Graph-based Knowledge Distillation by Multi-head Attention Network

TL;DR

This paper introduces a novel graph-based knowledge distillation method using multi-head attention to transfer dataset-level knowledge from a teacher to a student network, improving performance significantly.

Contribution

It proposes a new KD approach that distills dataset-based knowledge via multi-head attention, capturing intra-data relations for better student performance.

Findings

Achieved 7.05% higher accuracy on CIFAR100 compared to student alone.

Outperformed state-of-the-art methods by 2.46%.

Demonstrated effectiveness of dataset-level knowledge distillation.

Abstract

Knowledge distillation (KD) is a technique to derive optimal performance from a small student network (SN) by distilling knowledge of a large teacher network (TN) and transferring the distilled knowledge to the small SN. Since a role of convolutional neural network (CNN) in KD is to embed a dataset so as to perform a given task well, it is very important to acquire knowledge that considers intra-data relations. Conventional KD methods have concentrated on distilling knowledge in data units. To our knowledge, any KD methods for distilling information in dataset units have not yet been proposed. Therefore, this paper proposes a novel method that enables distillation of dataset-based knowledge from the TN using an attention network. The knowledge of the embedding procedure of the TN is distilled to graph by multi-head attention (MHA), and multi-task learning is performed to give relational inductive bias to the SN. The MHA can provide clear information about the source dataset, which can greatly improves the performance of the SN. Experimental results show that the proposed method is 7.05% higher than the SN alone for CIFAR100, which is 2.46% higher than the state-of-the-art.