检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Liang, Jianqing Chen, Min Liang, Jiye Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education School of Computer and Information Technology Shanxi University Shanxi Taiyuan030006 China

The Transformer architecture has recently gained considerable attention in the field of graph representation learning, as it naturally overcomes several limitations of Graph Neural Networks (GNNs) with customized attention mechanisms or positional and structural encodings. Despite making some progress, existing works tend to overlook external information of graphs, specifically the correlation between graphs. Intuitively, graphs with similar structures should have similar representations. Therefore, we propose Graph External Attention (GEA) - a novel attention mechanism that leverages multiple external node/edge key-value units to capture inter-graph correlations implicitly. On this basis, we design an effective architecture called Graph External Attention Enhanced Transformer (GEAET), which integrates local structure and global interaction information for more comprehensive graph representations. Extensive experiments on benchmark datasets demonstrate that GEAET achieves state-of-the-art empirical performance. The source code is available for reproducibility at: https://***/icm1018/GEAET. Copyright 2024 by the author(s)

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Causal Representation Enhances Cross-Domain Named Entity Recognition in Large Language Models

引用

computers, Materials & Continua 2025年第5期83卷 2809-2828页

作者： Jiahao Wu Jinzhong Xu Xiaoming Liu Guan Yang Jie Liu School of Artificial Intelligence Zhongyuan University of TechnologyZhengzhou450007China School of Computer Science Zhongyuan University of TechnologyZhengzhou450007China Zhengzhou Key Laboratory of Text Processing and Image Understanding Zhengzhou450007China School of Information Science and Technology North China University of TechnologyBeijing100144China

Large language models cross-domain named entity recognition task in the face of the scarcity of large language labeled data in a specific domain,due to the entity bias arising from the variation of entity information between different domains,which makes large language models prone to spurious correlations problems when dealing with specific domains and *** order to solve this problem,this paper proposes a cross-domain named entity recognition method based on causal graph structure enhancement,which captures the cross-domain invariant causal structural representations between feature representations of text sequences and annotation sequences by establishing a causal learning and intervention module,so as to improve the utilization of causal structural features by the large languagemodels in the target domains,and thus effectively alleviate the false entity bias triggered by the false relevance problem;meanwhile,through the semantic feature fusion module,the semantic information of the source and target domains is effectively *** results show an improvement of 2.47%and 4.12%in the political and medical domains,respectively,compared with the benchmark model,and an excellent performance in small-sample scenarios,which proves the effectiveness of causal graph structural enhancement in improving the accuracy of cross-domain entity recognition and reducing false correlations.

关键词： Large language model entity bias causal graph structure

来源：评论

学校读者我要写书评

暂无评论

A Bayesian matrix factorization model for dynamic user embedding in recommender system

引用

Frontiers of computer Science 2022年第5期16卷 233-235页

作者： Kaihan ZHANG Zhiqiang WANG Jiye LIANG Xingwang ZHAO Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education School of Computer and Information TechnologyShanxi UniversityTaiyuan 030006China

1 Introduction The main idea of recommender system is how to learn accurate users’embeddings from behavior data[1].Each dimension of users’embeddings can reflect the interests of users in different potential *** real-world scenarios,users’interests are drifting over time,which brings a challenge to learn accurate dynamic users’***,various time-aware recommendation methods have been proposed to tackle this problem by modeling the evolution process of users’interests[2−4].However,they usually assume that users’embeddings drift with the same range on all *** practice,users’embeddings should change diversely on different dimensions over ***,for the rapidly changing interests of the users,the corresponding dimensions should change *** the contrary,the dimensions representing stable interests may change slightly.

关键词： dimensions system dynamic

来源：评论

学校读者我要写书评

暂无评论

LOG: A Local-to-Global Optimization Approach for Retrieval-based Explainable Multi-Hop Question Answering 31

LOG: A Local-to-Global Optimization Approach for Retrieval-b...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Xu, Hao Zhao, Yunxiao Zhang, Jiayang Wang, Zhiqiang Li, Ru School of Computer and Information Technology Shanxi University Taiyuan China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China

