IEEE Transactions on Knowledge and Data Engineering最新文献_第5页

iBACon: imBalance-Aware Contrastive Learning for Time Series Forecasting iBACon：时间序列预测的非平衡感知对比学习

IF 10.4 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-07-16 DOI: 10.1109/TKDE.2025.3589693

Jing Zhang;Qun Dai;Rui Ye

{"title":"iBACon: imBalance-Aware Contrastive Learning for Time Series Forecasting","authors":"Jing Zhang;Qun Dai;Rui Ye","doi":"10.1109/TKDE.2025.3589693","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3589693","url":null,"abstract":"Time series forecasting (TSF) has gained significant attention as a widely explored research area in diverse applications. Existing methods, which focus on improvements in the most common scenarios, focus little on performance in rare cases. Despite their scarce occurrences in the data, these rare samples are more challenging and easily overlooked by models, significantly contributing to the total loss. In this paper, we propose a novel approach (dubbed iBACon) that overcomes this limitation by employing imbalance-aware contrastive learning and trend-seasonal decomposition architecture, specifically designed to solve TSF. To this end, we first introduce the Input-Output Difference (IOD) metric as a pseudo-label and reveal the data imbalance phenomenon in TSF. This label continuity inherently provides a meaningful distance between targets, implying a similarity between nearby targets in both label and feature spaces. Based on this similarity, the proposed imbalance-aware contrastive loss aims to reshape feature embeddings to facilitate knowledge dissemination among challenging samples and learn specific predictive features. Finally, when combined with our trend-seasonal decomposition network, iBACon significantly improves TSF accuracy. Experiments show that iBACon enhances overall average accuracy and substantially improves the 1-3% most challenging samples.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 10","pages":"5967-5982"},"PeriodicalIF":10.4,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145050853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

AuCoGNN: Enhancing Graph Fairness Learning Under Distribution Shifts With Automated Graph Generation 基于自动图生成的分布变化下的图公平性学习

IF 10.4 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-07-14 DOI: 10.1109/TKDE.2025.3586276

Xiao Wang;Yibo Li;Yujie Xing;Shaohua Fan;Chuan Shi

{"title":"AuCoGNN: Enhancing Graph Fairness Learning Under Distribution Shifts With Automated Graph Generation","authors":"Xiao Wang;Yibo Li;Yujie Xing;Shaohua Fan;Chuan Shi","doi":"10.1109/TKDE.2025.3586276","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3586276","url":null,"abstract":"Graph neural networks (GNNs) have shown strong performance on graph-structured data but may inherit bias from training data, leading to discriminatory predictions based on sensitive attributes like gender and race. Existing fairness methods assume that training and testing data share the same distribution, but how fairness is affected under distribution shifts remains largely unexplored. To address this, we first identify theoretical factors that cause bias in graphs and explore how fairness is influenced by distribution shifts, particularly focusing on representation distances between groups in training and testing graphs. Based on this, we propose FatraGNN, which uses a graph generator to create biased graphs from different distributions and an alignment module to reduce representation distances for specific groups. This improves fairness and classification performance on unseen graphs. However, FatraGNN has limitations in generating realistic graphs and addressing group differentiation. To overcome these, we introduce AuCoGNN, which includes an automated graph generation module and a contrastive alignment mechanism. This ensures better fairness by maximizing the representation distance between the same certain groups while minimizing the representation distance between different groups. Experiments on real-world and semi-synthetic datasets demonstrate the effectiveness of both models in improving fairness and accuracy.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 10","pages":"5781-5794"},"PeriodicalIF":10.4,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145051021","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

RConE: Rough Cone Embedding for Multi-Hop Logical Query Answering on Multi-Modal Knowledge Graphs RConE：基于多模态知识图的多跳逻辑查询应答的粗糙锥嵌入

IF 10.4 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-06-30 DOI: 10.1109/TKDE.2025.3584054

