Explaining Explanations: Axiomatic Feature Interactions for Deep Networks
This work addresses the need for deeper insights into model behavior for researchers and practitioners in machine learning, though it is incremental as it builds on existing feature attribution methods.
The authors tackled the problem of explaining neural network behavior by developing Integrated Hessians, a method that explains pairwise feature interactions, which overcomes theoretical limitations of previous methods and is not limited to specific architectures. The result shows that their method is faster for large feature sets and outperforms previous methods on quantitative benchmarks.
Recent work has shown great promise in explaining neural network behavior. In particular, feature attribution methods explain which features were most important to a model's prediction on a given input. However, for many tasks, simply knowing which features were important to a model's prediction may not provide enough insight to understand model behavior. The interactions between features within the model may better help us understand not only the model, but also why certain features are more important than others. In this work, we present Integrated Hessians, an extension of Integrated Gradients that explains pairwise feature interactions in neural networks. Integrated Hessians overcomes several theoretical limitations of previous methods to explain interactions, and unlike such previous methods is not limited to a specific architecture or class of neural network. Additionally, we find that our method is faster than existing methods when the number of features is large, and outperforms previous methods on existing quantitative benchmarks. Code available at https://github.com/suinleelab/path_explain