检索结果-内蒙古大学图书馆

Model Recovery in Federated Unlearning With Restricted Server Data Resources

IEEE Internet of Things Journal 2025年第11期12卷 17920-17935页

作者： Zhang, Jianxin Zhao, Mengda Wang, Zhenwei Su, Weijian Wang, Pengfei Dalian Minzu University School of Computer Science and Engineering Dalian116600 China Dalian University of Technology School of Computer Science and Technology Dalian116024 China Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Dalian116024 China

Recent model recovery methods in federated unlearning (FUL) either rely on additional communication with the remaining clients or require large amounts of high-quality data from the server for training, overlooking scenarios with limited data resources. Currently, Contrastive Language-Image Pretraining (CLIP) has demonstrated remarkable performance across a wide range of tasks, particularly excelling in few-shot learning scenarios. In this paper, inspired by CLIP, we explore the scenario of few-shot knowledge distillation and propose CLIP-Guided Few-shot Knowledge Distillation (CGKD) for Model Recovery in FUL. CGKD mainly consists of three components: 1) The unlearning module constructs the unlearning model by erasing all historical contributions of the target client, and this model is treated as the student model;2) Fine-tuning the pre-trained CLIP model using few-shot data from the server side to obtain a more robust teacher model (CLIP*);and 3) Model recovery is achieved through knowledge distillation, leveraging the rich visual and semantic knowledge of CLIP∗ to enhance the student model's understanding of image semantic context, thereby improving the performance of the unlearning model. Extensive experimental results demonstrate that CGKD outperforms the compared FUL method in recovery performance across four standard datasets, validating the effectiveness of our approach. © 2014 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

HALO: Half Life-Based Outdated Fact Filtering in Temporal Knowledge Graphs 25

HALO: Half Life-Based Outdated Fact Filtering in Temporal Kn...

引用

Companion Proceedings of the ACM on Web Conference 2025

作者： Feng Ding Tingting Wang Yupeng Gao Shuo Yu Jing Ren Feng Xia Dalian University of Technology Dalian China Dalian University of Technology Dalian China and Key Laboratory of Social Computing and Cognitive Intelligence Ministry of Education Dalian China RMIT University Melbourne Australia

ISBN: (纸本)9798400713316

Outdated facts in temporal knowledge graphs (TKGs) result from exceeding the expiration date of facts, which negatively impact reasoning performance on TKGs. However, existing reasoning methods primarily focus on positive importance of historical facts, neglecting adverse effects of outdated facts. Besides, training on these outdated facts yields extra computational cost. To address these challenges, we propose an outdated fact filtering framework named HALO, which quantifies the temporal validity of historical facts by exploring the half-life theory to filter outdated facts in TKGs. HALO consists of three modules: the temporal fact attention module, the dynamic relation-aware encoder module, and the outdated fact filtering module. Firstly, the temporal fact attention module captures the evolution of historical facts over time to identify relevant facts. Secondly, the dynamic relation-aware encoder module is designed for efficiently predicting the half life of each fact. Finally, we construct a time decay function based on the half-life theory to quantify the temporal validity of facts and filter outdated facts. Experimental results show that HALO outperforms the state-of-the-art TKG reasoning methods on three public datasets, demonstrating its effectiveness in detecting and filtering outdated facts.

关键词： graph learning

来源：评论

学校读者我要写书评

暂无评论

Speed up Federated Unlearning With Temporary Local Models

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable computing 2025年

作者： Ameen, Muhammad Wang, Pengfei Su, Weijian Wei, Xiaopeng Zhang, Qiang Dalian University of Technology School of Computer Science and Technology Dalian116024 China Ministry of Education Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Dalian116024 China Yidatec Co. Ltd Dalian116085 China

