Abstract
Continual learning (CL) aims to enhance sequential learning by alleviating the forgetting of previously acquired knowledge. Recent advances in CL lack consideration of the real-world scenarios, where labeled data are scarce and unlabeled data are abundant. To narrow this gap, we focus on semi-supervised continual learning (SSCL). We exploit unlabeled data under limited supervision in the CL setting and demonstrate the feasibility of semi-supervised learning in CL. In this work, we propose a novel method, namely Meta-SSCL, which combines meta-learning with pseudo-labeling and data augmentations to learn a sequence of semi-supervised tasks without catastrophic forgetting. Extensive experiments on CL benchmark text classification datasets show that our method achieves promising results in SSCL.
Original language | English |
---|---|
Title of host publication | Proceedings of the 31st ACM International Conference on Information and Knowledge Management |
Editors | Esra Akbas, Badrul Sarwar |
Place of Publication | New York NY USA |
Publisher | Association for Computing Machinery (ACM) |
Pages | 4024-4028 |
Number of pages | 5 |
ISBN (Electronic) | 9781450392365 |
ISBN (Print) | 9781450392365 |
DOIs | |
Publication status | Published - 2022 |
Event | ACM International Conference on Information and Knowledge Management 2022 - Atlanta, United States of America Duration: 17 Oct 2022 → 21 Oct 2022 Conference number: 31st https://dl.acm.org/doi/proceedings/10.1145/3511808 (Proceedings) https://www.cikm2022.org/calls/call-for-applied-research-papers (Website) |
Conference
Conference | ACM International Conference on Information and Knowledge Management 2022 |
---|---|
Abbreviated title | CIKM 2022 |
Country/Territory | United States of America |
City | Atlanta |
Period | 17/10/22 → 21/10/22 |
Internet address |
Keywords
- continual learning
- text classification
- semi-supervised learning
- meta-learning