Interpreting Multivariate Shapley Interactions in DNNs
It addresses interpretability for AI researchers and practitioners, but appears incremental as it builds on existing Shapley-based attribution methods.
The paper tackles the problem of explaining deep neural networks by defining and quantifying multivariate interactions among input variables using Shapley values, with experiments showing the method's effectiveness.
This paper aims to explain deep neural networks (DNNs) from the perspective of multivariate interactions. In this paper, we define and quantify the significance of interactions among multiple input variables of the DNN. Input variables with strong interactions usually form a coalition and reflect prototype features, which are memorized and used by the DNN for inference. We define the significance of interactions based on the Shapley value, which is designed to assign the attribution value of each input variable to the inference. We have conducted experiments with various DNNs. Experimental results have demonstrated the effectiveness of the proposed method.