Suboptimal Shapley Value Explanations
This work addresses a specific bottleneck in explainable AI for researchers and practitioners, but it is incremental as it builds on existing Shapley value methods.
The paper tackles the problem of suboptimal baseline selection in Shapley value explanations for deep neural networks, which can negatively influence feature importance analysis, and proposes an uncertainty-based reweighting mechanism that shows effectiveness in experiments on NLP tasks.
Deep Neural Networks (DNNs) have demonstrated strong capacity in supporting a wide variety of applications. Shapley value has emerged as a prominent tool to analyze feature importance to help people understand the inference process of deep neural models. Computing Shapley value function requires choosing a baseline to represent feature's missingness. However, existing random and conditional baselines could negatively influence the explanation. In this paper, by analyzing the suboptimality of different baselines, we identify the problematic baseline where the asymmetric interaction between $\bm{x}'_i$ (the replacement of the faithful influential feature) and other features has significant directional bias toward the model's output, and conclude that $p(y|\bm{x}'_i) = p(y)$ potentially minimizes the asymmetric interaction involving $\bm{x}'_i$. We further generalize the uninformativeness of $\bm{x}'_i$ toward the label space $L$ to avoid estimating $p(y)$ and design a simple uncertainty-based reweighting mechanism to accelerate the computation process. We conduct experiments on various NLP tasks and our quantitative analysis demonstrates the effectiveness of the proposed uncertainty-based reweighting mechanism. Furthermore, by measuring the consistency of explanations generated by explainable methods and human, we highlight the disparity between model inference and human understanding.