Papers › Contrastive Learning in Distilled Models

Contrastive Learning in Distilled Models

23 Jan 2024arXiv:2401.12472archive 2025-07-28

Valerie Lim, Kai Wen Ng, Kenneth Lim

Natural Language Processing models like BERT can provide state-of-the-art word embeddings for downstream NLP tasks. However, these models yet to perform well on Semantic Textual Similarity, and may be too large to be deployed as lightweight edge applications. We seek to apply a suitable contrastive learning method based on the SimCSE paper, to a model architecture adapted from a knowledge distillation based model, DistilBERT, to address these two issues. Our final lightweight model DistilFace achieves an average of 72.1 in Spearman's correlation on STS tasks, a 34.2 percent improvement over BERT base.

Paper PDF Code

Code

kennethlimjf/contrastive-learning-in-distilled-models officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Contrastive Learning Knowledge Distillation STS Semantic Textual Similarity Word Embeddings

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Adam Attention Attention Dropout BERT Contrastive Learning Dense Connections DistilBERT Dropout Knowledge Distillation Layer Normalization Linear Layer Linear Warmup With Linear Decay Multi-Head Attention Residual Connection SimCSE Softmax Weight Decay WordPiece

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections