检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhao, Zongkai Xu, Guozeng Li, Xiuhua Wei, Kaiwen Zhong, Jiang School of Big Data & Software Engineering Chongqing University China College of Computer Science Chongqing University China

Locate-then-Edit Knowledge Editing (LEKE) is a key technique for updating large language models (LLMs) without full retraining. However, existing methods assume a single-user setting and become inefficient in real-world multi-client scenarios, where decentralized organizations (e.g., hospitals, financial institutions) independently update overlapping knowledge, leading to redundant mediator knowledge vector (MKV) computations and privacy concerns. To address these challenges, we introduce Federated Locate-then-Edit Knowledge Editing (FLEKE), a novel task that enables multiple clients to collaboratively perform LEKE while preserving privacy and reducing computational overhead. To achieve this, we propose FedEdit, a two-stage framework that optimizes MKV selection and reuse. In the first stage, clients locally apply LEKE and upload the computed MKVs. In the second stage, rather than relying solely on server-based MKV sharing, FLEKE allows clients retrieve relevant MKVs based on cosine similarity, enabling knowledge re-edit and minimizing redundant computations. Experimental results on two benchmark datasets demonstrate that FedEdit retains over 96% of the performance of non-federated LEKE while significantly outperforming a FedAvg-based baseline by approximately twofold. Besides, we find that MEMIT performs more consistently than PMET in the FLEKE task with our FedEdit framework. Our code is available at https://***/zongkaiz/FLEKE. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Benchmarking LLMs on the Semantic Overlap Summarization Task

arXiv

引用

arXiv 2024年

作者： Salvador, John Bansal, Naman Akter, Mousumi Sarkar, Souvika Das, Anupam Karmaker, Shubhra Kanti Big Data Intelligence Lab Department of Computer Science and Software Engineering College of Engineering Auburn University United States

Semantic Overlap Summarization (SOS) is a constrained multi-document summarization task, where the constraint is to capture the common/overlapping information between two alternative narratives. While recent advancements in Large Language Models (LLMs) have achieved superior performance in numerous summarization tasks, a benchmarking study of the SOS task using LLMs is yet to be performed. As LLMs’ responses are sensitive to slight variations in prompt design, a major challenge in conducting such a benchmarking study is to systematically explore a variety of prompts before drawing a reliable conclusion. Fortunately, very recently, the TELeR taxonomy has been proposed which can be used to design and explore various prompts for LLMs. Using this TELeR taxonomy and 15 popular LLMs, this paper comprehensively evaluates LLMs on the SOS Task, assessing their ability to summarize overlapping information from multiple alternative narratives. For evaluation, we report well-established metrics like ROUGE, BERTscore, and SEM-F1 on two different datasets of alternative narratives. We conclude the paper by analyzing the strengths and limitations of various LLMs in terms of their capabilities in capturing overlapping information1 © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Knowledge-Guided Cross-Topic Visual Question Generation 30

Knowledge-Guided Cross-Topic Visual Question Generation

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Liu, Hongfei Wang, Guohua Xie, Jiayuan Chen, Jiali Fang, Wenhao Cai, Yi School of Software Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China Department of Computing The Hong Kong Polytechnic University Hong Kong

ISBN: (纸本)9782493814104

Visual question generation (VQG) task aims to generate high-quality questions based on the input image. Current methods primarily focus on generating questions containing specified content utilizing answers or question types as constraints. However, these constraints make it challenging to control the topic of generated questions (e.g., conversation or test subject topics) for various applications. Thus, it is necessary to utilize topics as constraints to guide question generation. Considering that there are many topics and it is almost impossible for human annotations to cover them, we propose the cross-topic learning VQG (CTL-VQG) task, which aims to generate questions related to unseen topics in cross-topic scenarios. In this paper, we propose a knowledge-guided cross-topic visual question generation (KC-VQG) model to extract unseen topic-related information for question generation. Specifically, an image-topic feature extractor is introduced in our model to extract topic-related intuitive visual features;an image-topic knowledge extractor is used to extract and select the most appropriate topic-related implicit knowledge from large language models for generating questions. Extensive experiments show that our model outperforms baselines and can effectively generate unseen topic-related questions in cross-topic scenarios. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： data mining

来源：评论

学校读者我要写书评

暂无评论

Ranking Enhanced Fine-Grained Contrastive Learning for Recommendation

Ranking Enhanced Fine-Grained Contrastive Learning for Recom...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Yunhang Yao Min Gao Hongwei Zhou Zongwei Wang Zehua Zhao Qingyu Xiong School of Big Data and Software Engineering Chongqing University Chongqing China Faculty of Engineering The University of Sydney Sydney Australia

