Timezone: »

 
Poster
OpenXAI: Towards a Transparent Evaluation of Model Explanations
Chirag Agarwal · Satyapriya Krishna · Eshika Saxena · Martin Pawelczyk · Nari Johnson · Isha Puri · Marinka Zitnik · Himabindu Lakkaraju

Wed Nov 30 02:00 PM -- 04:00 PM (PST) @ Hall J #1013
in Poster Session 4 »

While several types of post hoc explanation methods have been proposed in recent literature, there is very little work on systematically benchmarking these methods. Here, we introduce OpenXAI, a comprehensive and extensible open-source 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 readily compare several explanation methods across a wide variety of metrics, models, and datasets. 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. While the first release of OpenXAI supports only tabular datasets, the explanation methods and metrics that we consider are general enough to be applicable to other data modalities. 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/. OpenXAI will be regularly updated to incorporate text and image datasets, other new metrics and explanation methods, and welcomes inputs from the community.

Keywords: Evaluation · Explainable Artificial Intelligence · benchmark · leaderboard
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Chirag Agarwal (Harvard University/Adobe)
Satyapriya Krishna (Harvard University)
Eshika Saxena (Harvard University)
Martin Pawelczyk (University of Tübingen)

# Academic Exp ## Phd Student at Uni of Tübingen, Germany: ## MSc Statistics, London School of Economics, UK ## MSc Econometrics, University of Edinburgh, UK ## BSc Economics, University of Cologne, Germany # Work Exp ## ML intern at SDG financing Lab, OECD, Paris ## Working student at r2b energy consulting, Cologne

Nari Johnson (CMU, Carnegie Mellon University)
Isha Puri (Harvard University)
Marinka Zitnik (Harvard University)
Himabindu Lakkaraju (Harvard)

More from the Same Authors