ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909606258671616 |
|---|---|
| author | Zhu, Zhiyu Zhang, Jiayu Jin, Zhibo Chen, Fang Zhou, Jianlong |
| author_facet | Zhu, Zhiyu Zhang, Jiayu Jin, Zhibo Chen, Fang Zhou, Jianlong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06258 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability Zhu, Zhiyu Zhang, Jiayu Jin, Zhibo Chen, Fang Zhou, Jianlong Machine Learning Artificial Intelligence 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. |
| title | ABE: A Unified Framework for Robust and Faithful Attribution-Based Explainability |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2505.06258 |