Mayank Kharbanda;Rajiv Ratn Shah;Raghava Mutharaju

{"title":"RConE: Rough Cone Embedding for Multi-Hop Logical Query Answering on Multi-Modal Knowledge Graphs","authors":"Mayank Kharbanda;Rajiv Ratn Shah;Raghava Mutharaju","doi":"10.1109/TKDE.2025.3584054","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3584054","url":null,"abstract":"Multi-hop query answering over a Knowledge Graph (KG) involves traversing one or more hops from the start node to answer a query. Path-based and logic-based methods are state-of-the-art for multi-hop question answering. The former is used in link prediction tasks. The latter is for answering complex logical queries. The logical multi-hop querying technique embeds the KG and queries in the same embedding space. The existing work incorporates First Order Logic (FOL) operators, such as conjunction (<inline-formula><tex-math>$wedge$</tex-math></inline-formula>), disjunction (<inline-formula><tex-math>$vee$</tex-math></inline-formula>), and negation (<inline-formula><tex-math>$lnot$</tex-math></inline-formula>), in queries. Though current models have most of the building blocks to execute the FOL queries, they cannot use the dense information of multi-modal entities in the case of Multi-Modal Knowledge Graphs (MMKGs). We propose RConE, an embedding method to capture the multi-modal information needed to answer a query. The model first shortlists candidate (multi-modal) entities containing the answer. It then finds the solution (sub-entities) within those entities. Several existing works tackle path-based question-answering in MMKGs. However, to our knowledge, we are the first to introduce logical constructs in querying MMKGs and to answer queries that involve sub-entities of multi-modal entities as the answer. Extensive evaluation of four publicly available MMKGs indicates that RConE outperforms the current state-of-the-art.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 10","pages":"6135-6146"},"PeriodicalIF":10.4,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145036942","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analyzing and Enhancing LDP Perturbation Mechanisms in Federated Learning 联邦学习中LDP摄动机制的分析与改进

IF 10.4 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-06-18 DOI: 10.1109/TKDE.2025.3580796

Jiawei Duan;Qingqing Ye;Haibo Hu;Xinyue Sun

{"title":"Analyzing and Enhancing LDP Perturbation Mechanisms in Federated Learning","authors":"Jiawei Duan;Qingqing Ye;Haibo Hu;Xinyue Sun","doi":"10.1109/TKDE.2025.3580796","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3580796","url":null,"abstract":"Recently, federated learning (FL) has become a prevalent algorithm to harvest data while preserving privacy. However, private information can still be compromised by local parameters during transmissions between local parties and the central server. To address this problem, local differential privacy (LDP) has been adopted. Known as federated LDP-SGD, each local device only sends perturbed parameters to the central server. However, due to the low model efficiency caused by overwhelming LDP noise, only a relaxed LDP privacy scheme, namely Gaussian mechanism, is explored in the federated LDP-SGD literature. The objective of this paper is to enable other LDP mechanisms (e.g., Laplace, Piecewise, Square Wave and Gaussian) in federated learning by enhancing their model efficiency. We first propose an analytical framework that generalizes federated LDP-SGD and derives its model efficiency. Serving as a benchmark, this framework can compare performances of different LDP mechanisms in federated learning. Based on this framework, we identify a new perspective to generally optimize federated LDP-SGD, namely, the vectorized perturbation strategy <italic>LDPVec</i>. By only perturbing the direction of a gradient, <italic>LDPVec</i> better preserves the descending direction of the gradient, which consequently leads to comprehensive efficiency improvements in terms of various LDP mechanisms.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 10","pages":"5767-5780"},"PeriodicalIF":10.4,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145051020","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DFL-Net: Disentangled Feature Learning Network for Multi-View Clustering DFL-Net：用于多视图聚类的解纠缠特征学习网络

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-06-12 DOI: 10.1109/TKDE.2025.3574150