ISBN: (纸本)9798891761964

Multi-hop question answering (MHQA) aims to utilize multi-source intensive documents retrieved to derive the answer. However, it is very challenging to model the importance of knowledge retrieved. Previous approaches primarily emphasize single-step and multi-step iterative decomposition or retrieval, which are susceptible to failure in long-chain reasoning due to the progressive accumulation of erroneous information. To address this problem, we propose a novel Local-tO-Global optimized retrieval method (LOG) to discover more beneficial information, facilitating the MHQA. In particular, we design a pointwise conditional V-information based local information modeling to cover usable documents with reasoning knowledge. We also improve tuplet objective loss, advancing multi-examples-aware global optimization to model the relationship between scattered documents. Extensive experimental results demonstrate our proposed method outperforms prior state-of-the-art models, and it can significantly improve multi-hop reasoning, notably for long-chain reasoning. Our code is available at https://***/yunxiaomr/LOG. © 2025 Association for Computational Linguistics.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Enhancing Event Causality Identification with LLM Knowledge and Concept-Level Event Relations 31

Enhancing Event Causality Identification with LLM Knowledge ...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Su, Ya Zhang, Hu Zhang, Guangjun Wang, Yujie Fan, Yue Li, Ru Wang, Yuanlong School of Computer and Information Technology Shanxi University Taiyuan China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Taiyuan China

ISBN: (纸本)9798891761964

Event Causality Identification (ECI) aims to identify fine-grained causal relationships between events in an unstructured text. Existing ECI methods primarily rely on knowledge-enhanced and graph-based reasoning approaches, but they often overlook the dependencies between similar events. Additionally, the connection between unstructured text and structured knowledge is relatively weak. Therefore, this paper proposes an ECI method enhanced by LLM Knowledge and Concept-Level Event Relations (LKCER). Specifically, LKCER constructs a conceptual-level heterogeneous event graph by leveraging the local contextual information of related event mentions, generating a more comprehensive global semantic representation of event concepts. At the same time, the knowledge generated by COMET is filtered and enriched using LLM, strengthening the associations between event pairs and knowledge. Finally, the joint event conceptual representation and knowledge-enhanced event representation are used to uncover potential causal relationships between events. The experimental results show that our method outperforms previous state-of-the-art methods on both benchmarks, EventStoryLine and Causal-TimeBank. © 2025 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on mixed decision implications based on formal concept analysis

引用

International Journal of Cognitive Computing in Engineering 2023年第1期4卷 71-77页

作者： Ren, Xingguo Li, Deyu Zhai, Yanhui School of Computer and Information Technology Shanxi University Shanxi Taiyuan030006 China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi University Shanxi Taiyuan030006 China

Decision implication is an important form of knowledge representation and acquisition in Formal Concept Analysis. Decision implication reduces the redundancy of knowledge extracted from data. However, decision implication cannot extract negative information from data, so there is information loss in decision implication. This paper introduces negative attributes to decision implication and proposes mixed decision implication, enabling decision implication to extract negative knowledge from data and to represent richer decision knowledge. This paper studies the logical systems of mixed decision implications. The semantical system of mixed decision implications is constructed to represent and deduce sound mixed decision implications and avoid contradictory mixed decision implications. In the syntactical system, Mixed Augmentation and Mixed Combination are introduced and the soundness, completeness and non-redundancy of these two inference rules are proved. © 2023

关键词： Formal concept analysis

来源：评论

学校读者我要写书评

暂无评论

FSA-Net:A Cost-efficient Face Swapping Attention Network with Occlusion-Aware Normalization

引用

Intelligent Automation & Soft Computing 2023年第7期37卷 971-983页

作者： Zhipeng Bin Huihuang Zhao Xiaoman Liang Wenli Chen College of Computer Science and Technology Hengyang Normal UniversityHengyang421002China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang421002China

The main challenges in face swapping are the preservation and adaptive superimposition of attributes of two *** this study,the Face Swapping Attention Network(FSA-Net)is proposed to generate photoreal-istic face *** existing face-swapping methods ignore the blending attributes or mismatch the facial keypoint(cheek,mouth,eye,nose,etc.),which causes artifacts and makes the generated face silhouette *** address this problem,a novel reinforced multi-aware attention module,referred to as RMAA,is proposed for handling facial fusion and expression occlusion *** framework includes two *** the first stage,a novel attribute encoder is proposed to extract multiple levels of target face attributes and integrate identities and attributes when synthesizing swapped *** the second stage,a novel Stochastic Error Refinement(SRE)module is designed to solve the problem of facial occlusion,which is used to repair occlusion regions in a semi-supervised way without any *** proposed method is then compared with the current state-of-the-art *** obtained results demonstrate the qualitative and quantitative outperformance of the proposed *** details are provided at the footnote link and at https://***/view/fsa-net-official.

