Unbalanced Class-incremental Learning for Text Classification Based on Experience Replay

Lifeng Chen, Huaping Zhang, Silamu Wushour, Yugang Li

Research output: Contribution to journalConference articlepeer-review

Abstract

While deep learning has achieved remarkable results for text classification, incremental learning for text classification is still a challenge. The main problem is that models suffer from catastrophic forgetting, which is they always forget knowledge learned before when labelled data comes sequentially and is trained in sequence. In this study, we propose methods of preventing catastrophic forgetting to handle unbalanced increased data. As an improvement over experience replay, our approaches improve the accuracy about 23.3% with 23% of all training data on Yahoo and 9.5% with 12% of all training data and on DBPedia.

Original languageEnglish
Article number012001
JournalJournal of Physics: Conference Series
Volume2513
Issue number1
DOIs
Publication statusPublished - 2023
Event2023 7th International Conference on Artificial Intelligence, Automation and Control Technologies, AIACT 2023 - Virtual, Online, China
Duration: 24 Feb 202326 Feb 2023

Fingerprint

Dive into the research topics of 'Unbalanced Class-incremental Learning for Text Classification Based on Experience Replay'. Together they form a unique fingerprint.

Cite this