King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；SDAIA-KAUST Center of Excellence in Data Science and Artificial Intelligence（沙特数据与人工智能局-阿卜杜拉国王科技大学数据科学与人工智能卓越中心）；Iowa State University（爱荷华州立大学）；Computational Bioscience Research Center（计算生物科学研究中心）
Cheng-Long Wang, Mengdi Huai, Di Wang
备注：
To appear in the 32nd USENIX Security Symposium, August 2023, Anaheim, CA, USA
As a way to implement the "right to be forgotten" in machine learning, \textit{machine unlearning} aims to completely remove the contributions and information of the samples to be deleted from a trained model without affecting the contributions of other samples. Recently, many frameworks for machine unlearning have been proposed, and most of them focus on image and text data. To extend machine unlearning to graph data, \textit{GraphEraser} has been proposed. However, a critical issue is that \textit{GraphEraser} is specifically designed for the transductive graph setting, where the graph is static and attributes and edges of test nodes are visible during training. It is unsuitable for the inductive setting, where the graph could be dynamic and the test graph information is invisible in advance. Such inductive capability is essential for production machine learning systems with evolving graphs like social media and transaction networks. To fill this gap, we propose the \underline{\bf G}\underline{\bf U}ided \underline{\bf I}n\underline{\bf D}uctiv\underline{\bf E} Graph Unlearning framework (GUIDE). GUIDE consists of three components: guided graph partitioning with fairness and balance, efficient subgraph repair, and similarity-based aggregation. Empirically, we evaluate our method on several inductive benchmarks and evolving transaction graphs. Generally speaking, GUIDE can be efficiently implemented on the inductive graph learning tasks for its low graph partition cost, no matter on computation or structure information. The code will be available here: https://github.com/Happy2Git/GUIDE.
Towards Efficient Target-Level Machine Unlearning Based on Essential Graph
University of Technology Sydney（悉尼科技大学）；City University of Macau（澳门城市大学）；Shenzhen Institute of Advanced Technology, University of Chinese Academy of Sciences（中国科学院大学深圳先进技术研究院）
CISPA Helmholtz Center for Information Security（CISPA亥姆霍兹信息安全中心）；University of Virginia（弗吉尼亚大学）；University of Lausanne（洛桑大学）
Machine unlearning is a process of removing the impact of some training data from the machine learning (ML) models upon receiving removal requests. While straightforward and legitimate, retraining the ML model from scratch incurs a high computational overhead. To address this issue, a number of approximate algorithms have been proposed in the domain of image and text data, among which SISA is the state-of-the-art solution. It randomly partitions the training set into multiple shards and trains a constituent model for each shard. However, directly applying SISA to the graph data can severely da…
Nanyang Technological University Singapore（南洋理工大学新加坡）
As a new and promising approach, existing machine unlearning (MU) works typically emphasize theoretical formulations or optimization objectives to achieve knowledge removal. However, when deployed in real-world scenarios, such solutions typically face scalability issues and have to address practical requirements such as full access to original datasets and model. In contrast to the existing approaches, we regard classification training as a sequential process where classes are learned sequentially, which we call \emph{inductive approach}. Unlearning can then be done by reversing the last train…
University of Massachusetts Lowell, USA（马萨诸塞大学洛约拉分校）；Pennsylvania State University, USA（宾夕法尼亚州立大学）；Michigan State University, USA（密歇根州立大学）；The Chinese University of Hong Kong, China（香港中文大学）；Sapienza University of Rome, Italy（罗马萨皮恩扎大学）
Structural Disentanglement in Bilinear MLPs via Architectural Inductive Bias
Department of Electrical Engineering, Indian Institute of Technology Roorkee (IIT Roorkee), India；Department of Material Science \& Engineering, IIT Roorkee, India；Mehta Family School of Data Science
Department of Electrical Engineering and Computer Science University of California Irvine（电气工程与计算机科学系加州大学伊维特分校）；Department of Electrical and Computer Engineering University of Rochester（电气与计算机工程系罗切斯特大学）
