Self-learn to Explain Siamese Networks Robustly

Abstract

Learning to compare two objects are essential in applications, such as digital forensics, face recognition, and brain network analysis, especially when labeled data is scarce and imbalanced. As these applications make high-stake decisions and involve societal values like fairness and transparency, it is critical to explain the learned models. We aim to study post-hoc explanations of Siamese networks (SN) widely used in learning to compare. We characterize the instability of gradient-based explanations due to the additional compared object in SN, in contrast to architectures with a single input instance. We propose an optimization framework that derives global invariance from unlabeled data using self-learning to promote the stability of local explanations tailored for specific query-reference pairs. The optimization problems can be solved using gradient descent-ascent (GDA) for constrained optimization, or SGD for KL-divergence regularized unconstrained optimization, with convergence proofs, especially when the objective functions are nonconvex due to the Siamese architecture. Quantitative results and case studies on tabular and graph data from neuroscience and chemical engineering show that the framework respects the self-learned invariance while robustly optimizing the faithfulness and simplicity of the explanation. We further demonstrate the convergence of GDA experimentally.

arXiv commentAccepted to ICDM 2021

References in corpus (10)

• European Union regulations on algorithmic decision-making and a "right to explanation"
• Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
• Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Actionable Recourse in Linear Classification
• "Why Should I Trust You?": Explaining the Predictions of Any Classifier
• SigNet: Convolutional Siamese Network for Writer Independent Offline Signature Verification
• Self-supervised Learning on Graphs: Deep Insights and New Direction
• Interpretable Credit Application Predictions With Counterfactual Explanations
• Contrastive Graph Neural Network Explanation