A Comprehensive Survey of Continual Learning: Theory, Method and Application
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-08 · 46 (8) · 5362-5383
DOI: 10.1109/tpami.2024.3367329 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-08. Verfasst von Liyuan Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1103-mal zitiert (Crossref) und nennt 318 Literaturangaben. Gefördert von: National Natural Science Foundation of China, BNRist, Tsinghua Institute for Guo Qiang.
Abstract (Originalsprache)
To cope with real-world dynamics, an intelligent system needs to incrementally acquire, update, accumulate, and exploit knowledge throughout its lifetime. This ability, known as continual learning, provides a foundation for AI systems to develop themselves adaptively. In a general sense, continual learning is explicitly limited by catastrophic forgetting, where learning a new task usually results in a dramatic performance drop of the old tasks. Beyond this, increasingly numerous advances have emerged in recent years that largely extend the understanding and application of continual learning. The growing and widespread interest in this direction demonstrates its realistic significance as well as complexity. In this work, we present a comprehensive survey of continual learning, seeking to bridge the basic settings, theoretical foundations, representative methods, and practical applications. Based on existing theoretical and empirical results, we summarize the general objectives of continual learning as ensuring a proper stability-plasticity trade-off and an adequate intra/inter-task generalizability in the context of resource efficiency. Then we provide a state-of-the-art and elaborated taxonomy, extensively analyzing how representative strategies address continual learning, and how they are adapted to particular challenges in various applications. Through an in-depth discussion of promising directions, we believe that such a holistic perspective can greatly facilitate subsequent exploration in this field and beyond.
Förderung
- National Natural Science Foundation of China
- BNRist
- Tsinghua Institute for Guo Qiang
- Tsinghua-OPPO Joint Research Center for Future Terminal Technology
- High Performance Computing Center
- Tsinghua University
- Postdoctoral Fellowship Program of CPSF
- Shuimu Tsinghua Scholar
Zitieren
APA
Wang, L., Zhang, X., Su, H., & Zhu, J. (2024). A Comprehensive Survey of Continual Learning: Theory, Method and Application. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(8), 5362-5383. https://doi.org/10.1109/tpami.2024.3367329
Vancouver
Wang L, Zhang X, Su H, Zhu J. A Comprehensive Survey of Continual Learning: Theory, Method and Application. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(8):5362-5383. doi:10.1109/tpami.2024.3367329
BibTeX
@article{Wang2024,
author = {Wang, Liyuan and Zhang, Xingxing and Su, Hang and Zhu, Jun},
title = {A Comprehensive Survey of Continual Learning: Theory, Method and Application},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {8},
pages = {5362--5383},
doi = {10.1109/tpami.2024.3367329}
}
EUVIMED