Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting

Ilias Chalkidis, Anders Søgaard


Abstract
In document classification for, e.g., legal and biomedical text, we often deal with hundreds of classes, including very infrequent ones, as well as temporal concept drift caused by the influence of real world events, e.g., policy changes, conflicts, or pandemics. Class imbalance and drift can sometimes be mitigated by resampling the training data to simulate (or compensate for) a known target distribution, but what if the target distribution is determined by unknown future events? Instead of simply resampling uniformly to hedge our bets, we focus on the underlying optimization algorithms used to train such document classifiers and evaluate several group-robust optimization algorithms, initially proposed to mitigate group-level disparities. Reframing group-robust algorithms as adaptation algorithms under concept drift, we find that Invariant Risk Minimization and Spectral Decoupling outperform sampling-based approaches to class imbalance and concept drift, and lead to much better performance on minority classes. The effect is more pronounced the larger the label set.
Anthology ID:
2022.findings-acl.192
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2441–2454
Language:
URL:
https://aclanthology.org/2022.findings-acl.192
DOI:
10.18653/v1/2022.findings-acl.192
Bibkey:
Cite (ACL):
Ilias Chalkidis and Anders Søgaard. 2022. Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2441–2454, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting (Chalkidis & Søgaard, Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.192.pdf
Software:
 2022.findings-acl.192.software.zip
Video:
 https://aclanthology.org/2022.findings-acl.192.mp4
Code
 coastalcph/lw-robust
Data
BioASQ