Uncertainty-Aware Explanations Through Probabilistic Self-Explainable Neural Networks

2024-03-20

arXiv.org

AI Summary

The black-box nature of deep neural networks hinders their trustworthy deployment in high-stakes applications. To address this, we propose Probabilistic Prototype-based Self-Explaining Neural Networks (Prob-PSENN), the first framework to elevate prototype learning from point estimation to a probabilistic modeling paradigm: prototypes are represented as distributions rather than fixed points, enabling joint optimization of prediction and explanation while explicitly quantifying explanation uncertainty. Our method integrates probabilistic deep learning, end-to-end differentiable prototype optimization, and Bayesian principles to identify uncertain predictions and provide calibrated, interpretable feedback. Evaluated on multiple benchmarks, Prob-PSENN generates more robust and semantically coherent explanations than deterministic counterparts, achieves predictive accuracy on par with non-probabilistic PSENN, and significantly enhances model trustworthiness and decision transparency in safety-critical domains.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Probabilistic Programming
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs

Abstract

The lack of transparency of Deep Neural Networks continues to be a limitation that severely undermines their reliability and usage in high-stakes applications. Promising approaches to overcome such limitations are Prototype-Based Self-Explainable Neural Networks (PSENNs), whose predictions rely on the similarity between the input at hand and a set of prototypical representations of the output classes, offering therefore a deep, yet transparent-by-design, architecture. In this paper, we introduce a probabilistic reformulation of PSENNs, called Prob-PSENN, which replaces point estimates for the prototypes with probability distributions over their values. This provides not only a more flexible framework for an end-to-end learning of prototypes, but can also capture the explanatory uncertainty of the model, which is a missing feature in previous approaches. In addition, since the prototypes determine both the explanation and the prediction, Prob-PSENNs allow us to detect when the model is making uninformed or uncertain predictions, and to obtain valid explanations for them. Our experiments demonstrate that Prob-PSENNs provide more meaningful and robust explanations than their non-probabilistic counterparts, while remaining competitive in terms of predictive performance, thus enhancing the explainability and reliability of the models.

Problem

• Improving transparency in Deep Neural Networks
• Introducing uncertainty in model explanations
• Enhancing reliability of high-stakes applications

Innovation

• Probabilistic Self-Explainable Neural Networks
• Uncertainty-aware model explanations
• End-to-end prototype learning framework