检索结果-内蒙古大学图书馆

18th International Joint Conference on Theoretical Computer Science-Frontier of Algorithmic Wisdom, IJTCS-FAW 2024

作者： Liang, Huili Wang, Xiao Wei, Yechao Wu, Pingfan Shanghai University of Finance and Economics Shanghai China North East Normal University Changchun China Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai China

ISBN: (纸本)9789819777518

Optimization on Riemannian manifolds has attracted the attention of many in the machine learning community due to its potential in solving constrained optimization problems. However, high cost of geodesic-based retraction algorithms often limits the applications of Riemannian optimization algorithm in practical problems that are intensely resource consuming. We focus on the positive orthant constrained optimization problems, a special type of constraint that are present in many application areas from evolutionary game theory to non-negative matrix factorization. We propose an accelerated natural gradient descent algorithm modified from evolutionary game dynamics and show that our algorithm converges to second-order stationary points. Our theoretical analysis and experiments verify that a geodesic free acceleration scheme has the potential to balance the convergence guarantee and computational efficiency in constrained non-convex optimization problems like non-negative matrix factorization. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Hedonic Coalition Formation Game and Contract-Based Federated Learning in AAV-Assisted Internet of Things

引用

IEEE Internet of Things Journal 2025年第9期12卷 11258-11272页

作者： Liu, Jia Li, Xiaoxu Xu, Yang Lyu, Chen Wang, Yichuan Liu, Xiaoying Xidian University School of Computer Science and Technology Xi’an710071 China Shanghai University of Finance and Economics School of Computing and Artificial Intelligence MoE Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai200433 China Xi’an University of Technology Shaanxi Key Laboratory of Network Computing and Security Technology Xi’an710071 China Zhejiang University of Technology School of Computer Science and Technology Hangzhou310023 China

Coupled with the rise of Deep Learning, the wealth of data and enhanced computation capabilities of Internet of Things (IoT) components enable effective artificial intelligence (AI)-based models to be built. Beyond ground data sources, autonomous aerial vehicles (AAVs)-based service providers for data collection and AI model training, i.e., Drones-as-a-Service (DaaS), have become increasingly popular in recent years. However, the stringent regulations governing data privacy potentially impede data sharing across independently owned AAVs. To this end, we propose in this article a federated learning (FL)-based architecture that enables privacy-preserving collaborative machine learning across a federation of independent DaaS providers for the development of IoT applications. Specifically, this work introduces a novel incentive mechanism based on the hedonic coalition formation game to enhance the sustainable efficiency and stability of the FL system. By establishing tailored operational rules and functions, the proposed mechanism enables IoT sensing nodes to autonomously form optimal coalitions with AAVs, thereby ensuring robust collaboration. To deal with incentive mismatches and information asymmetry, we leverage the contract theory and propose a self-disclosure mechanism that guarantees truthful reporting of AAV capabilities while optimizing the global model owner’s profits. The performance-based AAV type is also defined to offer a practical measure for heterogeneous AAVs and serve as the foundation for fair and effective contract design. Simulation results validate the superiority of the proposed approach, demonstrating significant improvements in utility optimization and system stability compared to existing benchmarks. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Error Slice Discovery via Manifold Compactness

arXiv

引用

arXiv 2025年

作者： Yu, Han Liu, Jiashuo Zou, Hao Xu, Renzhe He, Yue Zhang, Xingxuan Cui, Peng Department of Computer Science and Technology Tsinghua University Beijing China ITCS Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai University of Finance and Economics Shanghai China

Despite the great performance of deep learning models in many areas, they still make mistakes and underperform on certain subsets of data, i.e. error slices. Given a trained model, it is important to identify its semantically coherent error slices that are easy to interpret, which is referred to as the error slice discovery problem. However, there is no proper metric of slice coherence without relying on extra information like predefined slice labels. Current evaluation of slice coherence requires access to predefined slices formulated by metadata like attributes or subclasses. Its validity heavily relies on the quality and abundance of metadata, where some possible patterns could be ignored. Besides, current algorithms cannot directly incorporate the constraint of coherence into their optimization objective due to the absence of an explicit coherence metric, which could potentially hinder their effectiveness. In this paper, we propose manifold compactness, a coherence metric without reliance on extra information by incorporating the data geometry property into its design, and experiments on typical datasets empirically validate the rationality of the metric. Then we develop Manifold Compactness based error Slice Discovery (MCSD), a novel algorithm that directly treats risk and coherence as the optimization objective, and is flexible to be applied to models of various tasks. Extensive experiments on the benchmark and case studies on other typical datasets demonstrate the superiority of MCSD. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning Personalizable Clustered Embedding for Recommender Systems

