检索结果-内蒙古大学图书馆

Enhanced Acceleration for Generalized Nonconvex Low-Rank Matrix Learning

Chinese Journal of electronics 2025年第1期34卷 98-113页

作者： Hengmin Zhang Jian Yang Wenli Du Bob Zhang Zhiyuan Zha Bihan Wen School of Electrical and Electronic Engineering Nanyang Technological University School of Computer Science and Engineering Nanjing University of Science and Technology School of Information Science and Engineering East China University of Science and Technology Department of Electrical and Computer Engineering University of Macau

Matrix minimization techniques that employ the nuclear norm have gained recognition for their applicability in tasks like image inpainting, clustering, classification, and reconstruction. However, they come with inherent biases and computational burdens, especially when used to relax the rank function, making them less effective and efficient in real-world scenarios. To address these challenges, our research focuses on generalized nonconvex rank regularization problems in robust matrix completion, low-rank representation, and robust matrix regression. We introduce innovative approaches for effective and efficient low-rank matrix learning, grounded in generalized nonconvex rank relaxations inspired by various substitutes for the ?0-norm relaxed functions. These relaxations allow us to more accurately capture low-rank structures. Our optimization strategy employs a nonconvex and multi-variable alternating direction method of multipliers, backed by rigorous theoretical analysis for complexity and *** algorithm iteratively updates blocks of variables, ensuring efficient convergence. Additionally, we incorporate the randomized singular value decomposition technique and/or other acceleration strategies to enhance the computational efficiency of our approach, particularly for large-scale constrained minimization problems. In conclusion, our experimental results across a variety of image vision-related application tasks unequivocally demonstrate the superiority of our proposed methodologies in terms of both efficacy and efficiency when compared to most other related learning methods.

关键词： Learning systems Image recognition Minimization Computational efficiency Complexity theory Matrix decomposition Optimization Image reconstruction Singular value decomposition Convergence

来源：评论

学校读者我要写书评

暂无评论

Autonomous embodied navigation task generation from natural language dialogues

引用

science China(information sciences) 2025年第5期68卷 119-132页

作者： Haifeng XU Yongchang LI Lumeng MA Chunwen LI Yanzhi DONG Xiaohu YUAN Huaping LIU Department of Automation Tsinghua University School of Physics and Electronic Information Yantai University School of Electrical and Electronic Engineering Shanghai Institute of Technology Department of Computer Science and Technology Tsinghua University

Robots are increasingly being deployed in densely populated environments, such as homes, hotels, and office buildings, where they rely on explicit instructions from humans to perform tasks. However, complex tasks often require multiple instructions and prolonged monitoring, which can be time-consuming and demanding for users. Despite this, there is limited research on enabling robots to autonomously generate tasks based on real-life scenarios. Advanced intelligence necessitates robots to autonomously observe and analyze their environment and then generate tasks autonomously to fulfill human requirements without explicit commands. To address this gap, we propose the autonomous generation of navigation tasks using natural language dialogues. Specifically, a robot autonomously generates tasks by analyzing dialogues involving multiple persons in a real office environment to facilitate the completion of item transportation between various *** propose the leveraging of a large language model(LLM) through chain-of-thought prompting to generate a navigation sequence for a robot from dialogues. We also construct a benchmark dataset consisting of 625 multiperson dialogues using the generation capability of LLMs. Evaluation results and real-world experiments in an office building demonstrate the effectiveness of the proposed method.

关键词： proactive robot robot navigation service robot large language model

来源：评论

学校读者我要写书评

暂无评论

Solid additive modulates acceptor crystallization to achieve 19.11%efficiency and high storage stability in organic solar cells

引用

Journal of Energy Chemistry 2025年第4期103卷 19-26页

作者： Luye Cao Hengyuan Zhang Jingwen Du Zeyu He Xiaoyang Du Hui Lin Caijun Zheng Gang Yang Xinrui Li Silu Tao School of Optoelectronic Science and Engineering University of Electronic Science and Technology of ChinaChengdu 610054SichuanChina School of Electrical Engineering and Electronic Information Xihua UniversityChengdu 610039SichuanChina

