miCSE: Mutual Information Contrastive Learning for Low-shot Sentence Embeddings
This addresses the challenge of sample efficiency in self-supervised learning for sentence embeddings, particularly in low-data scenarios, though it is incremental as it builds on existing contrastive methods.
The paper tackled the problem of few-shot sentence embedding by proposing miCSE, a mutual information-based contrastive learning framework that enforces alignment between attention patterns of augmented views, resulting in strong performance on multiple few-shot benchmarks.
This paper presents miCSE, a mutual information-based contrastive learning framework that significantly advances the state-of-the-art in few-shot sentence embedding. The proposed approach imposes alignment between the attention pattern of different views during contrastive learning. Learning sentence embeddings with miCSE entails enforcing the structural consistency across augmented views for every sentence, making contrastive self-supervised learning more sample efficient. As a result, the proposed approach shows strong performance in the few-shot learning domain. While it achieves superior results compared to state-of-the-art methods on multiple benchmarks in few-shot learning, it is comparable in the full-shot scenario. This study opens up avenues for efficient self-supervised learning methods that are more robust than current contrastive methods for sentence embedding.