Negatives-Dominant Contrastive Learning for Generalization in Imbalanced Domains

TL;DR

This paper introduces a novel contrastive learning approach called Negative-Dominant Contrastive Learning (NDCL) to improve model generalization in imbalanced domain settings by emphasizing negatives and enforcing posterior consistency.

Contribution

It provides the first theoretical generalization bound for Imbalanced Domain Generalization and proposes NDCL, a method that enhances discriminability and domain alignment through negative emphasis and re-weighted strategies.

Findings

NDCL outperforms existing methods on benchmark datasets.

Theoretical analysis confirms the importance of posterior discrepancy.

Negative emphasis improves minority class decision boundaries.

Abstract

Imbalanced Domain Generalization (IDG) focuses on mitigating both domain and label shifts, both of which fundamentally shape the model's decision boundaries, particularly under heterogeneous long-tailed distributions across domains. Despite its practical significance, it remains underexplored, primarily due to the technical complexity of handling their entanglement and the paucity of theoretical foundations. In this paper, we begin by theoretically establishing the generalization bound for IDG, highlighting the role of posterior discrepancy and decision margin. This bound motivates us to focus on directly steering decision boundaries, marking a clear departure from existing methods. Subsequently, we technically propose a novel Negative-Dominant Contrastive Learning (NDCL) for IDG to enhance discriminability while enforce posterior consistency across domains. Specifically, inter-class decision-boundary separation is enhanced by placing greater emphasis on negatives as the primary signal in our contrastive learning, naturally amplifying gradient signals for minority classes to avoid the decision boundary being biased toward majority classes. Meanwhile, intra-class compactness is encouraged through a re-weighted cross-entropy strategy, and posterior consistency across domains is enforced through a prediction-central alignment strategy. Finally, rigorous yet challenging experiments on benchmarks validate the effectiveness of our NDCL. The code is available at https://github.com/Alrash/NDCL.