Ideal nanoscale phase-separated morphology is the primary condition to obtain high photovoltaic conversion efficiency(PCE)and high stability of organic solar cells(OSCs).However,the differences in solubility,miscibility and crystallinity between donors and acceptors make it difficult to achieve the optimal active layer morphology of ***,the volatile solid additive 3,5-dibromotoluene(DTL)with strong electronegativity and dipole moment has been developed for *** can interact with the acceptor,modulating its crystallization and stacking,enhancing donor/acceptor miscibility,reducing trap density,inhibiting carrier recombination,and balancing charge ***,the introduction of DTL finely tunes the energy level of the accepto r,which greatly enhances the open-circuit voltage(V_(OC))of the device compared to the conventional additive 1,8-diiodooctane(DIO).As a result,the DTL-treated PM6:L8-BObased OSCs obtained a high PCE of 18.87%and enhanced ***,the PM6:PM1:L8-BO+DTL-based OSCs achieved a champion PCE of 19.11%.This work deepens the working mechanism of additive strategy for regulating the morphology and improving performance,providing an effective method for achieving high-performance OSCs.

关键词： Additive strategy Intermolecular interaction Energy level regulation Energetic disorder Trap density

来源：评论

学校读者我要写书评

暂无评论

Metarelation2vec:A Metapath-Free Scalable Representation Learning Model for Heterogeneous Networks

引用

Tsinghua science and technology 2024年第2期29卷 553-575页

作者： Lei Chen Yuan Li Yong Lei Xingye Deng School of Information and Electrical Engineering Hunan University of Science and TechnologyXiangtan 411201China School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan 411201China

Metapaths with specific complex semantics are critical to learning diverse semantic and structural information of heterogeneous networks(HNs)for most of the existing representation learning ***,any metapaths consisting of multiple,simple metarelations must be driven by domain *** sensitive,expensive,and limited metapaths severely reduce the flexibility and scalability of the existing models.A metapath-free,scalable representation learning model,called Metarelation2vec,is proposed for HNs with biased joint learning of all metarelations in a bid to address this ***,a metarelation-aware,biased walk strategy is first designed to obtain better training samples by using autogenerating cooperation probabilities for all metarelations rather than using expert-given ***,grouped nodes by the type,a common and shallow skip-gram model is used to separately learn structural proximity for each node ***,grouped links by the type,a novel and shallow model is used to separately learn the semantic proximity for each link ***,supervised by the cooperation probabilities of all meta-words,the biased training samples are thrown into the shallow models to jointly learn the structural and semantic information in the HNs,ensuring the accuracy and scalability of the *** experimental results on three tasks and four open datasets demonstrate the advantages of our proposed model.

关键词： metarelation random walk heterogeneous network metapath representation learning

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving recommendation with coarse-grained spatiotemporal contexts

引用

science China(information sciences) 2025年第4期68卷 66-81页

作者： Lei CHEN Chen GAO Jiahuan LEI Xiaoyi DU Xinlei SHI Hengliang LUO Depeng JIN Yong LI Meng WANG Department of Electronic Engineering BNRist Tsinghua University Meituan Inc. School of Computer Science and Information Engineering Hefei University of Technology

The behavior of users on online life service platforms like Meituan and Yelp often occurs within specific finegrained spatiotemporal contexts(i.e., when and where). Recommender systems, designed to serve millions of users, typically operate in a fully server-based manner, requiring on-device users to upload their behavioral data, including fine-grained spatiotemporal contexts, to the server, which has sparked public concern regarding privacy. Consequently, user devices only upload coarse-grained spatiotemporal contexts for user privacy protection. However, previous research mostly focuses on modeling fine-grained spatiotemporal contexts using knowledge graph convolutional models, which are not applicable to coarse-grained spatiotemporal contexts in privacy-constrained recommender systems. In this paper, we investigate privacy-preserving recommendation by leveraging coarse-grained spatiotemporal contexts. We propose the coarse-grained spatiotemporal knowledge graph for privacy-preserving recommendation(CSKG), which explicitly models spatiotemporal co-occurrences using common-sense knowledge from coarse-grained contexts. Specifically, we begin by constructing a spatiotemporal knowledge graph tailored to coarse-grained spatiotemporal contexts. Then we employ a learnable metagraph network that integrates common-sense information to filter and extract co-occurrences. CSKG evaluates the impact of coarsegrained spatiotemporal contexts on user behavior through the use of a knowledge graph convolutional network. Finally, we introduce joint learning to effectively learn representations. By conducting experiments on two real large-scale datasets,we achieve an average improvement of about 11.0% on two ranking metrics. The results clearly demonstrate that CSKG outperforms state-of-the-art baselines.

