检索结果-内蒙古大学图书馆

Echo of Neighbors: Privacy Amplification for Personalized Private Federated Learning with Shuffle Model

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Yixuan Zhao, Suyun Xiong, Li Liu, Yuhan Chen, Hong Key Laboratory of Data Engineering and Knowledge Engineering Ministry of Education Renmin University of China China Engineering Research Center Ministry of Education on Database and BI China Information School Renmin University of China China Department of Computer Science Emory University United States

Federated Learning, as a popular paradigm for collaborative training, is vulnerable against privacy attacks. Different privacy levels regarding users’ attitudes need to be satisfied locally, while a strict privacy guarantee for the global model is also required centrally. Personalized Local Differential Privacy (PLDP) is suitable for preserving users’ varying local privacy, yet only provides a central privacy guarantee equivalent to the worst-case local privacy level. Thus, achieving strong central privacy as well as personalized local privacy with a utility-promising model is a challenging problem. In this work, a general framework (APES) is built up to strengthen model privacy under personalized local privacy by leveraging the privacy amplification effect of the shuffle model. To tighten the privacy bound, we quantify the heterogeneous contributions to the central privacy user by user. The contributions are characterized by the ability of generating "echos" from the perturbation of each user, which is carefully measured by proposed methods Neighbor Divergence and Clip-Laplace Mechanism. Furthermore, we propose a refined framework (S-APES) with the post-sparsification technique to reduce privacy loss in high-dimension scenarios. To the best of our knowledge, the impact of shuffling on personalized local privacy is considered for the first time. We provide a strong privacy amplification effect, and the bound is tighter than the baseline result based on existing methods for uniform local privacy. Experiments demonstrate that our frameworks ensure comparable or higher accuracy for the global model. © 2023, CC BY.

关键词： Learning systems

MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized Recommendation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liu, Kang Xue, Feng Guo, Dan Wu, Le Li, Shujie Hong, Richang Hefei University of Technology School of Computer Science and Information Engineering Key Laboratory of Knowledge Engineering with Big Data Intelligent Interconnected Systems Laboratory of Anhui Province 485 Danxia Road Anhui Province Hefei230601 China Hefei University of Technology School of Software Key Laboratory of Knowledge Engineering with Big Data Intelligent Interconnected Systems Laboratory of Anhui Province 485 Danxia Road Anhui Province Hefei230601 China

In most E-commerce platforms, whether the displayed items trigger the user's interest largely depends on their most eye-catching multimodal content. Consequently, increasing efforts focus on modeling multimodal user preference, and the pressing paradigm is to incorporate complete multimodal deep features of the items into the recommendation module. However, the existing studies ignore the mismatch problem between multimodal feature extraction (MFE) and user interest modeling (UIM). That is, MFE and UIM have different emphases. Specifically, MFE is migrated from and adapted to upstream tasks such as image classification. In addition, it is mainly a content-oriented and non-personalized process, while UIM, with its greater focus on understanding user interaction, is essentially a user-oriented and personalized process. Therefore, the direct incorporation of MFE into UIM for purely user-oriented tasks, tends to introduce a large number of preference-independent multimodal noise and contaminate the embedding representations in UIM. This paper aims at solving the mismatch problem between MFE and UIM, so as to generate high-quality embedding representations and better model multimodal user preferences. Towards this end, we develop a novel model, multimodal entity graph collaborative filtering, short for MEGCF. The UIM of the proposed model captures the semantic correlation between interactions and the features obtained from MFE, thus making a better match between MFE and UIM. More precisely, semantic-rich entities are first extracted from the multimodal data, since they are more relevant to user preferences than other multimodal information. These entities are then integrated into the user-item interaction graph. Afterwards, a symmetric linear Graph Convolution Network (GCN) module is constructed to perform message propagation over the graph, in order to capture both high-order semantic correlation and collaborative filtering signals. Finally, the sentiment information fr

关键词： Sentiment analysis

Visible Thermal Person Re-Identification Via Multi-Branch Modality Residual Complementary Learning

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Chen, Long Sun, Rui Yu, Yiheng Du, Yun Zhang, Xudong Key Laboratory of Knowledge Engineering with Big Data Ministry of Education School of Computer and Information Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei University of Technology Hefei230009 China The School of Computer and Information Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei University of Technology Hefei230009 China

Visible-thermal Person Re-identification (VT Re-ID) is a challenging task in all-weather surveillance system. Existing methods focus on extracting the modality-shared features, ignoring the discriminative inter-modality complementary features. To tackle this issue, we propose the multi-branch modality residual complementary learning method consisting of modality residual complementary learning (MRCL) module and multi-branch feature learning (MBFL) module. The MRCL module can be easily integrated into existing CNN and Transformer baselines and drive the network to focus on both intra-modality and inter-modality information simultaneously. On one hand, we adopt the basic two-stream network to obtain the intra-modality features, on the other hand, we feed the residual image acquired by cross-modality correlation saliency erasing operation to another two-stream network to capture the inter-modality complementary features. Moreover, we employ the MBFL module to capture local spatial features and local channel features and integrate them with global features to increase the discriminability and robustness of the ultimate representations for handling intra-modality variations. The extensive experiments on RegDB and SYSU-MM01 datasets demonstrate the superiority of our proposed method compared with state-of-the-art methods. © 2024, The Authors. All rights reserved.

