Survey on Online Streaming Continual Learning - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Survey on Online Streaming Continual Learning

Résumé

Stream Learning (SL) attempts to learn from a data stream efficiently. A data stream learning algorithm should adapt to input data distribution shifts without sacrificing accuracy. These distribution shifts are known as ”concept drifts” in the literature. SL provides many supervised, semi-supervised, and unsupervised methods for detecting and adjusting to concept drift. On the other hand, Continual Learning (CL) attempts to preserve previous knowledge while performing well on the current concept when confronted with concept drift. In Online Continual Learning (OCL), this learning happens online. This survey explores the intersection of those two online learning paradigms to find synergies. We identify this intersection as Online Streaming Continual Learning (OSCL). The study starts with a gentle introduction to SL and then explores CL. Next, it explores OSCL from SL and OCL perspectives to point out new research trends and give directions for future research.

Dates et versions

hal-04468380 , version 1 (20-02-2024)

Identifiants

Citer

Nuwan Gunasekara, Bernhard Pfahringer, Heitor Murilo Gomes, Albert Bifet. Survey on Online Streaming Continual Learning. Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI 2023, 19th-25th August 2023, Macao, SAR, China, Aug 2023, Macao, China. pp.6628--6637, ⟨10.24963/IJCAI.2023/743⟩. ⟨hal-04468380⟩
7 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More