Unlearning on Spatio-Temporal Graphs through Subgraph Virtual Edge Reconstruction
Texas A&M University - Corpus Christi（德州农工大学科珀斯克里斯蒂分校）；Delft University of Technology（代尔夫特理工大学）；University of Texas at San Antonio（德克萨斯大学圣安东尼奥分校）；Biogen（渤健公司）
Graph-structured data is ubiquitous in practice and often processed using graph neural networks (GNNs). With the adoption of recent laws ensuring the ``right to be forgotten'', the problem of graph data removal has become of significant importance. To address the problem, we introduce the first known framework for \emph{certified graph unlearning} of GNNs. In contrast to standard machine unlearning, new analytical and heuristic unlearning challenges arise when dealing with complex graph data. First, three different types of unlearning requests need to be considered, including node feature, edg…
Enabling Group Fairness in Graph Unlearning via Bi-level Debiasing
Department of Electrical Engineering and Computer Science, University of California, Irvine（电气工程与计算机科学系，加州大学伊尔凡分校）；Donald Bren School of Information and Computer Sciences, University of California, Irvine（戴维·布伦信息与计算机科学学院，加州大学伊尔凡分校）
GraphMU: Repairing Robustness of Graph Neural Networks via Machine Unlearning
Chongqing University of Posts and Telecommunications（重庆邮电大学）；Chengdu University of Information Technology（成都信息工程大学）；Chongqing Normal University（重庆师范大学）
Computer Science Department, Vanderbilt University（范德比尔特大学计算机科学系）；Computer Science Department, Information Technology University（信息技术大学计算机科学系）；Systems Engineering Department, University of Texas at Dallas（德克萨斯大学达拉斯分校系统工程系）
Erase then Rectify: A Training-Free Parameter Editing Approach for Cost-Effective Graph Unlearning
Sun Yat-sen University（中山大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）；The Hong Kong University of Science and Technology（香港科技大学）
FairGU: Fairness-aware Graph Unlearning in Social Networks
Jilin University Changchun China；Zhejiang Gongshang University Hangzhou China；Adelaide University Adelaide Australia；Jinan University \& TAL Education Group Guangzhou China；RMIT University Melbourne Australia；Nanyang Technological University Singapore；Jilin University；Zhejiang Gongshang University；Adelaide University；Jinan University \& TAL Education Group；RMIT University；Nanyang Technological University
University of Massachusetts Lowell（马萨诸塞大学洛厄尔分校）；Adobe（奥多比）；Harvard University（哈佛大学）
Graph unlearning, which involves deleting graph elements such as nodes, node labels, and relationships from a trained graph neural network (GNN) model, is crucial for real-world applications where data elements may become irrelevant, inaccurate, or privacy-sensitive. However, existing methods for graph unlearning either deteriorate model weights shared across all nodes or fail to effectively delete edges due to their strong dependence on local graph neighborhoods. To address these limitations, we introduce GNNDelete, a novel model-agnostic layer-wise operator that optimizes two critical proper…
Central South University（中南大学）；Shanghai Maritime University（上海 Maritime 大学）；Shanghai Jiao Tong University（上海交通大学）；Tongji University（同济大学）；SenseTime Research（商汤科技研究院）；University of Sydney（悉尼大学）；Hong Kong University of Science（香港科学大学）
Forget and Explain: Transparent Verification of GNN Unlearning
Chung-Ang University Department of Smart Cities Seoul Republic of Korea（Chung-Ang大学智慧城市系 首尔 大韩民国）；Chung-Ang University Department of Computer Science（Chung-Ang大学计算机科学系）；Chung-Ang University（Chung-Ang大学）
State Key Laboratory for Novel Software Technology（计算机软件新技术国家重点实验室）；Nanjing University（南京大学）；National Institute of Healthcare Data Science（国家健康医疗数据科学研究院）
Federated Learning (FL) recently emerges as a paradigm to train a global machine learning model across distributed clients without sharing raw data. Knowledge Graph (KG) embedding represents KGs in a continuous vector space, serving as the backbone of many knowledge-driven applications. As a promising combination, federated KG embedding can fully take advantage of knowledge learned from different clients while preserving the privacy of local data. However, realistic problems such as data heterogeneity and knowledge forgetting still remain to be concerned. In this paper, we propose FedLU, a nov…