Federated unlearning (FUL) is a solution aimed at addressing the problem of removing data contributions from trained federated learning (FL) models. Existing FUL methods only focus on iterative unlearning of clients' contributions and fail to perform unlearning in scenarios where multiple clients request to remove their data at a time. Additionally, FUL still needs to address issues, including convergence speed, maintaining the global model's performance, and parallel unlearning to expedite the unlearning process. To fill this gap, we introduce Federated Clients Forgetting (FedCF), a fast and accurate FUL method that can eliminate single client contributions similar to existing methods, eliminate multiple clients' contributions on the global model parallelly, ensure the performance of the unlearned global model, and reduce the unlearning time. The key idea is to construct a temporary model by extracting knowledge from the remaining clients' updates and adding it to the corresponding parameters of the initial global model and then leverage a temporary model to reconstruct the unlearned global model. Extensive experiments on three benchmark datasets, FedCF demonstrates its efficiency and effectiveness for single client contribution unlearning, achieving an average time efficiency of 8.3x, 6.5x, and 4.1x over existing methods FedRetrain, FedEraser, and FUL with knowledge distillation, respectively. Additionally, FedCF showcases the time efficiency and performance guarantee after unlearning the contributions of multiple clients in parallel. © 2016 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Survey on Federated Long-Tailed Learning

引用

Jisuanji Xuebao/Chinese Journal of Computers 2025年第4期48卷 779-807页

作者： Zhou, Yi-Zhi Wang, Jun-Xiao Xie, Xin Wang, Peng-Fei Jia, Xi-Bei Qi, Heng Qin, Yu-Chen School of Computer Science and Technology Dalian University of Technology Liaoning Dalian116024 China Key Laboratory of Social Computing and Cognitive Intelligence（Dalian University of Technology） Ministry of Education Liaoning Dalian116024 China School of Cyberspace Security Guangzhou University Guangzhou510006 China College of Intelligence and Computing Tianjin University Tianjin300072 China Shenzhen Audaque Data Technology Co. Ltd. Guangdong Shenzhen518057 China

Federated learning, a machine learning method built on distributed training, effectively navigates the problem of data privacy leakage among users that joint modeling introduces. This effectiveness has led to the widespread use of federated learning-based methods in many fields. Yet, in practical applications of federated learning, the combined existence of statistical heterogeneity and long-tailed distribution presents a considerable hurdle, dramatically affecting the model's performance. Consequently, a principal objective of contemporary research is the mastery of the long-tailed challenge in a manner that maintains data privacy. Most of the existing researches on long-tailed learning and statistical heterogeneity are not viable in a federated learning setting. Furthermore, there is a paucity of detailed and comprehensive overviews of the cutting-edge methods in this area. This paper presents a comprehensive review of the research accomplishments in federated long-tailed learning. To begin with, the architecture of federated learning is briefly explained, followed by an introduction to core concepts and definitions concerning statistical heterogeneity, long-tailed learning, and federated long-tailed learning. The main challenges of federated long-tailed learning are mentioned as well, including differences in data distribution, imbalance in categories, and inconsistent updates between clients during training. Basing on different optimization methods, the algorithms for federated long-tailed learning are classified into two major categories: Model Component Improvement and Algorithm-based Optimization. Model Component Improvement methods include virtual feature re-training, classifier calibration, and personalized federal learning. Algorithm-based Optimization methods include cost-sensitive learning, knowledge distillation, client selection, and balance enhancement. Each algorithm's implementation details, as well as its advantages and disadvantages, are thoroughl

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Federated Unlearning with Fast Recovery

引用

IEEE Transactions on Mobile computing 2025年

作者： Zhou, Changjun Pan, Chenglin Li, Minglu Wang, Pengfei Zhejiang Normal University School of Computer Science and Technology Jinhua321000 China Dalian University of Technology School of Computer Science and Technology Dalian116024 China Dalian University of Technology Key Laboratory of Social Computing and Cognitive Intelligence Ministry of Education Dalian116024 China Yidatec Co. Ltd Dalian116085 China

