Enhancing Logits Distillation with Plug&Play Kendall’s $τ$ Ranking Loss

Yuchen Guan; Runxi Cheng; Kang Liu; Chun Yuan

2025 ICML ICML 2025

Enhancing Logits Distillation with Plug&Play Kendall’s $τ$ Ranking Loss

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Yuchen Guan, Runxi Cheng, Kang Liu, Chun Yuan

Topics

Artificial Intelligence > Core AI > Model Compression Machine Learning > Optimization & Theory > Neural Network Optimization Deep Learning > Optimization & Theory > Optimization

Keywords

ranking loss teacher logit gradient scaling logits distillation kendall's tau inter-class information

Download PDF