引用

ACM Transactions on Recommender Systems 2025年第3期3卷 1-38页

作者： Yizhou Chen Guangda Huzhang Anxiang Zeng Qingtao Yu Hui Sun Heng-Yi Li Jingyi Li Yabo Ni Han Yu Zhiming Zhou Shopee Pte Ltd. Singapore Singapore SCSE Nanyang Technological University Singapore Singapore Shopee Pte Ltd. Shanghai China Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai University of Finance and Economics Shanghai China

In recent years, recommender systems have advanced rapidly, where embedding learning for users and items plays a critical role. A standard method learns a unique embedding vector for each user and item. However, such a method has two important limitations in real-world applications: (1) it is hard to learn embeddings that generalize well for users and items that have rare interactions, and (2) it may incur unbearably high memory costs when the number of users and items scales up. Existing approaches either can only address one of the limitations or have flawed overall performances. In this article, we propose Clustered Embedding Learning (CEL) as an integrated solution to these two problems. CEL is a plug-and-play embedding learning framework that can be combined with any differentiable feature interaction model. It is capable of achieving improved performance, especially for cold users and items, with reduced memory cost. CEL enables automatic and dynamic clustering of users and items in a top-down fashion, where clustered entities could jointly learn a shared embedding. The accelerated version of CEL has an optimal time complexity, which supports efficient online updates. Theoretically, we prove the identifiability and the existence of a unique optimal number of clusters for CEL in the context of nonnegative matrix factorization. Empirically, we validate the effectiveness of CEL on three public datasets and one business dataset, showing its consistently superior performance against state-of-the-art methods. In particular, when incorporating CEL into the business model, it brings an improvement of \(+0.6\%\) in AUC, which translates into a significant revenue gain; meanwhile, the size of the embedding table gets 2,650 times smaller. Additionally, we demonstrate that if there is enough memory, learning a personalized embedding for each user and item around their clustering centers is feasible and can further boost performance. In this article, we enhance and extend

关键词： Embedding learning clustering recommender system meta-learning sparse data large-scale

来源：评论

学校读者我要写书评

暂无评论

ABXI: Invariant Interest Adaptation for Task-Guided Cross-Domain Sequential Recommendation

arXiv

引用

arXiv 2025年

作者： Bian, Qingtian Vinícius de Carvalho, Marcus Li, Tieying Xu, Jiaxing Fang, Hui Ke, Yiping College of Computing and Data Science Nanyang Technological University Singapore School of Computer Science and Engineering Northeastern University China Research Institute for Interdisciplinary Sciences Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai University of Finance and Economics Shanghai China

Cross-Domain Sequential Recommendation (CDSR) has recently gained attention for countering data sparsity by transferring knowledge across domains. A common approach merges domain-specific sequences into cross-domain sequences, serving as bridges to connect domains. One key challenge is to correctly extract the shared knowledge among these sequences and appropriately transfer it. Most existing works directly transfer unfiltered cross-domain knowledge rather than extracting domain-invariant components and adaptively integrating them into domain-specific modelings. Another challenge lies in aligning the domain-specific and cross-domain sequences. Existing methods align these sequences based on timestamps, but this approach can cause prediction mismatches when the current tokens and their targets belong to different domains. In such cases, the domain-specific knowledge carried by the current tokens may degrade performance. To address these challenges, we propose the A-B-Cross-to-Invariant Learning Recommender (ABXI). Specifically, leveraging LoRA’s effectiveness for efficient adaptation, ABXI incorporates two types of LoRAs to facilitate knowledge adaptation. First, all sequences are processed through a shared encoder that employs a domain LoRA for each sequence, thereby preserving unique domain characteristics. Next, we introduce an invariant projector that extracts domain-invariant interests from cross-domain representations, utilizing an invariant LoRA to adapt these interests into modeling each specific domain. Besides, to avoid prediction mismatches, all domain-specific sequences are aligned to match the domains of the cross-domain ground truths. Experimental results on three datasets demonstrate that our approach outperforms other CDSR counterparts by a large margin. The codes are available in https://***/DiMarzioBian/ABXI. © 2025, CC BY.