关键词： Learning systems

Social Group Query Based on Multi-Fuzzy-Constrained Strong Simulation

学校读者我要写书评

暂无评论

ACM Transactions on knowledge Discovery from data 2021年第3期16卷 1–27页

作者： Guliu Liu Lei Li Guanfeng Liu Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education and Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education Intelligent Interconnected Systems Laboratory of Anhui Province (Hefei University of Technology) and Hefei University of Technology Macquarie University NSW Australia Key Laboratory of Knowledge Engineering with Big Data (Hefei University of Technology) Ministry of Education and Mininglamp Academy of Sciences Mininglamp Technology

Traditional social group analysis mostly uses interaction models, event models, or other social network analysis methods to identify and distinguish groups. This type of method can divide social participants into different groups based on their geographic location, social relationships, and/or related events. However, in some applications, it is necessary to make more specific restrictions on the members and the interactions between members of the group. Generally, Graph Pattern Matching (GPM) technique is used to solve this problem. However, the existing GPM methods rarely consider the rich contextual information of nodes and edges to measure the credibility between members. In this article, first, a social group query problem that needs to consider the trust between members of the group is proposed. Then, to solve this problem, a multi-fuzzy-constrained strong simulation matching model is proposed based on multi-constrained simulation, and a Strong Simulation GPM algorithm (NTSS) based on the exploration of pattern Node Topological ordered sequence is proposed. Aiming at the inefficiency of the NTSS algorithm when pattern graph with multiple nodes with zero in-degree and the problem of repeated calculation of matching edges shared by multiple matching subgraphs, two optimization strategies are proposed. Finally, we conduct verification experiments on the effectiveness and efficiency of the NTSS algorithm and the algorithms with the optimization strategies on four social network datasets in real applications. Experimental results show that the NTSS algorithm is significantly better than the existing multi-constrained GPM algorithm, and the NTSS_Inv_EdgC algorithm, which combines two optimization strategies, greatly improves the efficiency of the NTSS algorithm.

关键词： Graph pattern matching contextual social network multi-fuzzy-constrained strong simulation social group query

Causal-Inspired Multitask Learning for Video-Based Human Pose Estimation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Chen, Haipeng Wu, Sifan Wang, Zhigang Yin, Yifang Jiao, Yingying Lyu, Yingda Liu, Zhenguang College of Computer Science and Technology Jilin University China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University China College of Computer Science and Technology Zhejiang Gongshang University China A*STAR Singapore Public Computer Education and Research Center Jilin University China The State Key Laboratory of Blockchain and Data Security Zhejiang University China Institute of Blockchain and Data Security China

Video-based human pose estimation has long been a fundamental yet challenging problem in computer vision. Previous studies focus on spatio-temporal modeling through the enhancement of architecture design and optimization strategies. However, they overlook the causal relationships in the joints, leading to models that may be overly tailored and thus estimate poorly to challenging scenes. Therefore, adequate causal reasoning capability, coupled with good interpretability of model, are both indispensable and prerequisite for achieving reliable results. In this paper, we pioneer a causal perspective on pose estimation and introduce a causal-inspired multitask learning framework, consisting of two stages. In the first stage, we try to endow the model with causal spatio-temporal modeling ability by introducing two self-supervision auxiliary tasks. Specifically, these auxiliary tasks enable the network to infer challenging keypoints based on observed keypoint information, thereby imbuing causal reasoning capabilities into the model and making it robust to challenging scenes. In the second stage, we argue that not all feature tokens contribute equally to pose estimation. Prioritizing causal (keypoint-relevant) tokens is crucial to achieve reliable results, which could improve the interpretability of the model. To this end, we propose a Token Causal Importance Selection module to identify the causal tokens and non-causal tokens (e.g., background and objects). Additionally, non-causal tokens could provide potentially beneficial cues but may be redundant. We further introduce a non-causal tokens clustering module to merge the similar non-causal tokens. Extensive experiments show that our method outperforms state-of-the-art methods on three large-scale benchmark datasets. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

Chinese Idiom Paraphrasing

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Qiang, Jipeng Li, Yang Zhang, Chaowei Li, Yun Yuan, Yunhao Zhu, Yi Wu, Xindong School of Information Engineering Yangzhou University Jiangsu Yangzhou China Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Anhui Hefei China

Idioms, are a kind of idiomatic expression in Chinese, most of which consist of four Chinese characters. Due to the properties of non-compositionality and metaphorical meaning, Chinese Idioms are hard to be understood by children and non-native speakers. This study proposes a novel task, denoted as Chinese Idiom Paraphrasing (CIP). CIP aims to rephrase idioms-included sentences to non-idiomatic ones under the premise of preserving the original sentence’s meaning. Since the sentences without idioms are easier handled by Chinese NLP systems, CIP can be used to pre-process Chinese datasets, thereby facilitating and improving the performance of Chinese NLP tasks, e.g., machine translation system, Chinese idiom cloze, and Chinese idiom embeddings. In this study, CIP task is treated as a special paraphrase generation task. To circumvent difficulties in acquiring annotations, we first establish a large-scale CIP dataset based on human and machine collaboration, which consists of 115,530 sentence pairs. We further deploy three baselines and two novel CIP approaches to deal with CIP problems. The results show that the proposed methods have better performances than the baselines based on the established CIP dataset. © 2022, CC BY.

