检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Yang, Yi-Rui Shi, Chang-Wei Li, Wu-Jun National Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing China

Byzantine-robust distributed learning (BRDL), in which computing devices are likely to behave abnormally due to accidental failures or malicious attacks, has recently become a hot research topic. However, even in the independent and identically distributed (i.i.d.) case, existing BRDL methods will suffer a significant drop on model accuracy due to the large variance of stochastic gradients. Increasing batch size is a simple yet effective way to reduce the variance. However, when the total number of gradient computation is fixed, a too-large batch size will lead to a too-small iteration number (update number), which may also degrade the model accuracy. In view of this challenge, we mainly study the effect of batch size when the total number of gradient computation is fixed in this work. In particular, we show that when the total number of gradient computation is fixed, the optimal batch size corresponding to the tightest theoretical upper bound in BRDL increases with the fraction of Byzantine workers. Therefore, compared to the case without attacks, a larger batch size is preferred when under Byzantine attacks. Motivated by the theoretical finding, we propose a novel method called Byzantine-robust stochastic gradient descent with normalized momentum (ByzSGDnm) in order to further increase model accuracy in BRDL. We theoretically prove the convergence of ByzSGDnm for general non-convex cases under Byzantine attacks. Empirical results show that when under Byzantine attacks, using a relatively large batch size can significantly increase the model accuracy, which is consistent with our theoretical results. Moreover, ByzSGDnm can achieve higher model accuracy than existing BRDL methods when under deliberately crafted attacks. In addition, we empirically show that increasing batch size has the bonus of training acceleration. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

MLC-NC: Long-Tailed Multi-Label Image Classification Through the Lens of Neural Collapse 39

MLC-NC: Long-Tailed Multi-Label Image Classification Through...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Tao, Zijian Li, Shao-Yuan Wan, Wenhai Zheng, Jinpeng Chen, Jia-Yao Li, Yuchen Huang, Sheng-Jun Chen, Songcan MIIT Key Laboratory of Pattern Analysis and Machine Intelligence China College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics China State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Technology Huazhong University of Science and Technology China College of Computer and Software Hohai University China

ISBN: (纸本)157735897X

Long-tailed (LT) data distribution is common in multi-label image classification (MLC) and can significantly impact the performance of classification models. One reason is the challenge of learning unbiased instance representations (i.e. features) for imbalanced datasets. Additionally, the co-occurrence of head/tail classes within the same instance, along with complex label dependencies, introduces further challenges. In this work, we delve into this problem through the lens of neural collapse (NC). NC refers to a phenomenon where the last-layer features and classifier of a deep neural network model exhibit a simplex Equiangular Tight Frame (ETF) structure during its terminal training phase. This structure creates an optimal linearly separable state. However, this phenomenon typically occurs in balanced datasets but rarely applies to the typical imbalanced problem. To induce NC properties under Long-tailed multi-label classification (LT-MLC) conditions, we propose an approach named MLC-NC, which aims to learn high-quality data representations and improve the model’s generalization ability. Specifically, MLC-NC accounts for the fact that different labels correspond to different feature parts located in images. MLC-NC extracts class-wise features from each instance through a cross-attention mechanism. To guide the features toward the ETF structure, we introduce visual-semantic feature alignment with a fixed ETF structured label embedding, which helps to learn evenly distributed class centers. To reduce within-class feature variation, we introduce collapse calibration within a lower-dimensional feature space. To mitigate classification bias, we concatenate features and feed them into a binarized fixed ETF classifier. As an orthogonal approach to existing methods, MLC-NC can be seamlessly integrated into various frameworks. Extensive experiments on widely-used benchmarks demonstrate the effectiveness of our method. Copyright © 2025, Association for the Advancement of Ar

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A Combinatorial Interaction Testing Method for Multi-Label Image Classifier 35

A Combinatorial Interaction Testing Method for Multi-Label I...

