ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability

TL;DR

The paper introduces ABE, a comprehensive framework that unifies and enhances attribution-based explainability for deep learning models, addressing scalability and usability issues of existing methods.

Contribution

It formalizes Fundamental Attribution Methods, integrates advanced algorithms, and offers a customizable, scalable platform for developing and validating attribution techniques.

Findings

Provides a scalable, extensible framework for attribution methods

Ensures compliance with attribution axioms

Facilitates development of novel attribution techniques

Abstract

Attribution algorithms are essential for enhancing the interpretability and trustworthiness of deep learning models by identifying key features driving model decisions. Existing frameworks, such as InterpretDL and OmniXAI, integrate multiple attribution methods but suffer from scalability limitations, high coupling, theoretical constraints, and lack of user-friendly implementations, hindering neural network transparency and interoperability. To address these challenges, we propose Attribution-Based Explainability (ABE), a unified framework that formalizes Fundamental Attribution Methods and integrates state-of-the-art attribution algorithms while ensuring compliance with attribution axioms. ABE enables researchers to develop novel attribution techniques and enhances interpretability through four customizable modules: Robustness, Interpretability, Validation, and Data & Model. This framework provides a scalable, extensible foundation for advancing attribution-based explainability and fostering transparent AI systems. Our code is available at: https://github.com/LMBTough/ABE-XAI.