关键词： Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

ABXI: Invariant Interest Adaptation for Task-Guided Cross-Domain Sequential Recommendation 25

ABXI: Invariant Interest Adaptation for Task-Guided Cross-Do...

引用

Proceedings of the ACM on Web Conference 2025

作者： Qingtian Bian Marcus de Carvalho Tieying Li Jiaxing Xu Hui Fang Yiping Ke College of Computing and Data Science Nanyang Technological University Singapore Singapore School of Computer Science and Engineering Northeastern University Shenyang China Research Institute for Interdisciplinary Sciences and Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai University of Finance and Economics Shanghai China

ISBN: (纸本)9798400712746

Cross-Domain Sequential Recommendation (CDSR) has recently gained attention for countering data sparsity by transferring knowledge across domains. A common approach merges domain-specific sequences into cross-domain sequences, serving as bridges to connect domains. One key challenge is to correctly extract the shared knowledge among these sequences and appropriately transfer it. Most existing works directly transfer unfiltered cross-domain knowledge rather than extracting domain-invariant components and adaptively integrating them into domain-specific modelings. Another challenge lies in aligning the domain-specific and cross-domain sequences. Existing methods align these sequences based on timestamps, but this approach can cause prediction mismatches when the current tokens and their targets belong to different domains. In such cases, the domain-specific knowledge carried by the current tokens may degrade performance. To address these challenges, we propose the A-B-Cross-to-Invariant Learning Recommender (ABXI). Specifically, leveraging LoRA's effectiveness for efficient adaptation, ABXI incorporates two types of LoRAs to facilitate knowledge adaptation. First, all sequences are processed through a shared encoder that employs a domain LoRA for each sequence, thereby preserving unique domain characteristics. Next, we introduce an invariant projector that extracts domain-invariant interests from cross-domain representations, utilizing an invariant LoRA to adapt these interests into modeling each specific domain. Besides, to avoid prediction mismatches, all domain-specific sequences are aligned to match the domains of the cross-domain ground truths. Experimental results on three datasets demonstrate that our approach outperforms other CDSR counterparts by a large margin. The codes are available in https://***/DiMarzioBian/ABXI.

关键词： cross-domain sequential recommendation

来源：评论

学校读者我要写书评

暂无评论

Price Stability and Improved Buyer Utility with Presentation Design: A Theoretical Study of the Amazon Buy Box 25

Price Stability and Improved Buyer Utility with Presentation...

引用

Proceedings of the ACM on Web Conference 2025

作者： Ophir Friedler Hu Fu Anna Karlin Ariana Tang Outbrain Netanya Israel Key Laboratory of Interdisciplinary Research of Computation and Economics Ministry of Education Shanghai University of Finance and Economics Shanghai China Allen School of Computer Science & Engineering University of Washington Seattle WA USA Shanghai University of Finance and Economics Shanghai China

ISBN: (纸本)9798400712746

Platforms design the form of presentation by which sellers are shown to the buyers. This design not only shapes the buyers' experience but also leads to different market equilibria or dynamics. One component in this design is through the platform's mediation of the search frictions experienced by the buyers for different sellers. We take a model of monopolistic competition and show that, on one hand, when all sellers have the same inspection costs, the market sees no stable price since the sellers always have incentives to undercut each other, and, on the other hand, the platform may stabilize the price by giving prominence to one seller chosen by a carefully designed mechanism. This calls to mind Amazon's Buy Box. We study natural mechanisms for choosing the prominent seller, characterize the range of equilibrium prices implementable by them, and find that in certain scenarios the buyers' surplus improves as the search friction increases.

关键词： Pandora box problem

来源：评论

学校读者我要写书评

暂无评论

A Bicriterion Concentration Inequality and Prophet Inequalities for k-Fold Matroid Unions 16

A Bicriterion Concentration Inequality and Prophet Inequalit...