关键词： privacy-preserveing coarse-grained spatiotemporal contexts recommender systems

来源：评论

学校读者我要写书评

暂无评论

Privacy-preserving explainable AI: a survey

引用

science China(information sciences) 2025年第1期68卷 23-56页

作者： Thanh Tam NGUYEN Thanh Trung HUYNH Zhao REN Thanh Toan NGUYEN Phi Le NGUYEN Hongzhi YIN Quoc Viet Hung NGUYEN School of Information and Communication Technology Griffith University School of Computer and Communication Sciences Ecole Polytechnique Federale de Lausanne Faculty of Mathematics and Computer Science University of Bremen Faculty of Information Technology HUTECH University Department of Computer Science Hanoi University of Science and Technology School of Electrical Engineering and Computer Science The University of Queensland

As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

关键词： privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI

来源：评论

学校读者我要写书评

暂无评论

MMInstruct: a high-quality multi-modal instruction tuning dataset with extensive diversity

引用

science China(information sciences) 2024年第12期67卷 36-51页

作者： Yangzhou LIU Yue CAO Zhangwei GAO Weiyun WANG Zhe CHEN Wenhai WANG Hao TIAN Lewei LU Xizhou ZHU Tong LU Yu QIAO Jifeng DAI School of Computer Science Nanjing University School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai AI Laboratory School of Computer Science Fudan University Department of Information Engineering The Chinese University of Hong Kong SenseTime Research Department of Electronic Engineering Tsinghua University

Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of vision large language models(VLLMs), existing visual instruction tuning datasets include the following limitations.(1) Instruction annotation quality: despite existing VLLMs exhibiting strong performance,instructions generated by those advanced VLLMs may still suffer from inaccuracies, such as hallucinations.(2) Instructions and image diversity: the limited range of instruction types and the lack of diversity in image data may impact the model's ability to generate diversified and closer to real-world scenarios outputs. To address these challenges, we construct a high-quality, diverse visual instruction tuning dataset MMInstruct,which consists of 973k instructions from 24 domains. There are four instruction types: judgment, multiplechoice, long visual question answering, and short visual question answering. To construct MMInstruct, we propose an instruction generation data engine that leverages GPT-4V, GPT-3.5, and manual correction. Our instruction generation engine enables semi-automatic, low-cost, and multi-domain instruction generation at 1/6 the cost of manual construction. Through extensive experiment validation and ablation experiments,we demonstrate that MMInstruct could significantly improve the performance of VLLMs, e.g., the model fine-tuning on MMInstruct achieves new state-of-the-art performance on 10 out of 12 benchmarks. The code and data shall be available at https://***/yuecao0119/MMInstruct.

关键词： instruction tuning multi-modal multi-domain dataset vision large language model

来源：评论

学校读者我要写书评

暂无评论

Research on temperature distribution characteristics of oilimmersed power transformers based on fluid network decoupling

引用

High Voltage 2024年第5期9卷 1136-1148页

作者： Yongming Xu Ziyi Xu Congrui Ren Yaodong Wang School of Electrical and Information Engineering Changzhou Institute of TechnologyChangzhouChina School of Electrical and Electronic Engineering Harbin University of Science and TechnologyHarbinChina Department of Engineering Durham UniversityDurhamUK

