Knowledge Transfer Graph for Deep Collaborative Learning

By Soma Minami, Tsubasa Hirakawa, Takayoshi Yamashita, Hironobu Fujiyoshi. 2019

13 citations recorded by the source corpus.

Knowledge transfer among multiple networks using their outputs or intermediate activations have evolved through extensive manual design from a simple teacher-student approach (knowledge distillation) to a bidirectional cohort one (deep mutual learning). The key factors of such knowledge transfer involve the network size, the number of networks, the transfer direction, and the design of the loss function. However, because these factors are enormous when combined and become intricately entangled, the methods of conventional knowledge transfer have explored only limited combinations. In this paper, we propose a new graph-based approach for more flexible and diverse combinations of knowledge transfer. To achieve the knowledge transfer, we propose a novel graph representation called knowledge transfer graph that provides a unified view of the knowledge transfer and has the potential to represent diverse knowledge transfer patterns. We also propose four gate functions that are introduced into loss functions. The four gates, which control the gradient, can deliver diverse combinations of knowledge transfer. Searching the graph structure enables us to discover more effective knowledge transfer methods than a manually designed one. Experimental results on the CIFAR-10, -100, and Tiny-ImageNet datasets show that the proposed method achieved significant performance improvements and was able to find remarkable graph structures.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Dacheng Tao
2. Jianping Gou
3. S. Maybank
4. Baosheng Yu
5. Lin Wang
6. Kuk-Jin Yoon
7. Gabriella Csurka
8. Jing Zhang

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Jianping Gou
3. S. Maybank
4. Lin Wang
5. Kuk-Jin Yoon
6. Baosheng Yu
7. Luc Van Gool
8. Trevor Darrell

Citations in the corpus

• Knowledge Distillation: A Survey (2020, background): “A bidirectional graph-based diverse collaborative learning was proposed to explore diverse knowledge transfer patterns by (Minami et al., 2019).”
• Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks (2020, methodology): “Regarding using S-T structures for KD, to date, there are several works such as [173, 207, 208, 212, 213, 214, 215, 218].”