引用

16th Innovations in Theoretical Computer Science Conference, ITCS 2025

作者： Alon, Noga Gravin, Nick Pollner, Tristan Rubinstein, Aviad Wang, Hongao Weinberg, S. Matthew Zhang, Qianfan Department of Mathematics Princeton University NJ United States Schools of Mathematics and Computer Science Tel Aviv University Tel Aviv Israel Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai University of Finance and Economics China Department of Management Science and Engineering Stanford University CA United States Department of Computer Science Stanford University CA United States Department of Computer Science Purdue University West LafayetteIN United States Department of Computer Science Princeton University NJ United States

ISBN: (纸本)9783959773614

We investigate prophet inequalities with competitive ratios approaching 1, seeking to generalize k-uniform matroids. We first show that large girth does not suffice: for all k, there exists a matroid of girth ≥ k and a prophet inequality instance on that matroid whose optimal competitive ratio is12. Next, we show k-fold matroid unions do suffice: we provide a prophet inequality with competitive ratio (Formula presented) for any k-fold matroid union. Our prophet inequality follows from an online contention resolution scheme. The key technical ingredient in our online contention resolution scheme is a novel bicriterion concentration inequality for arbitrary monotone 1-Lipschitz functions over independent items which may be of independent interest. Applied to our particular setting, our bicriterion concentration inequality yields "Chernoff-strength" concentration for a 1-Lipschitz function that is not (approximately) self-bounding. © Noga Alon, Nick Gravin, Tristan Pollner, Aviad Rubinstein, Hongao Wang, S. Matthew Weinberg, and Qianfan Zhang.

关键词： Choquet integral

来源：评论

学校读者我要写书评

暂无评论

Imperceptible and Targeted Physical Attacks on Deep Learning-Based Speech Semantic Communications

Imperceptible and Targeted Physical Attacks on Deep Learning...

引用

IEEE Conference on Wireless Communications and Networking

作者： Yuhao Hua Yang Xu Chen Lyu Jia Liu Yulong Shen Weidong Yang Norio Shiratori Hangzhou Institute of Technology Xidian University Hangzhou China School of Computer Science and Technology Xidian University Xi'an China MoE Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai University of Finance and Economics Shanghai China Center for Strategic Cyber Resilience Research and Development National Institute of Informatics Tokyo Japan Research and Development Initiative Chuo University Tokyo Japan

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

The deep learning-based semantic communication system (DeepSC) is designed to improve the efficiency and accuracy of information transmission, by leveraging joint source-channel coding techniques to extract relevant semantic features. However, existing research on attack methods targeting DeepSC has primarily focused on text and image domains, leaving the speech domain largely unexplored. To this end, this paper proposes Iterative Semantic Gradient Update (ISGU), a novel approach for crafting physical layer adversarial attacks on DeepSC for speech transmission (DeepSC-ST). Specifically, we introduce a joint loss that combines the semantic similarity loss with Connectionist Temporal Classification loss to expedite the generation process of targeted attacks against the DeepSC-ST. In addition, we design an algorithm to generate adversarial examples, enhancing their imperceptibility by meticulously controlling the perturbation power added to the input speech. Extensive experiments indicate that ISGU is capable of rapidly generating highly covert adversarial examples, with a notably high attack success rate.

关键词： Training Perturbation methods Oral communication Information processing Speech enhancement Semantic communication Physical layer Feature extraction Security Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Topological chaos in oligopoly competition

引用

economics Letters 2025年 252卷

作者： Li, Xiaoliang Zhang, Ally Quan School of Business Guangzhou College of Technology and Business Guangzhou 510850 China MoE Key Laboratory of Interdisciplinary Research of Computation and Economics Shanghai University of Finance and Economics Shanghai 200433 China Department of Accounting and Finance Lancaster University Management School Lancaster University Lancaster LA1 4YX United Kingdom

This letter demonstrates that oligopoly competition can exhibit topological chaos by applying Mitra's sufficient condition. To overcome the computational challenges arising from the lack of a simple closed-form expression for the modal point, we develop a resultant-based method. Our results show that, for a sufficiently large number of firms, there must exist parameter values that guarantee topological chaos. © 2025 The Authors

关键词： Mitra's sufficient condition Oligopoly game Resultant Topological chaos

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：