Towards Interaction Detection Using Topological Analysis on Neural Networks
arXiv:2010.13015
Abstract
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.
References in corpus (5)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Predictive learning via rule ensembles
- Feature Engineering for Predictive Modeling using Reinforcement Learning
- Take it in your stride: Do we need striding in CNNs?
- Feature Interaction Interpretability: A Case for Explaining Ad-Recommendation Systems via Neural Interaction Detection