization via shifting and scaling. To conduct our experiments, we implement two new optimizers in PyTorch, namely, a version of BatchNorm that we refer to as AffineLayer, which includes the re-parameterization step without normalization, and a version with just the normalization step, that we call BatchNorm-minus. We compare the performance of our AffineLayer and BatchNorm-minus implementations to standard BatchNorm, and we also compare these to the case where no batch normalization is used. We experiment with four ResNet architectures (ResNet18, ResNet34, ResNet50, and ResNet101) over a standard image dataset and multiple batch sizes. Among other findings, we provide empirical evidence that the success of BatchNorm may derive primarily from improved weight initialization.","PeriodicalId":13641,"journal":{"name":"Inf. Sci.","volume":"104 1","pages":"118951"},"PeriodicalIF":0.0,"publicationDate":"2023-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75507549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Assessor-Guided Learning for Continual Environments 持续环境的评估指导学习

Inf. Sci. Pub Date : 2023-03-21 DOI: 10.48550/arXiv.2303.11624

M. A. Ma'sum, Mahardhika Pratama, E. Lughofer, Weiping Ding, W. Jatmiko

{"title":"Assessor-Guided Learning for Continual Environments","authors":"M. A. Ma'sum, Mahardhika Pratama, E. Lughofer, Weiping Ding, W. Jatmiko","doi":"10.48550/arXiv.2303.11624","DOIUrl":"https://doi.org/10.48550/arXiv.2303.11624","url":null,"abstract":"This paper proposes an assessor-guided learning strategy for continual learning where an assessor guides the learning process of a base learner by controlling the direction and pace of the learning process thus allowing an efficient learning of new environments while protecting against the catastrophic interference problem. The assessor is trained in a meta-learning manner with a meta-objective to boost the learning process of the base learner. It performs a soft-weighting mechanism of every sample accepting positive samples while rejecting negative samples. The training objective of a base learner is to minimize a meta-weighted combination of the cross entropy loss function, the dark experience replay (DER) loss function and the knowledge distillation loss function whose interactions are controlled in such a way to attain an improved performance. A compensated over-sampling (COS) strategy is developed to overcome the class imbalanced problem of the episodic memory due to limited memory budgets. Our approach, Assessor-Guided Learning Approach (AGLA), has been evaluated in the class-incremental and task-incremental learning problems. AGLA achieves improved performances compared to its competitors while the theoretical analysis of the COS strategy is offered. Source codes of AGLA, baseline algorithms and experimental logs are shared publicly in url{https://github.com/anwarmaxsum/AGLA} for further study.","PeriodicalId":13641,"journal":{"name":"Inf. Sci.","volume":"84 1","pages":"119088"},"PeriodicalIF":0.0,"publicationDate":"2023-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80913230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

THAT-Net: Two-layer hidden state aggregation based two-stream network for traffic accident prediction 基于两层隐藏状态聚合的两流交通事故预测网络

Inf. Sci. Pub Date : 2023-03-01 DOI: 10.2139/ssrn.4331054

Wei Liu, Zhang Tao, Yisheng Lu, Jun Chen, Longsheng Wei

引用次数: 3

PKET-GCN: Prior knowledge enhanced time-varying graph convolution network for traffic flow prediction 基于先验知识增强时变图卷积网络的交通流预测

Inf. Sci. Pub Date : 2023-03-01 DOI: 10.2139/ssrn.4331039

Yinxin Bao, Jialin Liu, Qinqin Shen, Yang Cao, Weiping Ding, Quan Shi

引用次数: 5