Explaining Generalization Power of a DNN Using Interactive Concepts

This paper explains the generalization power of a deep neural network (DNN) from the perspective of interactions. Although there is no universally accepted definition of the concepts encoded by a DNN, the sparsity of interactions in a DNN has been proved, i.e., the output score of a DNN can be well explained by a small number of interactions between input variables. In this way, to some extent, we can consider such interactions as interactive concepts encoded by the DNN. Therefore, in this paper, we derive an analytic explanation of inconsistency of concepts of different complexities. This may shed new lights on using the generalization power of concepts to explain the generalization power of the entire DNN. Besides, we discover that the DNN with stronger generalization power usually learns simple concepts more quickly and encodes fewer complex concepts. We also discover the detouring dynamics of learning complex concepts, which explains both the high learning difficulty and the low generalization power of complex concepts. The code will be released when the paper is accepted.

Authors

• Huilin Zhou Shanghai Jiao Tong University
• Hao Zhang vivo Mobile Communication Co., Ltd
• Huiqi Deng Shanghai Jiao Tong University
• Dongrui Liu Shanghai Jiao Tong University
• Wen Shen
• Shih-Han Chan Shanghai Jiao Tong University University of California San Diego
• Quanshi Zhang Shanghai Jiao Tong University

Keywords

• ML: Transparent, Interpretable, Explainable ML