$f$-FUM: Federated Unlearning via min--max and $f$-divergence
Department of Statistics, Universite de Geneve, Geneva, Switzerland（日内瓦大学统计系）；University of Cambridge, Cambridge, United Kingdom（剑桥大学）；The Alan Turing Institute, London, UK（艾伦·图灵研究所）
Radmehr Karimian, Amirhossein Bagheri, Meghdad Kurmanji, Nicholas D. Lane, Gholamali Aminian
Federated learning (FL) enables collaborative training while keeping raw data on clients. Deletion requests and the discovery of poisoned data create a need to remove selected contributions from an already trained model. This is challenging in FL because client data are decentralized and their influence is entangled through repeated aggregation. We present f-FUM, an active federated unlearning method that builds on teacher-student forget/retain optimization. Starting from a pretrained global model, the method keeps that model fixed as a teacher. Clients maximize an $f$-divergence between student and teacher predictive distributions on forget examples, then minimize KL-based teacher-student disagreement and supervised loss on retained examples. The updates are aggregated in separate, sample-weighted synchronization phases without moving raw data to the server or changing the model architecture. We evaluate forget-side divergence choices in client-level and data-level deletion settings involving backdoors, label confusion, and clean-data deletion. Under equal synchronization-phase budgets, divergence choice changes the forgetting-utility trade-off, yielding improvements in some settings and mixed results in others. In the evaluated configurations, f-FUM uses up to 8 times fewer synchronization phases than full federated retraining.
Machine Unlearning with Minimal Gradient Dependence for High Unlearning Ratios
School of Information, Renmin University of China（中国人民大学信息学院）；School of Computer Science and Big Data, Minjiang University（闽江学院计算机与大数据学院）；RMIT University（皇家墨尔本理工大学）
Efficient machine unlearning with minimax optimality
Institute of Statistics and Big Data, Renmin University of China（中国人民大学统计与大数据研究院）；Department of Statistics, Rutgers University（罗格斯大学统计系）；Department of Statistics and Data Science, Tsinghua University（清华大学统计与数据科学系）
本文提出一种通用损失函数的机器遗忘统计框架，针对平方损失开发了Unlearning Least Squares方法，证明其在仅使用预训练估计器、遗忘样本和少量剩余样本时的最小最大最优性，并建立了无需全量重训练的推断程序。
Electrical Engineering and Computer Science, University of California, Merced, CA 95343, USA（电气工程与计算机科学系，加州大学默塞德分校）；Department of Applied Mathematics, University of California, Merced, CA 95343, USA（应用数学系，加州大学默塞德分校）；Department of Innovation and Research, North Carolina State University, Raleigh, NC, USA（创新与研究系，北卡罗来纳州立大学）；Automation (MESA) Lab, Department of Mechanical Engineering, School of Engineering, University of California, Merced, CA 95343, USA（自动化（MESA）实验室，机械工程系，工程学院，加州大学默塞德分校）
SEMU: Singular Value Decomposition for Efficient Machine Unlearning
Faculty of Mathematics and Computer Science, Jagiellonian University（雅盖隆大学数学与计算机科学学院）；Institute of Theoretical and Applied Informatics, Polish Academy of Sciences（波兰科学院理论与应用信息研究所）；Ardigen SA（Ardigen SA公司）
PrivEraserVerify: Efficient, Private, and Verifiable Federated Unlearning
Department of Electronics and Communication Engineering（电子与通信工程系）；Department of Mathematics and Computer Science（数学与计算机科学系）；Khulna University of Engineering & Technology（库尔纳工程与技术大学）；Hobart and William Smith Colleges（霍巴特和威廉·斯密斯学院）；Department of Electrical and Electronic Engineering（电气与电子工程系）
pFedUL: Layer-Aware Federated Unlearning for Personalized Federated Learning
