A Robust Prototype-Based Network with Interpretable RBF Classifier Foundations

2024-12-20

arXiv.org

AI Summary

Existing deep prototype-based networks (e.g., CBC) achieve strong performance but suffer from interpretability contradictions, insufficient robustness, and a theoretical disconnect between shallow and deep models. Method: This paper proposes a unified robust and interpretable prototype classification framework. First, it establishes a rigorous equivalence between deep prototype networks and radial basis function (RBF) classifiers, bridging the theoretical gap. Second, it introduces the first prototype learning mechanism with provable ℓ₂-robustness guarantees. Third, it jointly employs probabilistic modeling and robust optimization to eliminate interpretability conflicts. Contributions/Results: The deep variant achieves state-of-the-art accuracy across multiple benchmarks; the shallow variant retains full interpretability while significantly outperforming comparable methods and providing certified ℓ₂-robustness—thereby unifying performance, interpretability, and robustness within a single principled framework.

Technology Category

• Machine Learning: Adversarial Learning & Robustness
• Computer Vision: Interpretability, Explainability, and Transparency
• Natural Language Processing: Safety and Robustness

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

Abstract

Prototype-based classification learning methods are known to be inherently interpretable. However, this paradigm suffers from major limitations compared to deep models, such as lower performance. This led to the development of the so-called deep Prototype-Based Networks (PBNs), also known as prototypical parts models. In this work, we analyze these models with respect to different properties, including interpretability. In particular, we focus on the Classification-by-Components (CBC) approach, which uses a probabilistic model to ensure interpretability and can be used as a shallow or deep architecture. We show that this model has several shortcomings, like creating contradicting explanations. Based on these findings, we propose an extension of CBC that solves these issues. Moreover, we prove that this extension has robustness guarantees and derive a loss that optimizes robustness. Additionally, our analysis shows that most (deep) PBNs are related to (deep) RBF classifiers, which implies that our robustness guarantees generalize to shallow RBF classifiers. The empirical evaluation demonstrates that our deep PBN yields state-of-the-art classification accuracy on different benchmarks while resolving the interpretability shortcomings of other approaches. Further, our shallow PBN variant outperforms other shallow PBNs while being inherently interpretable and exhibiting provable robustness guarantees.

Problem

• Deep Prototype Base Networks
• Interpretability Issues
• Model Stability

Innovation

• Improved Component-Based Classification
• Depth Prototype Base Networks
• Enhanced Stability and Explainability