Due to the complex structure and large size of large-capacity oil-immersed power transformers,it is difficult to predict the winding temperature distribution directly by numerical analysis.A 180 MVA,220 kV oil-immersed self-cooling power transformer is used as the research *** authors decouple the internal fluid domain of the power transformer into four regions:high voltage windings,medium voltage windings,low voltage windings,and radiators through fluid networks and establish the 3D fluidtemperature field numerical analysis model of the four regions,*** results of the fluid network model are used as the inlet boundary conditions for the 3D fluidtemperature numerical analysis *** turn,the fluid resistance of the fluid network model is corrected according to the results of the 3D fluid-temperature field numerical analysis *** prediction of the temperature distribution of windings is realised by the coupling calculation between the fluid network model and the 3D fluid-temperature field numerical analysis *** on this,the effect of the loading method of the heat source is also investigated using the proposed *** hotspot temperatures of the high-voltage,medium-voltage,and low-voltage windings are 89.43,86.33,and 80.96°C,***,an experimental platform is built to verify the *** maximum relative error between calculated and measured values is 4.42%,which meets the engineering accuracy requirement.

关键词： winding network distribution

来源：评论

学校读者我要写书评

暂无评论

A Generative Model-Based Network Framework for Ecological Data Reconstruction

引用

computers, Materials & Continua 2025年第1期82卷 929-948页

作者： Shuqiao Liu Zhao Zhang Hongyan Zhou Xuebo Chen School of Electronic and Information Engineering University of Science and Technology LiaoningAnshan114051China School of Computer Science and Software Engineering University of Science and Technology LiaoningAnshan114051China

This study examines the effectiveness of artificial intelligence techniques in generating high-quality environmental data for species introductory site selection *** Strengths,Weaknesses,Opportunities,Threats(SWOT)analysis data with Variation Autoencoder(VAE)and Generative AdversarialNetwork(GAN)the network framework model(SAE-GAN),is proposed for environmental data *** model combines two popular generative models,GAN and VAE,to generate features conditional on categorical data embedding after SWOT *** model is capable of generating features that resemble real feature distributions and adding sample factors to more accurately track individual sample *** data is used to retain more semantic information to generate *** model was applied to species in Southern California,USA,citing SWOT analysis data to train the *** show that the model is capable of integrating data from more comprehensive analyses than traditional methods and generating high-quality reconstructed data from them,effectively solving the problem of insufficient data collection in development *** model is further validated by the Technique for Order Preference by Similarity to an Ideal Solution(TOPSIS)classification assessment commonly used in the environmental data *** study provides a reliable and rich source of training data for species introduction site selection systems and makes a significant contribution to ecological and sustainable development.

关键词： Convolutional Neural Network(CNN) VAE GAN TOPSIS data reconstruction

来源：评论

学校读者我要写书评

暂无评论

Robust federated contrastive recommender system against targeted model poisoning attack

引用

science China(information sciences) 2025年第4期68卷 50-65页

作者： Wei YUAN Chaoqun YANG Liang QU Guanhua YE Quoc Viet Hung NGUYEN Hongzhi YIN School of Electrical Engineering and Computer Science The University of Queensland School of Information and Communication Technology Griffith University Deep Neural Computing Company Limited

Federated recommender systems(FedRecs) have garnered increasing attention recently, thanks to their privacypreserving benefits. However, the decentralized and open characteristics of current FedRecs present at least two ***, the performance of FedRecs is compromised due to highly sparse on-device data for each client. Second, the system's robustness is undermined by the vulnerability to model poisoning attacks launched by malicious users. In this paper, we introduce a novel contrastive learning framework designed to fully leverage the client's sparse data through embedding augmentation, referred to as CL4FedRec. Unlike previous contrastive learning approaches in FedRecs that necessitate clients to share their private parameters, our CL4FedRec aligns with the basic FedRec learning protocol, ensuring compatibility with most existing FedRec implementations. We then evaluate the robustness of FedRecs equipped with CL4FedRec by subjecting it to several state-of-the-art model poisoning attacks. Surprisingly, our observations reveal that contrastive learning tends to exacerbate the vulnerability of FedRecs to these attacks. This is attributed to the enhanced embedding uniformity, making the polluted target item embedding easily proximate to popular items. Based on this insight, we propose an enhanced and robust version of CL4FedRec(rCL4FedRec) by introducing a regularizer to maintain the distance among item embeddings with different popularity levels. Extensive experiments conducted on four commonly used recommendation datasets demonstrate that rCL4FedRec significantly enhances both the model's performance and the robustness of FedRecs.

关键词： federated recommender system contrastive learning model poisoning attack and defense

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：