# Efficient and Robust Knowledge Distillation from A Stronger Teacher Based on Correlation Matching

Source: [Efficient and Robust Knowledge Distillation from A Stronger Teacher Based on Correlation Matching](<https://www.sota2.com/research/paper/68fa75241e209131cea661c9>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T03:27:16.108Z

Authors: Wenqi Niu, Yingchao Wang, Guohui Cai, Hanpo Hou

Published: 2024-10-09T05:42:47.000Z

## Abstract

Knowledge Distillation (KD) has emerged as a pivotal technique for neural network compression and performance enhancement. Most KD methods aim to transfer dark knowledge from a cumbersome teacher model to a lightweight student model based on Kullback-Leibler (KL) divergence loss. However, the student performance improvements achieved through KD exhibit diminishing marginal returns, where a stronger teacher model does not necessarily lead to a proportionally stronger student model. To address this issue, we empirically find that the KL-based KD method may implicitly change the inter-class relationships learned by the student model, resulting in a more complex and ambiguous decision boundary, which in turn reduces the model's accuracy and generalization ability. Therefore, this study argues that the student model should learn not only the probability values from the teacher's output but also the relative ranking of classes, and proposes a novel Correlation Matching Knowledge Distillation (CMKD) method that combines the Pearson and Spearman correlation coefficients-based KD loss to achieve more efficient and robust distillation from a stronger teacher model. Moreover, considering that samples vary in difficulty, CMKD dynamically adjusts the weights of the Pearson-based loss and Spearman-based loss. CMKD is simple yet practical, and extensive experiments demonstrate that it can consistently achieve state-of-the-art performance on CIRAR-100 and ImageNet, and adapts well to various teacher architectures, sizes, and other KD methods.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2410.06561>)

[PDF](<https://arxiv.org/pdf/2410.06561.pdf>)