Zhe Chen;Xiao-Jun Wu;Tianyang Xu;Josef Kittler

{"title":"DFL-Net: Disentangled Feature Learning Network for Multi-View Clustering","authors":"Zhe Chen;Xiao-Jun Wu;Tianyang Xu;Josef Kittler","doi":"10.1109/TKDE.2025.3574150","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3574150","url":null,"abstract":"Multi-view clustering aims at partitioning data into their underlying categories by mining shared and complementary information conveyed by different views. Although the integration of deep learning and disentanglement learning has markedly improved clustering performance, our analysis reveals two fundamental limitations in existing approaches: inadequate separation between view-shared and view-exclusive features; and the negative effects of clustering-irrelevant information on feature decoupling. To tackle these issues, we present a novel Disentangled Feature Learning Network (DFL-Net), which utilizes a progressive learning framework to systematically disentangle features. DFL-Net initially establishes view-shared representations through semantic disparity minimization, followed by the construction of orthogonal feature subspaces using cross-view and intra-view independence constraints to isolate view-specific features. Subsequently, DFL-Net enforces clustering consistency across views to adaptively eliminate irrelevant information, thus enhancing the overall effectiveness of disentanglement learning. The framework introduces two significant innovations: a comprehensive feature independence criterion that concurrently reduces intra-view and cross-view feature dependencies, and an irrelevance filtering mechanism that ensures cross-view clustering consistency. Extensive experiments on benchmark datasets demonstrate the superior performance of DFL-Net compared to state-of-the-art methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 8","pages":"4537-4547"},"PeriodicalIF":8.9,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144572954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Gaussian Process Latent Variable Modeling for Few-Shot Time Series Forecasting 少量时间序列预测的高斯过程隐变量建模

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-06-02 DOI: 10.1109/TKDE.2025.3573673

Yunyao Cheng;Chenjuan Guo;Kaixuan Chen;Kai Zhao;Bin Yang;Jiandong Xie;Christian S. Jensen;Feiteng Huang;Kai Zheng

{"title":"Gaussian Process Latent Variable Modeling for Few-Shot Time Series Forecasting","authors":"Yunyao Cheng;Chenjuan Guo;Kaixuan Chen;Kai Zhao;Bin Yang;Jiandong Xie;Christian S. Jensen;Feiteng Huang;Kai Zheng","doi":"10.1109/TKDE.2025.3573673","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3573673","url":null,"abstract":"Accurate time series forecasting is crucial for optimizing resource allocation, industrial production, and urban management, particularly with the growth of cyber-physical and IoT systems. However, limited training sample availability in fields like physics and biology poses significant challenges. Existing models struggle to capture long-term dependencies and to model diverse meta-knowledge explicitly in few-shot scenarios. To address these issues, we propose MetaGP, a meta-learning-based Gaussian process latent variable model that uses a Gaussian process kernel function to capture long-term dependencies and to maintain strong correlations in time series. We also introduce Kernel Association Search (KAS) as a novel meta-learning component to explicitly model meta-knowledge, thereby enhancing both interpretability and prediction accuracy. We study MetaGP on simulated and real-world few-shot datasets, showing that it is capable of state-of-the-art prediction accuracy. We also find that MetaGP can capture long-term dependencies and can model meta-knowledge, thereby providing valuable insights into complex time series patterns.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 8","pages":"4604-4619"},"PeriodicalIF":8.9,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144581694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

DASCE: Long-Tailed Data Augmentation Based Sparse Class-Correlation Exploitation 基于稀疏类相关开发的长尾数据增强

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-06-02 DOI: 10.1109/TKDE.2025.3573899

Mengnan Qi;Shasha Mao;Yimeng Zhang;Jing Gu;Shuiping Gou;Licheng Jiao;Yuming Zhang

