Timezone: »
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.
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
-
2021 : CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms »
Martin Pawelczyk · Sascha Bielawski · Johan Van den Heuvel · Tobias Richter · Gjergji Kasneci -
2022 : Structure-Inducing Pre-training »
Matthew McDermott · Brendan Yap · Peter Szolovits · Marinka Zitnik -
2022 : I Prefer not to Say – Operationalizing Fair and User-guided Data Minimization »
Tobias Leemann · Martin Pawelczyk · Christian Eberle · Gjergji Kasneci -
2022 : Trajectory-based Explainability Framework for Offline RL »
Shripad Deshmukh · Arpan Dasgupta · Chirag Agarwal · Nan Jiang · Balaji Krishnamurthy · Georgios Theocharous · Jayakumar Subramanian -
2022 : On the Trade-Off between Actionable Explanations and the Right to be Forgotten »
Martin Pawelczyk · Tobias Leemann · Asia Biega · Gjergji Kasneci -
2022 : TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations »
Dylan Slack · Satyapriya Krishna · Himabindu Lakkaraju · Sameer Singh -
2022 : On the Impact of Adversarially Robust Models on Algorithmic Recourse »
Satyapriya Krishna · Chirag Agarwal · Himabindu Lakkaraju -
2023 : Are Large Language Models Post Hoc Explainers? »
Nicholas Kroeger · Dan Ley · Satyapriya Krishna · Chirag Agarwal · Himabindu Lakkaraju -
2023 : Mapping the intermolecular interaction universe through self-supervised learning on molecular crystals »
Ada Fang · Ada Fang · ZAIXI ZHANG · Marinka Zitnik · Marinka Zitnik -
2023 : A Study on the Calibration of In-context Learning »
Hanlin Zhang · yifan zhang · Yaodong Yu · Eric Xing · Himabindu Lakkaraju · Sham Kakade -
2023 : Uncertainty In Natural Language Explanations Of Large Language Models »
Sree Harsha Tanneru · Chirag Agarwal · Himabindu Lakkaraju -
2023 : Are Large Language Models Post Hoc Explainers? »
Nicholas Kroeger · Dan Ley · Satyapriya Krishna · Chirag Agarwal · Himabindu Lakkaraju -
2023 : Uncertainty In Natural Language Explanations Of Large Language Models »
Sree Harsha Tanneru · Chirag Agarwal · Himabindu Lakkaraju -
2023 : Investigating the Fairness of Large Language Models for Predictions on Tabular Data »
Yanchen Liu · Srishti Gautam · Jiaqi Ma · Himabindu Lakkaraju -
2023 : Assessing AI Impact Assessments: A Classroom Study »
Nari Johnson · Hoda Heidari -
2023 : Keynote: Marinka Zitnik »
Marinka Zitnik -
2023 Workshop: Regulatable ML: Towards Bridging the Gaps between Machine Learning Research and Regulations »
Jiaqi Ma · Danielle Belgrave · P-R Stark · Daniele Magazzeni · Himabindu Lakkaraju · Junwei Deng · Usha Bhalla · Sarah Tan · Chirag Agarwal -
2023 Workshop: XAI in Action: Past, Present, and Future Applications »
Chhavi Yadav · Michal Moshkovitz · Nave Frost · Suraj Srinivas · Bingqing Chen · Valentyn Boreiko · Himabindu Lakkaraju · J. Zico Kolter · Dotan Di Castro · Kamalika Chaudhuri -
2023 Workshop: AI for Science: from Theory to Practice »
Yuanqi Du · Max Welling · Yoshua Bengio · Marinka Zitnik · Carla Gomes · Jure Leskovec · Maria Brbic · Wenhao Gao · Kexin Huang · Ziming Liu · Rocío Mercado · Miles Cranmer · Shengchao Liu · Lijing Wang -
2023 Poster: Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency »
Owen Queen · Tom Hartvigsen · Teddy Koker · Huan He · Theodoros Tsiligkaridis · Marinka Zitnik -
2023 Poster: $\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models »
Xuhong Li · Mengnan Du · Jiamin Chen · Yekun Chai · Himabindu Lakkaraju · Haoyi Xiong -
2023 Poster: Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability »
Usha Bhalla · Suraj Srinivas · Himabindu Lakkaraju -
2023 Poster: Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness »
