Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Yichen, Wang, Haozhao, Xu, Wenchao, Xiao, Tianzhe, Liu, Hong, Tu, Minzhu, Wang, Yuying, Yang, Xin, Zhang, Rui, Yu, Shui, Guo, Song, Li, Ruixuan
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909601924907008
author Li, Yichen
Wang, Haozhao
Xu, Wenchao
Xiao, Tianzhe
Liu, Hong
Tu, Minzhu
Wang, Yuying
Yang, Xin
Zhang, Rui
Yu, Shui
Guo, Song
Li, Ruixuan
author_facet Li, Yichen
Wang, Haozhao
Xu, Wenchao
Xiao, Tianzhe
Liu, Hong
Tu, Minzhu
Wang, Yuying
Yang, Xin
Zhang, Rui
Yu, Shui
Guo, Song
Li, Ruixuan
contents Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and scalability in deploying this paradigm in distributed systems, it is essential to conquer challenges stemming from both spatial and temporal dimensions, manifesting as distribution shifts, catastrophic forgetting, heterogeneity, and privacy issues. This survey focuses on a comprehensive examination of the development of the non-centralized continual learning algorithms and the real-world deployment across distributed devices. We begin with an introduction to the background and fundamentals of non-centralized learning and continual learning. Then, we review existing solutions from three levels to represent how existing techniques alleviate the catastrophic forgetting and distribution shift. Additionally, we delve into the various types of heterogeneity issues, security, and privacy attributes, as well as real-world applications across three prevalent scenarios. Furthermore, we establish a large-scale benchmark to revisit this problem and analyze the performance of the state-of-the-art NCCL approaches. Finally, we discuss the important challenges and future research directions in NCCL.
format Preprint
id arxiv_https___arxiv_org_abs_2412_13840
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey
Li, Yichen
Wang, Haozhao
Xu, Wenchao
Xiao, Tianzhe
Liu, Hong
Tu, Minzhu
Wang, Yuying
Yang, Xin
Zhang, Rui
Yu, Shui
Guo, Song
Li, Ruixuan
Machine Learning
Distributed, Parallel, and Cluster Computing
Non-Centralized Continual Learning (NCCL) has become an emerging paradigm for enabling distributed devices such as vehicles and servers to handle streaming data from a joint non-stationary environment. To achieve high reliability and scalability in deploying this paradigm in distributed systems, it is essential to conquer challenges stemming from both spatial and temporal dimensions, manifesting as distribution shifts, catastrophic forgetting, heterogeneity, and privacy issues. This survey focuses on a comprehensive examination of the development of the non-centralized continual learning algorithms and the real-world deployment across distributed devices. We begin with an introduction to the background and fundamentals of non-centralized learning and continual learning. Then, we review existing solutions from three levels to represent how existing techniques alleviate the catastrophic forgetting and distribution shift. Additionally, we delve into the various types of heterogeneity issues, security, and privacy attributes, as well as real-world applications across three prevalent scenarios. Furthermore, we establish a large-scale benchmark to revisit this problem and analyze the performance of the state-of-the-art NCCL approaches. Finally, we discuss the important challenges and future research directions in NCCL.
title Unleashing the Power of Continual Learning on Non-Centralized Devices: A Survey
topic Machine Learning
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2412.13840