{"title":"DASCE: Long-Tailed Data Augmentation Based Sparse Class-Correlation Exploitation","authors":"Mengnan Qi;Shasha Mao;Yimeng Zhang;Jing Gu;Shuiping Gou;Licheng Jiao;Yuming Zhang","doi":"10.1109/TKDE.2025.3573899","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3573899","url":null,"abstract":"The long-tailed data distribution frequently occurs in the real-world scenarios, whereas deep learning is not effective enough for such distribution. In order to improve the effectiveness for the long-tailed data, data augmentation is widely used to balance the distribution of classes by generating new samples. However, most existing studies are designed from the perspective of the class-independence assumption by default, ignoring the effect of interrelation among classes for data augmentation, which causes that some generated samples may be unrepresentative and useless for balancing the class-distribution. Inspired by this, we propose a new data augmentation method based the sparse class-correlation exploitation in this paper, which can generate more representative samples by utilizing the class-correlation, to effectively balance the class-distribution for the long-tailed data. In the proposed method, a sparse class-correlation exploration module is first proposed to explore the potential correlations among multiple classes for boosting the classification performance. Based on the class-correlations, the pivotal seed-samples are generated by maximizing the sparse representation of challenging samples. Meanwhile, an ambiguity-filtered translation module is designed to generate more representative new samples for the target classes based the obtained seed-samples by enhancing the class-consistency and suppressing the deviation from the target classes. In addition, we introduce the self-supervised feature and fuse it with the discriminative feature to explore more accurate class-correlations. Experimental results illustrate that the proposed method obtains better performance only with a small number of generated samples than the state-of-the-art methods.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 8","pages":"4497-4511"},"PeriodicalIF":8.9,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144573014","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Camouflaged Variational Graph AutoEncoder Against Attribute Inference Attacks for Cross-Domain Recommendation 针对跨域推荐属性推理攻击的伪装变分图自编码器

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-04-30 DOI: 10.1109/TKDE.2025.3565793

Yudi Xiong;Yongxin Guo;Weike Pan;Qiang Yang;Zhong Ming;Xiaojin Zhang;Han Yu;Tao Lin;Xiaoying Tang

{"title":"Camouflaged Variational Graph AutoEncoder Against Attribute Inference Attacks for Cross-Domain Recommendation","authors":"Yudi Xiong;Yongxin Guo;Weike Pan;Qiang Yang;Zhong Ming;Xiaojin Zhang;Han Yu;Tao Lin;Xiaoying Tang","doi":"10.1109/TKDE.2025.3565793","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3565793","url":null,"abstract":"Cross-domain recommendation (CDR) aims to alleviate the data sparsity problem by leveraging the benefits of modeling two domains. However, existing research often focuses on the recommendation performance while ignores the privacy leakage issue. We find that an attacker can infer user attribute information from the knowledge (e.g., user preferences) transferred between the source and target domains. For example, in our experiments, the average inference accuracies of attack models on gender and age attributes are 0.8323 and 0.3897. The best-performing attack model achieves accuracies of 0.8847 and 0.4634, exceeding a random inference by 25.10% and 64.04%. We can see that the leakage of user attribute information may significantly exceed what would be expected from random inference. In this paper, we propose a novel recommendation framework named CVGAE (short for camouflaged variational graph autoencoder), which effectively models user behaviors and mitigates the risk of user attribute information leakage at the same time. Specifically, our CVGAE combines the strengths of VAEs in capturing latent features and variability with the ability of GCNs in exploiting high-order relational information. Moreover, to ensure against attribute inference attacks without sacrificing the recommendation performance, we design a user attribute protection module that fuses user attribute-camouflaged information with knowledge transfer during cross-domain processes. We then conduct extensive experiments on three real-world datasets, and find our CVGAE is able to achieve strong privacy protection while making little sacrifices in recommendation accuracy.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 7","pages":"3916-3932"},"PeriodicalIF":8.9,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144219687","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Charging-Aware Task Assignment for Urban Logistics With Electric Vehicles 基于充电感知的电动汽车城市物流任务分配

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-04-30 DOI: 10.1109/TKDE.2025.3565858

