awesome-XAI: A Curated Collection of XAI Resources

Introduction

Welcome to awesome-XAI, a comprehensive repository dedicated to the dynamic and evolving field of Explainable Artificial Intelligence (XAI). This project is a curated list of influential papers, cutting-edge libraries, and valuable resources aimed at researchers, practitioners, and enthusiasts in XAI.

What is XAI?

Explainable Artificial Intelligence (XAI) is a branch of AI focused on making the decision-making processes of AI systems transparent and understandable to humans. This field addresses the growing need for accountability and comprehensibility in AI systems, especially in critical applications like healthcare, finance, and autonomous vehicles.

Features

• Research Papers: A selection of seminal and recent papers in XAI, categorized by themes such as interpretability methods, case studies, ethical implications, and more.
• Libraries and Tools: Links to open-source libraries and tools that are useful for implementing XAI methods in various programming languages.
• Tutorials and Guides: Step-by-step tutorials and comprehensive guides for beginners and advanced users alike.
• Community Contributions: A section for community-contributed resources, discussions, and collaborations.

Papers

Adadi and M. Berrada, ‘‘Peeking inside the black-box: A survey on explainable artificial intelligence (XAI),’’ IEEE Access, vol. 6, pp. 52138–52160, 2018, doi: 10.1109/ACCESS.2018.2870052.

Gilpin, Leilani H., et al. "Explaining explanations: An overview of interpretability of machine learning." 2018 IEEE 5th International Conference on data science and advanced analytics (DSAA). IEEE, 2018.

W James Murdoch, Chandan Singh, Karl Kumbier, Reza Abbasi-Asl, and Bin Yu. 2019. Definitions, methods, and applications in interpretable machine learning. Proceedings of the National Academy of Sciences 116, 44 (2019), 22071 – 22080.

Deng, Houtao. "Interpreting tree ensembles with intrees." International Journal of Data Science and Analytics 7.4 (2019): 277-287.

Molnar, Christoph. Interpretable machine learning. Lulu. com, 2020.

G. Vilone and L. Longo, ‘‘Explainable artificial intelligence: A systematic review,’’ May 2020, arXiv:2006.00093.

Tian, Yue, and Guanjun Liu. "MANE: Model-agnostic non-linear explanations for deep learning model." 2020 IEEE World Congress on Services (SERVICES). IEEE, 2020.

Ullah, Ihsan, et al. "Explaining deep learning models for tabular data using layer-wise relevance propagation." Applied Sciences 12.1 (2021): 136.

Hu, Zhongli Filippo, et al. "Recent studies of xai-review." Adjunct Proceedings of the 29th ACM Conference on User Modeling, Adaptation and Personalization. 2021.

Darias, Jesus M., Belén Díaz-Agudo, and Juan A. Recio-Garcia. "A Systematic Review on Model-agnostic XAI Libraries." ICCBR Workshops. 2021

K. Dedja, F. K. Nakano, K. Pliakos, and C. Vens, ‘‘BELLATREX: Building explanations through a locally accurate rule extractor,’’ Mar. 2022, arXiv:2203.15511.

XAI in Finance

Bussmann, Niklas, et al. "Explainable machine learning in credit risk management." Computational Economics 57 (2021): 203-216.

Hashemi, Masoud, and Ali Fathi. "Permuteattack: Counterfactual explanation of machine learning credit scorecards." arXiv preprint arXiv:2008.10138 (2020).

Dastile, Xolani, Turgay Celik, and Hans Vandierendonck. "Model-agnostic counterfactual explanations in credit scoring." IEEE Access 10 (2022): 69543-69554.

La Gatta, Valerio, et al. "PASTLE: Pivot-aided space transformation for local explanations." Pattern Recognition Letters 149 (2021): 67-74.

La Gatta, Valerio, et al. "CASTLE: Cluster-aided space transformation for local explanations." Expert Systems with Applications 179 (2021): 115045.

Martins, Tiago, et al. "Explainable Artificial Intelligence (XAI): a Systematic Literature Review on Taxonomies and Applications in Finance." IEEE Access (2023).

Libraries

Interpret

Fit interpretable models. Explain blackbox machine learning.

alibi

Algorithms for explaining machine learning models

AIX360

Interpretability and explainability of data and machine learning models

DALEX

moDel Agnostic Language for Exploration and eXplanation

DiCE

Generate Diverse Counterfactual Explanations for any machine learning model.

causalml

Uplift modeling and causal inference with machine learning algorithms

loom

A tree-based writing interface for GPT-3, visualizing the probability mass distribution of the future multiverse predicted by a language model conditioned on a prompt.

License

This project is licensed under the MIT License. For more details, see the LICENSE file in the repository.

Acknowledgments

Special thanks to the contributors, researchers, and practitioners who have made this project possible. Your dedication to advancing the field of XAI is deeply appreciated.