Abstract
In many real-world machine learning applications, samples belong to a set of domains e.g., for product reviews each review belongs to a product category. In this paper, we study multi-domain imbalanced learning (MIL), the scenario that there is imbalance not only in classes but also in domains. In the MIL setting, different domains exhibit different patterns and there is a varying degree of similarity and divergence among domains posing opportunities and challenges for transfer learning especially when faced with limited or insufficient training data.We propose a novel domain-aware contrastive knowledge transfer method called DCMI to (1) identify the shared domain knowledge to encourage positive transfer among similar domains (in particular from head domains to tail domains); (2) isolate the domain-specific knowledge to minimize the negative transfer from dissimilar domains. We evaluated the performance of DCMI on three different datasets showing significant improvements in different MIL scenarios.- Anthology ID:
- 2022.wassa-1.3
- Volume:
- Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- WASSA
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 25–36
- Language:
- URL:
- https://aclanthology.org/2022.wassa-1.3
- DOI:
- 10.18653/v1/2022.wassa-1.3
- Cite (ACL):
- Zixuan Ke, Mohammad Kachuee, and Sungjin Lee. 2022. Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data. In Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis, pages 25–36, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- Domain-Aware Contrastive Knowledge Transfer for Multi-domain Imbalanced Data (Ke et al., WASSA 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.wassa-1.3.pdf
- Data
- LIAR