Part of Advances in Neural Information Processing Systems 36 (NeurIPS 2023) Main Conference Track
Anton Xue, Rajeev Alur, Eric Wong
Explanation methods for machine learning models tend not to provide any formal guarantees and may not reflect the underlying decision-making process.In this work, we analyze stability as a property for reliable feature attribution methods. We prove that relaxed variants of stability are guaranteed if the model is sufficiently Lipschitz with respect to the masking of features. We develop a smoothing method called Multiplicative Smoothing (MuS) to achieve such a model.We show that MuS overcomes the theoretical limitations of standard smoothing techniques and can be integrated with any classifier and feature attribution method.We evaluate MuS on vision and language models with various feature attribution methods, such as LIME and SHAP, and demonstrate that MuS endows feature attributions with non-trivial stability guarantees.