English
Related papers

Related papers: Parallel Unlearning in Inherited Model Networks

200 papers

In Machine Learning, the emergence of \textit{the right to be forgotten} gave birth to a paradigm named \textit{machine unlearning}, which enables data holders to proactively erase their data from a trained model. Existing machine…

Cryptography and Security · Computer Science 2022-07-01 Yi Liu , Lei Xu , Xingliang Yuan , Cong Wang , Bo Li

Federated learning (FL) facilitates edge devices to cooperatively train a global shared model while maintaining the training data locally and privately. However, a common assumption in FL requires the participating edge devices to have…

Machine Learning · Computer Science 2024-02-02 Yun-Hin Chan , Zhihan Jiang , Jing Deng , Edith C. -H. Ngai

Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel…

Distributed, Parallel, and Cluster Computing · Computer Science 2022-07-25 Samson B. Akintoye , Liangxiu Han , Huw Lloyd , Xin Zhang , Darren Dancey , Haoming Chen , Daoqiang Zhang

The practical deployment of Federated Learning (FL) on resource-constrained devices is fundamentally limited by the high cost of training large models and the instability caused by heterogeneous (non-IID) client data. Conventional pruning…

Machine Learning · Computer Science 2026-05-13 Christian Internò , Elena Raponi , Markus Olhofer , Ali Raza , Thomas Bäck , Niki van Stein , Yaochu Jin , Barbara Hammer

Federated Learning (FL) often suffers from severe performance degradation when faced with non-IID data, largely due to local classifier bias. Traditional remedies such as global model regularization or layer freezing either incur high…

Machine Learning · Computer Science 2025-06-11 Sunny Gupta , Nikita Jangid , Amit Sethi

When handling streaming graphs, existing graph representation learning models encounter a catastrophic forgetting problem, where previously learned knowledge of these models is easily overwritten when learning with newly incoming graphs. In…

Machine Learning · Computer Science 2024-07-11 Yilun Liu , Ruihong Qiu , Yanran Tang , Hongzhi Yin , Zi Huang

Deep learning models are prone to forgetting information learned in the past when trained on new data. This problem becomes even more pronounced in the context of federated learning (FL), where data is decentralized and subject to…

Machine Learning · Computer Science 2023-07-19 Sara Babakniya , Zalan Fabian , Chaoyang He , Mahdi Soltanolkotabi , Salman Avestimehr

Federated Unlearning (FUL) aims to remove specific participants' data contributions from a trained Federated Learning model, thereby ensuring data privacy and compliance with regulatory requirements. Despite its potential, progress in FUL…

Machine Learning · Computer Science 2026-03-17 Minh-Duong Nguyen , Senura Hansaja , Le-Tuan Nguyen , Quoc-Viet Pham , Ken-Tye Yong , Nguyen H. Tran , Dung D. Le

Federated Unlearning (FU) enables clients to remove the influence of specific data from a collaboratively trained shared global model, addressing regulatory requirements such as GDPR and CCPA. However, this unlearning process introduces a…

Machine Learning · Computer Science 2025-06-03 Hithem Lamri , Manaar Alam , Haiyan Jiang , Michail Maniatakos

Inverse problems involving differential equations often require identifying unknown parameters or functions from data. Existing approaches, such as Physics-Informed Neural Networks (PINNs), Universal Differential Equations (UDEs) and…

Machine Learning · Computer Science 2025-05-23 Shalev Manor , Mohammad Kohandel

Machine unlearning (MU) for large language models (LLMs), commonly referred to as LLM unlearning, seeks to remove specific undesirable data or knowledge from a trained model, while maintaining its performance on standard tasks. While…

Machine Learning · Computer Science 2026-03-03 Yiwei Chen , Soumyadeep Pal , Yimeng Zhang , Qing Qu , Sijia Liu

We study the problem of actively learning a non-parametric choice model based on consumers' decisions. We present a negative result showing that such choice models may not be identifiable. To overcome the identifiability problem, we…

Machine Learning · Computer Science 2024-04-26 Fransisca Susan , Negin Golrezaei , Ehsan Emamjomeh-Zadeh , David Kempe

Deep neural networks (DNNs) have recently achieved a great success in computer vision and several related fields. Despite such progress, current neural architectures still suffer from catastrophic interference (a.k.a. forgetting) which…

Computer Vision and Pattern Recognition · Computer Science 2021-11-23 Hichem Sahbi , Haoming Zhan

Deep learning models often struggle to maintain generalizability in medical imaging, particularly under domain-fracture scenarios where distribution shifts arise from varying imaging techniques, acquisition protocols, patient populations,…

Machine Learning · Computer Science 2025-08-15 Furkan Pala , Islem Rekik

Seismic data often contain gaps due to various obstacles in the investigated area and recording instrument failures. Deep learning techniques offer promising solutions for reconstructing missing data parts by leveraging existing…

Geophysics · Physics 2024-04-04 Mohammad Mahdi Abedi , David Pardo , Tariq Alkhalifah

In Autonomous Driving Systems (ADS), Directed Acyclic Graphs (DAGs) are widely used to model complex data dependencies and inter-task communication. However, existing DAG scheduling approaches oversimplify data fusion tasks by assuming…

Systems and Control · Electrical Eng. & Systems 2025-10-29 Hoora Sobhani , Hyoseung Kim

The advent of Federated Learning (FL) highlights the practical necessity for the right to be forgotten for all clients, allowing them to request data deletion from the machine learning models service provider. This necessity has spurred a…

Machine Learning · Computer Science 2025-01-09 Hanlin Gu , Win Kent Ong , Chee Seng Chan , Lixin Fan

Non-intrusive load monitoring (NILM) aims at decomposing the total reading of the household power consumption into appliance-wise ones, which is beneficial for consumer behavior analysis as well as energy conservation. NILM based on deep…

Signal Processing · Electrical Eng. & Systems 2021-05-25 Haijin Wang , Caomingzhe Si , Junhua Zhao

We present Synergy Aware Forgetting Ensemble (SAFE), a method to adapt large models on a diverse collection of data while minimizing the expected cost to remove the influence of training samples from the trained model. This process, also…

Machine Learning · Computer Science 2023-08-23 Yonatan Dukler , Benjamin Bowman , Alessandro Achille , Aditya Golatkar , Ashwin Swaminathan , Stefano Soatto

Machine unlearning aims to remove the influence of specific data from trained models while preserving general utility. Existing approximate unlearning methods often rely on performance-degradation heuristics, such as loss maximization or…

Machine Learning · Computer Science 2026-03-13 Jonas Mirlach , Sonia Laguna , Julia E. Vogt