关键词： Natural language processing systems

Recurring Drift Detection and Model Selection-Based Ensemble Classification for data Streams with Unlabeled data

学校读者我要写书评

暂无评论

New Generation Computing 2021年第2期39卷 341-376页

作者： Li, Peipei Wu, Man He, Junhong Hu, Xuegang Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei 230009 China School of Computer Science and Information Engineering Hefei University of Technology Hefei 230009 China CloudWalk Technology Co. Ltd. Guangzhou China

data stream classification is widely popular in the field of network monitoring, sensor network and electronic commerce, etc. However, in the real-world applications, recurring concept drifting and label missing in data streams seriously aggravate the difficulty on the classification solutions. And this challenge has received little attention from the research community. Motivated by this, we propose a new ensemble classification approach based on the recurring concept drifting detection and model selection for data streams with unlabeled data. First, we build an ensemble model based on the classifiers and clusters. To improve the classification accuracy, we use the ensemble model to predict each data chunk and partition clusters according to the distribution of predicted class labels. Second, we adopt a new concept drifting detection method based on the divergence of concept distributions between adjoining data chunks to distinguish recurring concept drifts. All historical new concepts will be maintained. Meanwhile, we introduce the time-stamp-based weights for base models in the ensemble model. In the selection of the base model, we consider the time-stamp-based weight and the divergence between concept distributions simultaneously. Finally, extensive experiments conducted on four benchmark data sets show that our approach can quickly adapt to data streams with recurring concept drifts, and improve the classification accuracy compared to several state-of-the-art classification algorithms for data streams with concept drifts and unlabeled data. © 2021, Ohmsha, Ltd. and Springer Japan KK, part of Springer Nature.

关键词： data stream classification Ensemble learning Recurring concept drift Unlabeled data

Research on Crowdsourcing Truth Inference Method Based on Graph Embedding 12

学校读者我要写书评

暂无评论

Research on Crowdsourcing Truth Inference Method Based on Gr...

12th IEEE International Conference on Big knowledge, ICBK 2021

作者： Zhou, Liangzhu Zhuo, Xingrui Wu, Gongqing Zhang, Zan Bao, Xianyu Hefei University of Technology Key Laboratory of Knowledge Engineering With Big Data of Ministry of Education Hefei China School of Computer Science and Information Engineering Hefei University of Technology Hefei China Shenzhen Academy of Inspection and Quarantine Shenzhen China

ISBN: (纸本)9781665438582

Crowdsourcing is a cheap and popular method to solve problems that are difficult for computers to handle. Due to the differences in ability among workers on crowdsourcing platforms, existing research use aggregation strategies to deal with the labels of different workers to improve the utility of crowdsourcing data. However, most of these studies are based on probabilistic graphical models, which have problems such as difficulty in setting initial parameters. This paper proposes a novel crowdsourcing method Truth Inference based on Graph Embedding (TIGE) for single-choice questions, the method draws on the idea of graph autoencoder, constructs feature vectors for each crowdsourcing task, embeds the relationship between crowdsourcing tasks and workers in graphs, then uses graph neural networks to convert crowdsourcing problems into graph node prediction problems. The feature vectors are continuously optimized in the convolutional layer to obtain the final result. Compared with the six state-of-the-art algorithms on real-world datasets, our method has significant advantages in accuracy and F1-score. © 2021 IEEE.

关键词： Graph neural networks

GKG-LLM: A Unified Framework for Generalized knowledge Graph Construction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Jian Wei, Bifan Qi, Shihao Zhu, Haiping Liu, Jun Lin, Qika School of Computer Science and Technology Xi’an Jiaotong University Xi’an China School of Continuing Education Xi’an Jiaotong University Xi’an China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an China National University of Singapore Singapore

The construction of Generalized knowledge Graph (GKG), including knowledge graph, event knowledge graph and commonsense knowledge graph, is fundamental for various natural language processing tasks. Current studies typically construct these types of graph separately, overlooking holistic insights and potential unification that could be beneficial in computing resources and usage perspectives. However, a key challenge in developing a unified framework for GKG is obstacles arising from task-specific differences. In this study, we propose a unified framework for constructing generalized knowledge graphs to address this challenge. First, we collect data from 15 sub-tasks in 29 datasets across the three types of graphs, categorizing them into in-sample, counter-task, and out-of-distribution (OOD) data. Then, we propose a three-stage curriculum learning fine-tuning framework, by iteratively injecting knowledge from the three types of graphs into the Large Language Models. Extensive experiments show that our proposed model improves the construction of all three graph types across in-domain, OOD and counter-task data. Copyright © 2025, The Authors. All rights reserved.

关键词： knowledge graph