Contrastive learning (CL) has been widely used to improve recommendation performance, since its self-supervised signals can effectively alleviate the data sparsity issue in recommender systems. Nevertheless, most existing CL-based recommendation models construct negative sample pairs following the common practice, which may include many false negatives (i.e., highly similar nodes). Some studies detect potential false negatives through specific rules and either remove these samples from the negative samples or treat them all as positive samples. However, they lack a finer-grained consideration of the samples. To address this limitation, we propose a Ranking Enhanced Fine-grained Contrastive Learning method (REFCL). Specifically, we devise two sampling strategies to generate two sets of positive samples with different confidence levels. These well-ordered positive sample sets are then integrated into our novel contrastive loss, which allows for a more nuanced consideration of distinctions between samples and thereby enhancing the discriminative qualities of the learned user/item representations. Extensive experiments conducted on three real-world datasets demonstrate the effectiveness and generality of REFCL.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Quantum Dempster Rule of Combination

arXiv

引用

arXiv 2023年

作者： He, Huaping Xiao, Fuyuan School of Big Data and Software Engineering Chongqing University Chongqing401331 China

Dempster rule of combination (DRC) is widely used for uncertainty reasoning in intelligent information system, which is generalized to complex domain recently. However, as the increase of identification framework elements, the computational complexity of Dempster Rule of Combination increases exponentially. To address this issue, we propose a novel quantum Dempster rule of combination (QDRC) by means of Toffoli gate. The QDRC combination process is completely implemented using quantum circuits. Copyright © 2023, The Authors. All rights reserved.

关键词： Quantum theory

来源：评论

学校读者我要写书评

暂无评论

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need 38

Unlearnable 3D Point Clouds: Class-wise Transformation Is Al...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DSFM: Enhancing Functional Code Clone Detection with Deep Subtree Interactions

DSFM: Enhancing Functional Code Clone Detection with Deep Su...

引用

International Conference on software engineering (ICSE)

作者： Zhiwei Xu Shaohua Qiang Dinghong Song Min Zhou Hai Wan Xibin Zhao Ping Luo Hongyu Zhang KLISS BNRist School of Software Tsinghua University Beijing China School of Big Data and Software Engineering Chongqing University Chongqing China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Functional code clone detection is important for software maintenance. In recent years, deep learning techniques are introduced to improve the performance of functional code clone detectors. By representing each code snippet as a vector containing its program semantics, syntactically dissimilar functional clones are detected. However, existing deep learning-based approaches attach too much importance to code feature learning, hoping to project all recognizable knowledge of a code snippet into a single vector. We argue that these deep learning-based approaches can be enhanced by considering the characteristics of syntactic code clone detection, where we need to compare the contents of the source code (e.g., intersection of tokens, similar flow graphs, and similar subtrees) to obtain code clones. In this paper, we propose a novel deep learning-based approach named DSFM, which incorporates comparisons between code snippets for detecting functional code clones. Specifically, we improve the typical deep clone detectors with deep subtree interactions that compare every two subtrees extracted abstract syntax trees (ASTs) of two code snippets, thereby introducing more fine-grained semantic similarity. By conducting extensive experiments on three widely-used datasets, GCJ, OJClone, and bigCloneBench, we demonstrate the great potential of deep subtree interactions in code clone detection task. The proposed DSFM outperforms the state-of-the-art approaches, including two traditional approaches, two unsupervised and four supervised deep learning-based baselines.

关键词： software maintenance Codes Source coding Semantics Cloning Detectors Syntactics

来源：评论

学校读者我要写书评

暂无评论

A topic detection method based on KM-LSH Fusion algorithm and improved BTM model

引用

Soft Computing 2024年第19期28卷 11421-11438页

作者： Liu, Wenjun Guo, Huan Gan, Jiaxin Wang, Hai Wang, Hailan Zhang, Chao Peng, Qingcheng Sun, Yuyan Yu, Bao Hou, Mengshu Li, Bo Li, Xiaolei School of Computer and Software Engineering XiHua University Chengdu610039 China Chengdu611731 China Intelligent Policing Key Laboratory of Sichuan Province Sichuan Police College Luzhou646000 China School of Big Data and Artificial Intelligence Chengdu Technological University Chengdu611730 China Sichuan Provincial Engineering Research Center of Hydroelectric Energy Power Equipment Technology Chengdu610039 China

