Technology Category
Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP ModelsComputer Vision: Interpretability, Explainability, and TransparencyMachine Learning: Multimodal Learning
A Comprehensive Survey on Self-Interpretable Neural Networks
🤖 AI Summary
Neural networks suffer from limited interpretability, hindering their adoption in high-stakes decision-making. To address this, we present a systematic survey of self-interpretable neural networks (SINNs) and propose the first five-dimensional taxonomy—covering attribution-, function-, concept-, prototype-, and rule-based approaches—unified across multimodal domains including vision, natural language processing, graph learning, and deep reinforcement learning. Methodologically, we establish a structured framework for SINN design and evaluation, introduce the first open-source tracking repository (Awesome-Self-Interpretable-Neural-Network), and rigorously define evaluation metrics and fundamental open challenges. Through comprehensive literature analysis, modeling abstraction, visual case studies, and cross-domain validation, we deliver a reproducible interpretability paradigm and practical implementation guidelines. Our work bridges the gap between theoretical SINN design and trustworthy real-world deployment.
Technology Category
Application Category
📝 Abstract
Neural networks have achieved remarkable success across various fields. However, the lack of interpretability limits their practical use, particularly in critical decision-making scenarios. Post-hoc interpretability, which provides explanations for pre-trained models, is often at risk of robustness and fidelity. This has inspired a rising interest in self-interpretable neural networks, which inherently reveal the prediction rationale through the model structures. Although there exist surveys on post-hoc interpretability, a comprehensive and systematic survey of self-interpretable neural networks is still missing. To address this gap, we first collect and review existing works on self-interpretable neural networks and provide a structured summary of their methodologies from five key perspectives: attribution-based, function-based, concept-based, prototype-based, and rule-based self-interpretation. We also present concrete, visualized examples of model explanations and discuss their applicability across diverse scenarios, including image, text, graph data, and deep reinforcement learning. Additionally, we summarize existing evaluation metrics for self-interpretability and identify open challenges in this field, offering insights for future research. To support ongoing developments, we present a publicly accessible resource to track advancements in this domain: https://github.com/yangji721/Awesome-Self-Interpretable-Neural-Network.
Problem
Research questions and friction points this paper is trying to address.
Interpretable Neural Networks
Explainable AI
Critical Decision Making
Innovation
Methods, ideas, or system contributions that make the work stand out.
Self-explaining neural networks
Multidimensional interpretability
Visualisation and application in diverse domains
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
