Exploring Contrastive Learning for Long-Tailed Multi-Label Text Classification
Authors:
Preprint
Abstract
Learning an effective representation in multi-label text classification (MLTC) is a significant challenge in NLP. This challenge arises from the inherent complexity of the task, which is shaped by two key factors: the intricate connections between labels and the widespread long-tailed distribution of the data. To overcome this issue, one potential approach involves integrating supervised contrastive learning with classical supervised loss functions. Although contrastive learning has shown remarkable performance in multi-class classification, its impact in the multi-label framework has not been thoroughly investigated. In this paper, we conduct an in-depth study of supervised contrastive learning and its influence on representation in MLTC context. We emphasize the importance of considering long-tailed data distributions to build a robust representation space, which effectively addresses two critical challenges associated with contrastive learning that we identify: the "lack of positives" and the "attraction-repulsion imbalance". Building on this insight, we introduce a novel contrastive loss function for MLTC. It attains Micro-F1 scores that either match or surpass those obtained with other frequently employed loss functions, and demonstrates a significant improvement in Macro-F1 scores across three multi-label datasets.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- An Effective Deployment of Contrastive Learning in Multi-label Text Classification2023
- An Exploration of Encoder-Decoder Approaches to Multi-Label Classification for Legal and Biomedical Text2023
- Label-representative graph convolutional network for multi-label text classificationApplied Intelligence, 2022
- Use All The Labels: A Hierarchical Multi-Label Contrastive Learning Framework2022
- Improved Multi-label Classification under Temporal Concept Drift: Rethinking Group-Robust Algorithms in a Label-Wise Setting2022
- Contrastive Learning-Enhanced Nearest Neighbor Mechanism for Multi-Label Text Classification2022
- SpanEmo: Casting Multi-label Emotion Classification as Span-prediction2021
- Label-Specific Dual Graph Neural Network for Multi-Label Text Classification2021
- Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning2021
- Label-Specific Document Representation for Multi-Label Text Classification2019