Graph-based Knowledge Distillation by Multi-head Attention Network

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.

Accepted to BMVC 2019 as an oral presentation

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• Distilling the Knowledge in a Neural Network
• FitNets: Hints for Thin Deep Nets
• Wide Residual Networks
• Low-resolution Face Recognition in the Wild via Selective Knowledge Distillation
• Long Short-Term Memory-Networks for Machine Reading
• Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons

Cited by in corpus (11)

• Knowledge Distillation: A Survey
• Compacting Deep Neural Networks for Internet of Things: Methods and Applications
• Convolutional Fine-Grained Classification with Self-Supervised Target Relation Regularization
• A Survey on Symbolic Knowledge Distillation of Large Language Models
• Role-Wise Data Augmentation for Knowledge Distillation
• Semi-Supervised Domain Generalizable Person Re-Identification
• Collaborative Distillation in the Parameter and Spectrum Domains for Video Action Recognition
• Knowledge Distillation in Wide Neural Networks: Risk Bound, Data Efficiency and Imperfect Teacher
• Interactive Knowledge Distillation
• Matching Guided Distillation
• Partial to Whole Knowledge Distillation: Progressive Distilling Decomposed Knowledge Boosts Student Better