paper-with-me

Papers

Federated Continual Learning with Weighted Inter-client Transfer

2020-03-06 · Jaehong Yoon, Wonyong Jeong, Giwoong Lee, Eunho Yang, Sung Ju Hwang

There has been a surge of interest in continual learning and federated learning, both of which are important in deep neural networks in real-world scenarios. Yet little research has been done regarding the scenario where each client learns on a sequence of tasks from a private local data stream. This problem of federated continual learning poses new challenges to continual learning, such as utilizing knowledge from other clients, while preventing interference from irrelevant knowledge. To resolve these issues, we propose a novel federated continual learning framework, Federated Weighted Inter-client Transfer (FedWeIT), which decomposes the network weights into global federated parameters and sparse task-specific parameters, and each client receives selective knowledge from other clients by taking a weighted combination of their task-specific parameters. FedWeIT minimizes interference between incompatible tasks, and also allows positive knowledge transfer across clients during learning. We validate our FedWeIT against existing federated learning and continual learning methods under varying degrees of task similarity across clients, and our model significantly outperforms them with a large reduction in the communication cost. Code is available at https://github.com/wyjeong/FedWeIT

📄 PDF Abstract BibTeX arXiv:2003.03196

Code (1)

wyjeong/FedWeIT 공식 구현 tf

Tasks

Continual LearningFederated LearningTransfer Learning

Similar Papers 제목 키워드 기반

Federated Continual Learning for Text Classification via Selective Inter-client Transfer

2022-10-12 · Yatin Chaudhary, Pranav Rai, Matthias Schubert, Hinrich Schütze 외

In this work, we combine the two paradigms: Federated Learning (FL) and Continual Learning (CL) for text classification task in cloud-edge continuum. The objective of Federated Continual Learning (FCL) is to improve deep…

Continual LearningFederated Learningtext-classificationText Classification+1

FedProK: Trustworthy Federated Class-Incremental Learning via Prototypical Feature Knowledge Transfer

2024-05-04 · Xin Gao, Xin Yang, Hao Yu, Yan Kang 외

Federated Class-Incremental Learning (FCIL) focuses on continually transferring the previous knowledge to learn new classes in dynamic Federated Learning (FL). However, existing methods do not consider the trustworthines…

class-incremental learningClass Incremental LearningFederated LearningIncremental Learning+1

Addressing Client Drift in Federated Continual Learning with Adaptive Optimization

2022-03-24 · Yeshwanth Venkatesha, Youngeun Kim, Hyoungseob Park, Yuhang Li 외

Federated learning has been extensively studied and is the prevalent method for privacy-preserving distributed learning in edge devices. Correspondingly, continual learning is an emerging field targeted towards learning …

Continual LearningFederated LearningPrivacy Preserving

FedKNOW: Federated Continual Learning with Signature Task Knowledge Integration at Edge

2022-12-04 · Yaxin Luopan, Rui Han, Qinglong Zhang, Chi Harold Liu 외

Deep Neural Networks (DNNs) have been ubiquitously adopted in internet of things and are becoming an integral of our daily life. When tackling the evolving learning tasks in real world, such as classifying different type…

Continual LearningTransfer Learning

Masked Autoencoders are Efficient Continual Federated Learners

2023-06-06 · Subarnaduti Paul, Lars-Joel Frey, Roshni Kamath, Kristian Kersting 외

Machine learning is typically framed from a perspective of i.i.d., and more importantly, isolated data. In parts, federated learning lifts this assumption, as it sets out to solve the real-world challenge of collaborativ…

Continual LearningFederated LearningTransfer Learning