Papers Read on AI

Papers Read on AI header image 1
August 2, 2022  

OpenXAI: Towards a Transparent Evaluation of Model Explanations

August 2, 2022

While several types of post hoc explanation methods (e.g., feature attribution methods) have been proposed in recent literature, there is little to no work on systematically benchmarking these methods in an efficient and transparent manner. Here, we introduce OpenXAI, a comprehensive and extensible opensource framework for evaluating and benchmarking post hoc explanation methods. OpenXAI comprises of the following key components: (i) a flexible synthetic data generator and a collection of diverse real-world datasets, pre-trained models, and state-of-the-art feature attribution methods, (ii) open-source implementations of twenty-two quantitative metrics for evaluating faithfulness, stability (robustness), and fairness of explanation methods, and (iii) the first ever public XAI leaderboards to benchmark explanations. OpenXAI is easily extensible, as users can readily evaluate custom explanation methods and incorporate them into our leaderboards. Overall, OpenXAI provides an automated end-to-end pipeline that not only simplifies and standardizes the evaluation of post hoc explanation methods, but also promotes transparency and reproducibility in benchmarking these methods. OpenXAI datasets and data loaders, implementations of state-of-the-art explanation methods and evaluation metrics, as well as leaderboards are publicly available at https://open-xai.github.io/.

2022: Chirag Agarwal, Eshika Saxena, Satyapriya Krishna, Martin Pawelczyk, Nari Johnson, I. Puri, M. Zitnik, Himabindu Lakkaraju

https://arxiv.org/pdf/2206.11104v1.pdf