Alert button
Picture for Ting Hsiang Wang

Ting Hsiang Wang

Alert button

Towards Interaction Detection Using Topological Analysis on Neural Networks

Nov 04, 2020
Zirui Liu, Qingquan Song, Kaixiong Zhou, Ting Hsiang Wang, Ying Shan, Xia Hu

Figure 1 for Towards Interaction Detection Using Topological Analysis on Neural Networks
Figure 2 for Towards Interaction Detection Using Topological Analysis on Neural Networks
Figure 3 for Towards Interaction Detection Using Topological Analysis on Neural Networks
Figure 4 for Towards Interaction Detection Using Topological Analysis on Neural Networks

Detecting statistical interactions between input features is a crucial and challenging task. Recent advances demonstrate that it is possible to extract learned interactions from trained neural networks. It has also been observed that, in neural networks, any interacting features must follow a strongly weighted connection to common hidden units. Motivated by the observation, in this paper, we propose to investigate the interaction detection problem from a novel topological perspective by analyzing the connectivity in neural networks. Specially, we propose a new measure for quantifying interaction strength, based upon the well-received theory of persistent homology. Based on this measure, a Persistence Interaction detection~(PID) algorithm is developed to efficiently detect interactions. Our proposed algorithm is evaluated across a number of interaction detection tasks on several synthetic and real world datasets with different hyperparameters. Experimental results validate that the PID algorithm outperforms the state-of-the-art baselines.

Viaarxiv icon