Suraj Srinivas · Sebastian Bordt · Himabindu Lakkaraju -
2023 Poster: Full-Atom Protein Pocket Design via Iterative Refinement »
ZAIXI ZHANG · Zepu Lu · Hao Zhongkai · Marinka Zitnik · Qi Liu -
2023 Poster: Post Hoc Explanations of Language Models Can Improve Language Models »
Satyapriya Krishna · Jiaqi Ma · Dylan Slack · Asma Ghandeharioun · Sameer Singh · Himabindu Lakkaraju -
2023 Poster: Gaussian Membership Inference Privacy »
Tobias Leemann · Martin Pawelczyk · Gjergji Kasneci -
2022 : Contributed Talk: TalkToModel: Explaining Machine Learning Models with Interactive Natural Language Conversations »
Dylan Slack · Satyapriya Krishna · Himabindu Lakkaraju · Sameer Singh -
2022 : Keynote »
Marinka Zitnik -
2022 Workshop: New Frontiers in Graph Learning »
Jiaxuan You · Marinka Zitnik · Rex Ying · Yizhou Sun · Hanjun Dai · Stefanie Jegelka -
2022 Workshop: AI for Science: Progress and Promises »
Yi Ding · Yuanqi Du · Tianfan Fu · Hanchen Wang · Anima Anandkumar · Yoshua Bengio · Anthony Gitter · Carla Gomes · Aviv Regev · Max Welling · Marinka Zitnik -
2022 Poster: Use-Case-Grounded Simulations for Explanation Evaluation »
Valerie Chen · Nari Johnson · Nicholay Topin · Gregory Plumb · Ameet Talwalkar -
2022 Poster: Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency »
Xiang Zhang · Ziyuan Zhao · Theodoros Tsiligkaridis · Marinka Zitnik -
2022 Poster: Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanations »
Tessa Han · Suraj Srinivas · Himabindu Lakkaraju -
2022 Poster: Efficient Training of Low-Curvature Neural Networks »
Suraj Srinivas · Kyle Matoba · Himabindu Lakkaraju · François Fleuret -
2021 Workshop: AI for Science: Mind the Gaps »
Payal Chandak · Yuanqi Du · Tianfan Fu · Wenhao Gao · Kexin Huang · Shengchao Liu · Ziming Liu · Gabriel Spadon · Max Tegmark · Hanchen Wang · Adrian Weller · Max Welling · Marinka Zitnik -
2021 Poster: CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions »
Isha Puri · Amit Dhurandhar · Tejaswini Pedapati · Karthikeyan Shanmugam · Dennis Wei · Kush Varshney -
2020 Poster: Open Graph Benchmark: Datasets for Machine Learning on Graphs »
Weihua Hu · Matthias Fey · Marinka Zitnik · Yuxiao Dong · Hongyu Ren · Bowen Liu · Michele Catasta · Jure Leskovec -
2020 Poster: Graph Meta Learning via Local Subgraphs »
Kexin Huang · Marinka Zitnik -
2020 Spotlight: Open Graph Benchmark: Datasets for Machine Learning on Graphs »
Weihua Hu · Matthias Fey · Marinka Zitnik · Yuxiao Dong · Hongyu Ren · Bowen Liu · Michele Catasta · Jure Leskovec -
2020 Poster: GNNGuard: Defending Graph Neural Networks against Adversarial Attacks »
Xiang Zhang · Marinka Zitnik -
2020 Poster: Subgraph Neural Networks »
Emily Alsentzer · Samuel Finlayson · Michelle Li · Marinka Zitnik -
2020 Demonstration: MolDesigner: Interactive Design of Efficacious Drugs with Deep Learning »
Kexin Huang · Tianfan Fu · Dawood Khan · Ali Abid · Ali Abdalla · Abubaker Abid · Lucas Glass · Marinka Zitnik · Cao Xiao · Jimeng Sun -
2019 : Poster session »
Jindong Gu · Alice Xiang · Atoosa Kasirzadeh · Zhiwei Han · Omar U. Florez · Frederik Harder · An-phi Nguyen · Amir Hossein Akhavan Rahnama · Michele Donini · Dylan Slack · Junaid Ali · Paramita Koley · Michiel Bakker · Anna Hilgard · Hailey Joren · Gonzalo Ramos · Jialin Lu · Jingying Yang · Margarita Boyarskaya · Martin Pawelczyk · Kacper Sokol · Mimansa Jaiswal · Umang Bhatt · David Alvarez-Melis · Aditya Grover · Charles Marx · Sherry Yang · Jingyan Wang · Gökhan Çapan · Hanchen Wang · Steffen Grünewälder · Moein Khajehnejad · Gourab Patro · Russell Kunes · Samuel Deng · Yuanting Liu · Luca Oneto · Mengze Li · Thomas Weber · Stefan Matthes · Duy Patrick Tu