引用

35th IEEE International Symposium on software Reliability Engineering, ISSRE 2024

作者： Wang, Peng Hu, Shengyou Wu, Huayao Niu, Xintao Nie, Changhai Chen, Lin Nanjing University State Key Laboratory for Novel Software Technology and School of Computer Science China

ISBN: (纸本)9798350353884

Multi-label image classification is a critical task in computer vision, in which the correlations between labels are typically exploited by modern classifiers for an effective classification. In this study, we propose LV-CIT, a black-box testing method that applies Combinatorial Interaction Testing (CIT) to systematically test the ability of classifiers to handle such correlations. Specifically, LV-CIT views each label of the label space as an input-parameter taking binary values (indicating whether an object appears in an image), and manages to generate a label value covering array as the set of test cases to cover certain combinations of label values. Then, for each test case, LV-CIT relies on an object library to generate composite test images that perfectly match the specified labels, and reports classification errors if such labels cannot be correctly recognised. The experimental results on two popular datasets with six state-of-The-Art image classifiers show that LV-CIT is more efficient than the existing CIT tools in generating label value covering arrays. LV-CIT is also effective in errors revelation, as it can find 111% more errors by using 20% fewer test images than the existing methods for testing multi-label image classifiers. © 2024 IEEE.

关键词： Black-box testing

来源：评论

学校读者我要写书评

暂无评论

Empirically revisiting and enhancing automatic classification of bug and non-bug issues

引用

Frontiers of computer Science 2024年第5期18卷 25-44页

作者： Zhong LI Minxue PAN Yu PEI Tian ZHANG Linzhang WANG Xuandong LI State Key Laboratory for Novel Software Technology Nanjing UniversityNanjing 210023China Department of Computer Science and Technology Nanjing UniversityNanjing 210023China Software Institute Nanjing UniversityNanjing 210093China Department of Computing The Hong Kong Polytechnic UniversityHong KongChina

A large body of research effort has been dedicated to automated issue classification for Issue Tracking Systems(ITSs).Although the existing approaches have shown promising performance,the different design choices,including the different textual fields,feature representation methods and machine learning algorithms adopted by existing approaches,have not been comprehensively compared and *** fill this gap,we perform the first extensive study of automated issue classification on 9 state-of-the-art issue classification *** experimental results on the widely studied dataset reveal multiple practical guidelines for automated issue classification,including:(1)Training separate models for the issue titles and descriptions and then combining these two models tend to achieve better performance for issue classification;(2)Word embedding with Long Short-Term Memory(LSTM)can better extract features from the textual fields in the issues,and hence,lead to better issue classification models;(3)There exist certain terms in the textual fields that are helpful for building more discriminating classifiers between bug and non-bug issues;(4)The performance of the issue classification model is not sensitive to the choices of ML *** on our study outcomes,we further propose an advanced issue classification approach,DEEPLABEL,which can achieve better performance compared with the existing issue classification approaches.

关键词： issue tracking issue type prediction empirical study

来源：评论

学校读者我要写书评

暂无评论

Migrant Resettlement by Evolutionary Multiobjective Optimization

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第1期6卷 51-65页

作者： Liu, Dan-Xuan Gu, Yu-Ran Qian, Chao Mu, Xin Tang, Ke Nanjing University National Key Laboratory for Novel Software Technology School of Artificial Intelligence Nanjing210023 China Peng Cheng Laboratory Shenzhen518000 China Southern University of Science and Technology Department of Computer Science and Engineering Shenzhen518055 China

Migration has been a universal phenomenon, which brings opportunities as well as challenges for global development. As the number of migrants (e.g., refugees) increases rapidly, a key challenge faced by each country is the problem of migrant resettlement. This problem has attracted scientific research attention, from the perspective of maximizing the employment rate. Previous works mainly formulated migrant resettlement as an approximately submodular optimization problem subject to multiple matroid constraints and employed the greedy algorithm, whose performance, however, may be limited due to its greedy nature. In this article, we propose a new framework called migrant resettlement by evolutionary multiobjective optimization (MR-EMO), which reformulates migrant resettlement as a biobjective optimization problem that maximizes the expected number of employed migrants and minimizes the number of dispatched migrants simultaneously, and employs a multiobjective evolutionary algorithm (MOEA) to solve the biobjective problem. We implement MR-EMO using three MOEAs: the popular nondominated sorting genetic algorithm II (NSGA-II), MOEA based on decomposition (MOEA/D) as well as the theoretically grounded global simple evolutionary multiobjective optimizer (GSEMO). To further improve the performance of MR-EMO, we propose a specific MOEA, called GSEMO using matrix-swap mutation and repair mechanism (GSEMO-SR), which has a better ability to search for feasible solutions. We prove that MR-EMO using either GSEMO or GSEMO-SR can achieve better theoretical guarantees than the previous greedy algorithm. Experimental results under the interview and coordination migration models clearly show the superiority of MR-EMO (with either NSGA-II, MOEA/D, GSEMO or GSEMO-SR) over previous algorithms, and that using GSEMO-SR leads to the best performance of MR-EMO. © 2024 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Towards Cache-Assisted Hierarchical Detection for Real-Time Health Data Monitoring in IoHT