Topic detection is an information processing technology designed to help people deal with the growing problem of data information on the Internet. In the research literature, topic detection methods are used for topic classification through word embedding, supervised-based and unsupervised-based approaches. However, most methods for topic detection only address the problem of clustering and do not focus on the problem of topic detection accuracy reduction due to the cohesiveness of topics. Also, the sequence of biterm during topic detection can cause substantial deviations in the detected topic content. To solve the above problems, this paper proposes a topic detection method based on KM-LSH fusion algorithm and improved BTM model. KM-LSH fusion algorithm is a fusion algorithm that combines K-means clustering and LSH refinement clustering. The proposed method can solve the problem of cohesiveness of topic detection, and the improved BTM model can solve the influence of the sequence of biterm on topic detection. First, the text vector is constructed by processing the collected set of microblog texts using text preprocessing methods. Secondly, the KM-LSH fusion algorithm is used to calculate text similarity and perform topic clustering and refinement. Finally, the improved BTM model is used to model the texts, which is combined with the word position and the improved TF-IDF weight calculation algorithm to adjust the microblogging texts in clustering. The experiment results indicate that the proposed KM-LSH-IBTM method improves the evaluation indexes compared with the other three topic detection methods. In conclusion, the proposed KM-LSH-IBTM method promotes the processing capability of topic detection in terms of cohesiveness and the sequence of biterm. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

SynC: A Dense Retrieval Method based on Syntactical Contrastive Learning

SynC: A Dense Retrieval Method based on Syntactical Contrast...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Hongjin Tao Jun Zeng Yang Yu Ziwei Wang Xiaolin Hu School of Big Data and Software Chongqing University Chogqing China Innovation Center of Industrial Big-Data National Engineering Laboratory for Industrial Big-Data Application Technology Chogqing China

Recently, dense retrieval method has significantly outperformed sparse retrieval technology. It becomes a main-stream approach of relevant passage retrieving task. Dense retrieval tasks encode query and passage into dense representation space and apply contrastive learning to obtain more representative vectors, then retrieve the most similar passage by the inner product of the dense vectors. However, previous achievements rely on extremely large batch size, epoch and large-scaled pre-trained models, which results in tremendous computational resource consumption. Also, the expensive equipment prerequisite and low training efficiency constrain the development of dense retrieval community. Therefore, we present an alternative solution to improve training efficiency and quality by syntactical contrastive learning methods with specially designed masking strategy. To alleviate the computational consumption problem, this paper proposes query-based and passage-based masking strategies to obtain syntactical-isolated representations. Besides, instead of only considering query-to-passage similarity while conducting contrastive learning, we additionally consider query-to-query and passage-to-passage similarity when training the dual-encoder retriever. The experiments show that the proposed approach achieved competitive results in small batch size and epoch comparing to previous state-of-the-art dense retrieval methods, and also to strong baseline.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Development of Multi Objective Approach for Validation of PID Controller for Buck Converter 1

Development of Multi Objective Approach for Validation of PI...

引用

1st International Conference on Advances in Computer Science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Arun Kumar, K. Vegineni, Gopi Chand Suresh, C. Chowdari Marella, Bhagath Chandra Addanki, Sireesha Chimwal, Palak Big Data Architect India Sr.Software Engineer Enrollment and Eligibility Team India Electrical and Electronics Engineering School of Engineering and Technology Dhanalakshmi Srinivasan University Trichy Samayapuram621112 India Insights & Data Capgemini Department of Financial Services India System soft Technologies LLC India Bipin Tripathi Kumaon Institute of Technology Department of Electrical Engineering Almora Dwarahat India

ISBN: (纸本)9798331518578

Buck converters are a common converter of DCDC used for high energy conversion and power sources. These regulators are utilized in electronic gear to alter the result voltage because of changes in the heap current and information voltage. Therefore, in order to react to enquiries in real time, an efficient control system is required. In this work, an upgraded Sine Cosine Algorithm (ISCA) with proportional-integral-derivative (PID) controller is proposed for Mult objective optimization of a DC-DC buck converter. Through two distinct modifications, the limitations of the traditional SCA were therefore addressed, leading to the innovative use of nonlinear equations in conjunction with instrumental mechanisms to update the average location. By contrasting its response for frequency, response for increment, uncertainties of parametric, statistics of time-space indispensable error execution, objective capability, and resistance from aggravation with the previous methods-based PID for buck converters of DC-DC, the suggested ISCA-PID technique's robustness was evaluated. The results obtained later revealed that the suggested approach outperformed its algorithmic predecessors in terms of the DC-DC buck converter's remarkably improved transient responsiveness. © 2025 IEEE.

关键词： Buck converter

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：