Saunders College of Business, Rochester Institute of Technology（罗切斯特理工学院商学院）；School of Electrical and Computer Engineering, Georgia Institute of Technology（佐治亚理工学院电子与计算机工程学院）
$\textbf{AGT$^{AO}$}$: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality
School of Computer Science and Technology, Xi’an Jiaotong University, China（西安交通大学计算机科学与技术学院）；MOE KLINNS Lab, Xi’an Jiaotong University, China（西安交通大学MOE KLINNS实验室）；Shaanxi Province Key Laboratory of Big Data Knowledge Engineering, China（陕西省大数据知识工程重点实验室）
Remaining-data-free Machine Unlearning by Suppressing Sample Contribution
Institute of Image Processing and Pattern Recognition, School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（图像处理与模式识别研究院，自动化与智能感知学院，上海交通大学）
Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs
Dept. of Computer Science & Munich Data Science Institute, Technical University of Munich（计算机科学系及慕尼黑数据科学研究所，技术大学慕尼黑）；Mila, Université de Montréal（蒙特利尔大学Mila）
University of Trento（特伦托大学）；University of Bergamo（贝加莫大学）；Inria Grenoble（格勒诺布尔研究所）；Univ. Grenoble Alpes（格勒诺布尔阿尔卑斯大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）
Distribution-Guided and Constrained Quantum Machine Unlearning
Department of Electrical Engineering, Lahore University of Management Sciences, Lahore 54792, Pakistan.（电气工程系，拉合尔管理科学大学，巴基斯坦拉合尔）；Department of Physics, Lahore University of Management Sciences, Lahore 54792, Pakistan.（物理系，拉合尔管理科学大学，巴基斯坦拉合尔）
Machine Unlearning via Information Theoretic Regularization
Department of Mathematics University of California Davis（加州大学戴维斯分校数学系）；Center of Data Science and Artificial Intelligence Research University of California Davis（加州大学戴维斯分校数据科学与人工智能研究中心）
Parameter-Efficient Token Embedding Editing for Clinical Class-Level Unlearning
Department of Computer Science, The George Washington University（乔治华盛顿大学计算机科学系）；Center for Speech and Language Processing, Johns Hopkins University（约翰霍普金斯大学语音与语言处理中心）
Towards Federated Domain Unlearning: Verification Methodologies and Challenges
University of Macau（澳门大学）；University Of Electronic Science And Technology（电子科技大学）；Institute of High Performance Computing, Agency for Science, Technology and Research（新加坡科技研究局高性能计算研究院）
Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
The University of Arizona（亚利桑那大学）；The University of Tulsa（塔尔萨大学）；Clemson University（克莱姆森大学）；Western Digital Corporation（西部数据公司）；University of Georgia（佐治亚大学）
Unlearning Isn't Deletion: Investigating Reversibility of Machine Unlearning in LLMs
The Hong Kong Polytechnic University（香港理工大学）；Carnegie Mellon University（卡内基梅隆大学）；University of California, Santa Cruz（加州大学圣克ruz分校）；Huawei Technologies（华为技术有限公司）；Research Centre for Privacy and Security Technologies in Future Smart Systems, PolyU（未来智能系统中的隐私与安全技术研究中心，PolyU）
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）
机器遗忘是在接收到移除请求时从机器学习（ML）模型中移除一些训练数据的影响的过程。虽然简单合法，但从头开始重新训练ML模型会产生很高的计算开销。为了解决这个问题，在图像和文本数据领域已经提出了许多近似算法，其中SISA是最先进的解决方案。它将训练集随机划分为多个分片，并为每个分片训练一个组成模型。然而，直接将SISA应用于图数据可能会严重破坏图结构信息，从而破坏所产生的ML模型实用程序。在本文中，我们提出了GraphEraser，一种新的机器遗忘框架，适合于图形数据。它的贡献包括两个新的图划分算法和基于学习的聚合方法。我们在五个真实世界的图形数据集上进行了广泛的实验，以说明GraphEraser的学习效率和模型实用性。它实现了2.06 $\times$（小数据集）到35.94 $\times$（大数据集）的学习时间改进。另一方面，GraphEraser实现了高达$62.5\%$更高的F1分数，我们提出的基于学习的聚合方法实现了高达$112\%$更高的F1分数。\footnote{Our code is available at \url{https://github.com/MinChen00/Graph-Unlearning}.}
Classification-Head Bias in Class-Level Machine Unlearning: Diagnosis, Mitigation, and Evaluation
School of Computer Science and Cyber Engineering, Guangzhou University（计算机科学与电子工程学院，广州大学）；School of Artificial Intelligence, Guangzhou University（人工智能学院，广州大学）；Guangzhou Institute of Internet of Things（广州物联网研究院）