引用

computers, Materials & Continua 2023年第11期77卷 2529-2544页

作者： Muhammad Tahir Mingchu Li Irfan Khan Salman AAl Qahtani Rubia Fatima Javed Ali Khan Muhammad Shahid Anwar School of Software Technology Dalian University of Technology(DUT)Dalian116621China School of Software Technology Key Laboratory for Ubiquitous Network and Service Software of Liaoning ProvinceDalian116650China Department of Computer Engineering King Saud UniversityRiyadh11543Saudi Arabia School of Software Tsinghua UniversityBeijing100084China Department of Software Engineering University of Science and TechnologyBanu28100Pakistan Department of AI and Software Gachon UniversitySeongnamsi13120Korea

Real-time health data monitoring is pivotal for bolstering road services’safety,intelligence,and efficiency within the Internet of Health Things(IoHT)***,delays in data retrieval can markedly hinder the efficacy of big data awareness detection *** advocate for a collaborative caching approach involving edge devices and cloud networks to combat *** strategy is devised to streamline the data retrieval path,subsequently diminishing network *** an adept cache processing scheme poses its own set of challenges,especially given the transient nature of monitoring data and the imperative for swift data transmission,intertwined with resource allocation *** paper unveils a novel mobile healthcare solution that harnesses the power of our collaborative caching approach,facilitating nuanced health monitoring via edge *** system capitalizes on cloud computing for intricate health data analytics,especially in pinpointing health *** the dynamic locational shifts and possible connection disruptions,we have architected a hierarchical detection system,particularly during *** system caches data efficiently and incorporates a detection utility to assess data freshness and potential lag in response ***,we introduce the Cache-Assisted Real-Time Detection(CARD)model,crafted to optimize *** the inherent complexity of the NP-hard CARD model,we have championed a greedy algorithm as a *** reveal that our collaborative caching technique markedly elevates the Cache Hit Ratio(CHR)and data freshness,outshining its contemporaneous benchmark *** empirical results underscore the strength and efficiency of our innovative IoHT-based health monitoring *** encapsulate,this paper tackles the nuances of real-time health data monitoring in the IoHT landscape,presenting a joint edge-cloud caching strategy paired with a hierarchical detection *** methodology yields enh

关键词： Real-time health data monitoring Cache-Assisted Real-Time Detection(CARD) edge-cloud collaborative caching scheme hierarchical detection Internet of Health Things(IoHT)

来源：评论

学校读者我要写书评

暂无评论

Qualitative and Quantitative Model Checking Against Recurrent Neural Networks

引用

Journal of computer Science & technology 2024年第6期39卷 1292-1311页

作者： Zhen Liang Wan-Wei Liu Fu Song Bai Xue Wen-Jing Yang Ji Wang Zheng-Bin Pang Institute for Quantum Information&State Key Laboratory of High Performance Computing College of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410073China College of Computer Science and Technology National University of Defense TechnologyChangsha 410073China School of Information Science and Technology ShanghaiTech UniversityShanghai 201210China Institute of Software Chinese Academy of SciencesBeijing 100190China

Recurrent neural networks (RNNs) have been heavily used in applications relying on sequence data such as time series and natural languages. As a matter of fact, their behaviors lack rigorous quality assurance due to the black-box nature of deep learning. It is an urgent and challenging task to formally reason about the behaviors of RNNs. To this end, we first present an extension of linear-time temporal logic to reason about properties with respect to RNNs, such as local robustness, reachability, and some temporal properties. Based on the proposed logic, we formalize the verification obligation as a Hoare-like triple, from both qualitative and quantitative perspectives. The former concerns whether all the outputs resulting from the inputs fulfilling the pre-condition satisfy the post-condition, whereas the latter is to compute the probability that the post-condition is satisfied on the premise that the inputs fulfill the pre-condition. To tackle these problems, we develop a systematic verification framework, mainly based on polyhedron propagation, dimension-preserving abstraction, and the Monte Carlo sampling. We also implement our algorithm with a prototype tool and conduct experiments to demonstrate its feasibility and efficiency.

