Detecting Statistical Interactions from Neural Network Weights
Interpreting deep neural networks can enable new applications for predictive modeling where both accuracy and interpretability are required. In this paper, we examine the weights of a deep neural network to interpret the statistical interactions it captures. Our key observation is that any input features that interact with each other must follow strongly weighted paths to a common hidden unit before the final output. We propose a novel framework, which we call Neural Interaction Detector (NID), that identifies meaningful interactions of arbitrary-order without an exhaustive search on an exponential solution space of interaction candidates. Empirical evaluation on both synthetic and real-world data showed the effectiveness of NID, which detects interactions more accurately and efficiently than does the state-of-the-art.
READ FULL TEXT