关键词： Attention face-swapping neural network face manipulation identity swap image translation

来源：评论

学校读者我要写书评

暂无评论

ResPocket: A Multi-Scale Feature Fusion Method for Improving Protein Binding Site Detection

ResPocket: A Multi-Scale Feature Fusion Method for Improving...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Lin, Xiaoli Yang, Wenli Chen, Yaoyu Liao, Xiongwei Wu, Zimo Zhang, Xiaolong Wuhan University of Science and Technology Hubei Key Laboratory of Intelligent Information Processing and Real-Time Industrial System School of Computer Science and Technology China

ISBN: (纸本)9798350386226

Accurate detection of protein binding sites is critical for facilitating drug design. Most existing models rely on features at a single scale, leading to the loss of crucial global or local structural information. Therefore, this paper proposes a novel 3D model (ResPocket), to fully capture the multi-scale features of proteins. First, Residual Block (ResB) based on U-Net is used to capture features from different scales, including global and local structural information. Then, an Enhanced Attention Module (EAM) is designed to encode semantic dependencies by effectively capturing global context information. In addition, ResPocket focuses on learning local information about protein pockets with Self-Guided Mask Block (SGMB), to increase the robustness of the overall model and reduce its dependence on external mask guidance. Experimental results show that ResPocket improves by an average of 4.89% on DCA Top-n, by an average of 1.48% and 2.25% on DCC and DVO metrics, respectively. © 2024 IEEE.

关键词： Binding sites

来源：评论

学校读者我要写书评

暂无评论

An Evolutionary Multitasking Algorithm for Efficient Multiobjective Recommendations

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第3期6卷 518-532页

作者： Tian, Ye Ji, Luke Hu, Yiwei Ma, Haiping Wu, Le Zhang, Xingyi Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Hefei230601 China Anhui University Institutes of Physical Science and Information Technology Hefei230601 China Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Hefei230029 China

Represented by evolutionary algorithms and swarm intelligence algorithms, nature-inspired metaheuristics have been successfully applied to recommender systems and amply demonstrated effectiveness, in particular, for multiobjective recommendation. Owing to the population-based search paradigm, these algorithms can produce a number of recommendation lists, making diverse tradeoffs between multiple metrics and meeting the requirements of accuracy, novelty, diversity, and other user preferences. However, these algorithms are criticized for the low efficiency of the optimization process, especially when the number of users is large. To address this issue, this article proposes an evolutionary multitasking-based recommendation method, where each task corresponds to a user and all the tasks are optimized simultaneously, thus highly improving the efficiency of recommendation. To enhance the convergence speed, all the users are divided into multiple populations according to the similarity between their preferences, where each population evolves with internal knowledge transfer between users, and all the populations evolve with external knowledge transfer between populations. Experimental results on various datasets verify that the proposed method can better balance between multiple metrics than classical and deep neural network-based recommendation methods and exhibits significantly higher efficiency than evolutionary multiobjective optimization-based recommendation methods. © 2024 IEEE. All rights reserved.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Fingerprint Recognition via Federated Adaptive Domain Generalization

引用

computers, Materials & Continua 2025年第3期82卷 5035-5055页

作者： Yonghang Yan Xin Xie Hengyi Ren Ying Cao Hongwei Chang Henan Key Laboratory of Big Data Analysis and Processing Computer and Information EngineeringHenan UniversityKaifeng475004China College of Information Science and Technology Nanjing Forestry UniversityNanjing210037China Henan Branch China Life Insurance Co.Ltd.Zhengzhou450000China

Fingerprint features,as unique and stable biometric identifiers,are crucial for identity ***,traditional centralized methods of processing these sensitive data linked to personal identity pose significant privacy risks,potentially leading to user data *** Learning allows multiple clients to collaboratively train and optimize models without sharing raw data,effectively addressing privacy and security ***,variations in fingerprint data due to factors such as region,ethnicity,sensor quality,and environmental conditions result in significant heterogeneity across *** heterogeneity adversely impacts the generalization ability of the global model,limiting its performance across diverse *** address these challenges,we propose an Adaptive Federated Fingerprint Recognition algorithm(AFFR)based on Federated *** algorithm incorporates a generalization adjustment mechanism that evaluates the generalization gap between the local models and the global model,adaptively adjusting aggregation weights to mitigate the impact of heterogeneity caused by differences in data quality and feature ***,a noise mechanism is embedded in client-side training to reduce the risk of fingerprint data leakage arising from weight disclosures during model *** conducted on three public datasets demonstrate that AFFR significantly enhances model accuracy while ensuring robust privacy protection,showcasing its strong application potential and competitiveness in heterogeneous data environments.

关键词： Fingerprint recognition privacy protection federated learning adaptive weight adjustment

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：