关键词： recurrent neural network model checking temporal logic qualitative/quantitative verification

来源：评论

学校读者我要写书评

暂无评论

GaitCycFormer: Leveraging Gait Cycles and Transformers for Gait Emotion Recognition 39

GaitCycFormer: Leveraging Gait Cycles and Transformers for G...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zeng, Qingyang Shang, Lin State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China

ISBN: (纸本)157735897X

Gait Emotion Recognition (GER) is an emerging task within Human Emotion Recognition. Skeleton-based GER requires discriminative spatial and temporal features. However, current methods primarily focus on capturing spatial topology information but fail to effectively learn temporal features from long-distance frames. Moreover, these methods are mostly sensitive to the order of sampled sequences, resulting in significant accuracy drops when sequences are randomly sampled. In order to obtain a more robust and comprehensive spatial-temporal representation of gait, we introduce the Graph-Transformer architecture into GER for the first time, proposing a novel framework named GaitCycFormer. Specifically, we designed a Cycle Position Encoding (CPE) based on the gait cycle, which explicitly segments any gait sequence into more manageable periodic units, to enhance temporal feature modeling. Additionally, we incorporate a bi-level Transformer, consisting of an Intra-cycle Transformer and an Inter-cycle Transformer to capture local and global temporal information within each gait cycle and between gait cycles respectively. Experiments demonstrate that our GaitCycFormer achieves state-of-the-art performance on popular datasets, and proves to be more reliable and robust. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Text-Guided Fine-grained Counterfactual Inference for Short Video Fake News Detection 39

Text-Guided Fine-grained Counterfactual Inference for Short ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zong, Linlin Lin, Wenmin Zhou, Jiahui Liu, Xinyue Zhang, Xianchao Xu, Bo Wu, Shimin Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China School of Computer Science and Technology Dalian University of Technology Dalian China

ISBN: (纸本)157735897X

Detecting fake news in short videos is crucial for combating misinformation. Existing methods utilize topic modeling and co-attention mechanism, overlooking the modality heterogeneity and resulting in suboptimal performance. To address this issue, we introduce Text-Guided Fine-grained Counterfactual Inference for Short Video Fake News detection (TGFC-SVFN). TGFC-SVFN leverages modality bias removal and teacher-model-enhanced inter-modal knowledge distillation to integrate the heterogeneous modalities in short videos. Specifically, we use causality-based reasoning prompts guided text as teacher model, which then transfers knowledge to the video and audio student models. Subsequently, a multi-head attention mechanism is employed to fuse information from different modalities. In each module, we utilize fine-grained counterfactual inference based on a diffusion model to eliminate modality bias. Experimental results on publicly available fake short video news datasets demonstrate that our method outperforms state-of-the-art techniques. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Container-Aware Service Function Chains Placement and Optimization in Vehicular Edge Computing 22

Container-Aware Service Function Chains Placement and Optimi...

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Zhang, Kaixin Hu, Shihong Qu, Zhihao Ye, Baoliu Hohai University School of Computer Science and Software Engineering China Nanjing University National Key Laboratory for Novel Software Technology China

ISBN: (纸本)9798331509712

In the domain of Vehicular Edge Computing (VEC), this paper addresses the complex problem of Service Function Chain (SFC) placement, which is crucial for the efficient deployment of cloud applications in vehicular environments. Our approach leverages Virtual Network Function (VNF) technology, transitioning network services from traditional hardware to more flexible, container-based edge computing frameworks. The primary objective is to organize these VNFs into functional SFCs, thereby minimizing service delays in VEC systems. SFC placement faces two significant challenges. The first is the sequential dependency among VNFs within an SFC, which adds substantial complexity to container deployment. The second challenge is the cold start delay of VNF containers, a critical issue in scenarios requiring swift response times, which negatively impacts service quality in VEC applications. To address these challenges, we propose a comprehensive model for SFC placement that considers the deployment status of VNF containers, acknowledging the complexity of this NP-hard problem. The core of our contribution is the development of the Single SFC Placement Algorithm (SSPA), a sophisticated, greedy-based approach designed for the effective placement of individual SFCs. We enhance this algorithm by incorporating a Particle Swarm Optimization (PSO) technique, making it capable of efficiently handling the placement of multiple SFCs. Our solution aims to improve edge resource utilization and mitigate startup delays associated with the initial activation of containers, thereby reducing service delays. Extensive experimental evaluations demonstrate that our algorithm achieves a 34.3% average reduction in service delay compared to four baselines and a 5.8% average reduction compared to other container-aware algorithms. © 2024 IEEE.

关键词： service function chain SFC placement vehicle edge computing virtual network function

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：