Dynamic Margin-based Contrastive Learning for Robust Negative Sampling in Information Retrieval
Year: 2025
Type: conference-paper
Abstract: Modern information retrieval (IR) systems, powered by bi-encoder architectures and pretrained language models, rely on effective negative sampling for contrastive learning. While easy negatives are computationally simple, they fail to challenge the model, whereas hard negatives-selected via methods like BM25, ANCE, or ADORE-can be overly difficult and misleading. To this end, this paper proposes dynamic margin-based contrastive learning (DMCL), which adaptively adjusts the decision boundary based on query-negative similarity, ensuring consistent exposure to moderately hard negatives. Experiments across diverse datasets and models show that DMCL outperforms traditional methods, achieving state-of-the-art retrieval performance with minimal computational cost.
Authors: Tsai-Tsung Chen, Chuan-Ju Wang, Ming-Feng Tsai
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4412377270