Yafei Li;Yuke Pan;Guanglei Zhu;Shuo He;Mingliang Xu;Jianliang Xu

{"title":"Charging-Aware Task Assignment for Urban Logistics With Electric Vehicles","authors":"Yafei Li;Yuke Pan;Guanglei Zhu;Shuo He;Mingliang Xu;Jianliang Xu","doi":"10.1109/TKDE.2025.3565858","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3565858","url":null,"abstract":"The rapid growth of e-commerce has intensified the demand for efficient urban logistics. Electric Vehicles (EVs), with their eco-friendly and high-efficiency features, have emerged as a promising solution for improving urban logistics efficiency. However, due to their limited battery capacity, EVs often require recharging during operations, and improper charging decisions may lead to delivery delays, resulting in a loss of platform revenue. In this paper, we explore a novel EV Charging-Aware Task Assignment (ECTA) problem in urban logistics scenarios, where the objective is to maximize platform revenue by ensuring timely task completion while meeting the charging needs of EVs. To address this challenge, we present e-Charge, an efficient two-stage framework that enables real-time optimization of two continuous processes: task assignment and charging decision. For task assignment, which focuses on matching tasks to suitable EVs, we construct a hybrid weight model that incorporates charging penalties to calculate matching weights for EVs in both active and charging states, thus improving task assignment quality. Additionally, we implement an effective vehicle selection strategy to expedite the matching process, ensuring the efficiency of task assignment. For charging decision, which focuses on determining when and where EVs should be charged, we propose a multi-agent reinforcement learning (MARL) approach to dynamically select the charging timing for EVs. To further enhance decision-making quality, we devise a hierarchical communication graph that enables better collaboration between EVs and facilitates adaptive charging decisions. Finally, extensive experiments demonstrate that <italic>e-Charge</i> significantly outperforms compared methods, achieving higher revenue and task completion ratio across a wide range of parameter settings.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 7","pages":"3947-3961"},"PeriodicalIF":8.9,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144219592","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack 图数据增强与攻击中图神经网络的边摄动问题

IF 8.9 2区计算机科学

IEEE Transactions on Knowledge and Data Engineering Pub Date : 2025-04-30 DOI: 10.1109/TKDE.2025.3565306

Xin Liu;Yuxiang Zhang;Meng Wu;Mingyu Yan;Kun He;Wei Yan;Shirui Pan;Xiaochun Ye;Dongrui Fan

{"title":"Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack","authors":"Xin Liu;Yuxiang Zhang;Meng Wu;Mingyu Yan;Kun He;Wei Yan;Shirui Pan;Xiaochun Ye;Dongrui Fan","doi":"10.1109/TKDE.2025.3565306","DOIUrl":"https://doi.org/10.1109/TKDE.2025.3565306","url":null,"abstract":"Edge perturbation is a basic method to modify graph structures. It can be categorized into two veins based on their effects on the performance of graph neural networks (GNNs), i.e., graph data augmentation and attack. Surprisingly, both veins of edge perturbation methods employ the same operations, yet yield opposite effects on GNNs’ accuracy. A distinct boundary between these methods in using edge perturbation has never been clearly defined. Consequently, inappropriate perturbations may lead to undesirable outcomes, necessitating precise adjustments to achieve desired effects. Therefore, questions of “why edge perturbation has a two-faced effect?” and “what makes edge perturbation flexible and effective?” still remain unanswered. In this paper, we will answer these questions by proposing a unified formulation and establishing a quantizable boundary between two categories of edge perturbation methods. Specifically, we conduct experiments to elucidate the differences and similarities between these methods and theoretically unify the workflow of these methods by casting it to one optimization problem. Then, we devise Edge Priority Detector (EPD) to generate a novel priority metric, bridging these methods up in the workflow. Experiments show that EPD can make augmentation or attack flexibly and achieve comparable or superior performance to other counterparts with less time overhead.","PeriodicalId":13496,"journal":{"name":"IEEE Transactions on Knowledge and Data Engineering","volume":"37 7","pages":"4225-4238"},"PeriodicalIF":8.9,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144232036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0