SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.13499 · 2023

DistillCSE: Distilled Contrastive Learning for Sentence Embeddings

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

This paper proposes the DistillCSE framework, which performs contrastive learning under the self-training paradigm with knowledge distillation. The potential advantage of DistillCSE is its self-enhancing feature: using a base model to provide additional supervision signals, a stronger model may be learned through knowledge distillation. However, the vanilla DistillCSE through the standard implementation of knowledge distillation only achieves marginal improvements due to severe overfitting. The further quantitative analyses demonstrate the reason that the standard knowledge distillation exhibits a relatively large variance of the teacher model's logits due to the essence of contrastive learning. To mitigate the issue induced by high variance, this paper accordingly proposed two simple yet effective solutions for knowledge distillation: a Group-P shuffling strategy as an implicit regularization and the averaging logits from multiple teacher components. Experiments on standard benchmarks demonstrate that the proposed DistillCSE outperforms many strong baseline methods and yields a new state-of-the-art performance.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2310.13499")
get_code_for_paper("2310.13499")
have("2310.13499")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2310.13499.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2310.13499.svg)](https://syntology.ai/paper/2310.13499)

Connect an agent — have() is free.