Recent federated unlearning studies mainly focus on removing the target client's contributions from the global model permanently. However, the requirement for accommodating temporary user exits or additions in federated learning has been neglected. In this paper, we propose a novel recoverable federated unlearning scheme, named RFUL, which allows users to remove or add their local model to the global one at any time easily and quickly. It mainly consists of two main components, i.e., knowledge unlearning and knowledge recovery. In knowledge unlearning, the target contributions can be eliminated by training with mislabeled target data, while preserving the non-target contributions through distillation using the original model. In knowledge recovery, the forgotten contributions can be restored by training the target data using classification loss, while the non-target contributions are maintained through feature distillation and parameter freezing on the classifier. Both knowledge unlearning and recovery processes only require the participation of target data, guaranteeing the algorithm's practicality in federated learning systems. Extensive experiments demonstrate the significant efficacy of RFUL. For knowledge unlearning, RFUL matches state-of-the-art methods using only target data, achieving a runtime speedup of 3.3 to 8.7 times compared to retraining across various datasets. For knowledge recovery, RFUL exceeds state-of-the-art incremental learning methods by 5.02% to 29.97% in accuracy and achieves a runtime speedup of 1.8 to 4.4 times compared to retraining on different datasets. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Prompt Learning Framework with Large Language Model Augmentation for Few-shot Multi-label Intent Detection

A Prompt Learning Framework with Large Language Model Augmen...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhuang, Ning Wei, Xiao Li, Junlei Wang, Xiaobao Wang, Chenyang Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Shenzhen China Co. Ltd. Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9798350368741

Intent detection (ID) is essential in spoken language understanding, especially in multi-label settings where intent labels are interdependent and diverse. Existing methods like SE-MLP and QA-FT struggle in few-shot settings, due to limited data availability and efficiency concerns. To address this, we introduce a Prompt Learning framework with large language Model Augmentation (PLMA) for few-shot multi-label ID. In this study, we make three contributions. First, PLMA integrates large language models (LLMs) with small language models (SLMs), using LLMs to enhance SLMs, with prompt learning as the core framework. Second, it leverages LLMs to improve the model's understanding of both queries and labels by intent spans extraction and answer space expansion. Third, PLMA refines the QA-FT. A novel QA format template is designed to allow single-step training and inference for each input, improving efficiency. Experiments on NLU++ show that PLMA significantly outperforms other baselines in both in-domain and cross-domain settings, demonstrating its effectiveness in combining the strengths of both small and large models. © 2025 IEEE.

关键词： large language model multi-label intent detection prompt learning spoken language understanding

来源：评论

学校读者我要写书评

暂无评论

Class Semantic Prompts Enhanced Prototypical Fusion Method for Few-shot Named Entity Recognition

Class Semantic Prompts Enhanced Prototypical Fusion Method f...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Yu, Mei Tao, Yuang Zhao, Mankun Xu, Tianyi Meng, Zechen Zhang, Wenbin Yu, Jian School of Future Technology Tianjin University Tianjin300350 China College of Intelligence and Computing Tianjin University Tianjin300350 China Tianjin Key Laboratory of Cognitive Computing and Application Tianjin300350 China Tianjin Key Laboratory of Advanced Networking Tianjin300350 China Information and Network Center Tianjin University Tianjin300350 China

ISBN: (纸本)9798350368741

Few-shot named entity recognition is to identify named entities in scenarios where labeled data is scarce. Existing prototype building methods ignore the use of class semantic and it is difficult to obtain accurate prototype representations only by relying on few support samples. In this paper, we propose a class semantic prompts enhanced prototypical fusion method (CSFP). Specifically, we design a class-semantic prototype that adapts to current task through prompts. In order to add intra-class similarity to the existing prototype and obtain a more accurate and stable prototype representation, we consider the samples distribution and fuse class-semantic prototype with existing prototype through a weighted strategy. Experimental results on two few-shot NER benchmarks show that our method outperforms previous SOTA methods. The analysis further verifies the effectiveness of our method. © 2025 IEEE.

关键词： class semantic few-shot NER prompt learning prototype

来源：评论

学校读者我要写书评

暂无评论

Long-range Brain Graph Transformer

arXiv

引用

arXiv 2025年

作者： Yu, Shuo Jin, Shan Li, Ming Sarwar, Tabinda Xia, Feng School of Computer Science and Technology Dalian University of Technology China Key Laboratory of Social Computing and Cognitive Intelligence Dalian University of Technology Ministry of Education China School of Software Dalian University of Technology China Zhejiang Institute of Optoelectronics China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University China School of Computing Technologies RMIT University Australia

Understanding communication and information processing among brain regions of interest (ROIs) is highly dependent on long-range connectivity, which plays a crucial role in facilitating diverse functional neural integration across the entire brain. However, previous studies generally focused on the short-range dependencies within brain networks while neglecting the long-range dependencies, limiting an integrated understanding of brain-wide communication. To address this limitation, we propose Adaptive Long-range aware TransformER (ALTER), a brain graph transformer to capture long-range dependencies between brain ROIs utilizing biased random walk. Specifically, we present a novel long-range aware strategy to explicitly capture long-range dependencies between brain ROIs. By guiding the walker towards the next hop with higher correlation value, our strategy simulates the real-world brain-wide communication. Furthermore, by employing the transformer framework, ALERT adaptively integrates both short- and long-range dependencies between brain ROIs, enabling an integrated understanding of multilevel communication across the entire brain. Extensive experiments on ABIDE and ADNI datasets demonstrate that ALTER consistently outperforms generalized state-of-the-art graph learning methods (including SAN, Graphormer, GraphTrans, and LRGNN) and other graph learning based brain network analysis methods (including FBNETGEN, BrainNetGNN, BrainGNN, and BrainNETTF) in neurological disease diagnosis. Cases of long-range dependencies are also presented to further illustrate the effectiveness of ALTER. The implementation is available at https://***/yushuowiki/ALTER. Copyright © 2025, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

ApriDS: An evidence linkage network construction model for judgment documents

引用

Journal of King Saud university - Computer and Information Sciences 2025年第1期37卷 1-13页

作者： Zhou, Yulin Qin, Yongbin Lin, Chuan Text Computing & Cognitive Intelligence Engineering Research Center of National Education Ministry Guizhou University Guiyang 550025 China State Key Laboratory of Public Big Data Guizhou University Guiyang 550025 China College of Computer Science & Technology Guizhou University Guiyang 550025 China

Evidence serves as the basis for determining facts in the judicial trial process, and exploring the correlation between evidence has become an essential task. However, there is uncertainty and unreliability of evidence. In this paper, we propose an ApriDS model that can mine correlations between evidence and construct evidence linkage networks. Specifically, we use the association rule algorithm to mining for the correlations between evidence in order to initially construct an evidence linkage network. Moreover, we also combine the imprecise reasoning theory to alleviate unreliability among evidence. Finally, combining the above effectively mitigates uncertainty and unreliability in the evidence linkage network. We conduct extensive experiments and present analyses on five case datasets, including marriages, thefts, homicides, contract disputes and unlawful detention. Compared to the baseline model, our method’s accuracy improves by 12.75%, 14.16%, 14.80%, 21.64% and 26.15% on the five datasets, respectively. © The Author(s) 2025.

关键词： Apriori algorithm D-S evidence theory Evidence linkage network Judgment document

来源：评论

学校读者我要写书评

暂无评论

Augmenting Short Enrollment Speech via Synthesis for Target Speaker Extraction

Augmenting Short Enrollment Speech via Synthesis for Target ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Huang, Zikang Lin, Jingru Ge, Meng Jiang, Yu Wang, Xiaobao Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Shenzhen China Department of Electrical and Computer and Engineering National University of Singapore Singapore Co. Ltd. Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9798350368741

A high-quality enrollment speech is crucial to target speaker extraction (TSE), since it provides essential cues for identifying the target speaker in the mixture. However, real applications usually only permit a short enrollment speech, e.g. a wakeup word for a mobile device, that provides limited cues. To address this issue, we propose an enrollment augmentation strategy that allows us to enrich the limited enrollment speech with massive text data through speech synthesis. By doing so, the extended enrollment speech contains enhanced speaker timbre and phonetic content which leads to better extraction quality. Furthermore, we propose a training data augmentation strategy to improve the model's robustness and generalization in short enrollment speech scenarios. Experiments on Libri2Mix demonstrate that our proposed strategies bring a significant improvement in extreme scenarios where only 0.5s and 1-word enrollment speech is provided. We also release our code at https://***/HuangZikang-TJU/Aug4TSE. © 2025 IEEE.

关键词： continue speaking data augmentation short enrollment speech synthesis Target speaker extraction

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：