awesome-contrastive-explanation

A curated list of papers on contrastive explanation in ML.

Table of Contents

• Social science and philosophical insights
• Local explanations
• Natural language explanations
• Planning and Reinforcement learning

Social science and philosophical insights

• Explanation in artificial intelligence: Insights from the social sciences (2019 Artificial intelligence), Tim Miller [arxiv]
• Contrastive Explanation: A Structural-Model Approach (2018), Tim Miller [arxiv]
• Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciences (2017 IJCAI workshop XAI), Tim Miller, Piers Howe, Liz Sonenberg [arxiv]
• Why P rather than Q? The curiosities of fact and foil (1994 Philosophical Studies), Eric Barnes
• Contrastive Explanation and Causal Triangulation (1991 Philosophy of Science), Peter Lipton

Pertinent positives/negatives (local explanations)

• Learning Global Transparent Models from Local Contrastive Explanations (2020), Tejaswini Pedapati, Avinash Balakrishnan, Karthikeyan Shanmugam, Amit Dhurandhar [arxiv]
• Model Agnostic Contrastive Explanations for Structured Data (2019), Amit Dhurandhar, Tejaswini Pedapati, Avinash Balakrishnan, Pin-Yu Chen, Karthikeyan Shanmugam, Ruchir Puri [arxiv]
• Generating Contrastive Explanations with Monotonic Attribute Functions (2019), Ronny Luss, Pin-Yu Chen, Amit Dhurandhar, Prasanna Sattigeri, Yunfeng Zhang, Karthikeyan Shanmugam, Chun-Chen Tu [arxiv]
• Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives (2018 NeurIPS) Amit Dhurandhar, Pin-Yu Chen, Ronny Luss, Chun-Chen Tu, Paishun Ting, Karthikeyan Shanmugam, Payel Das [arxiv]

Natural language explanations

• Conversational Explanations of Machine Learning Predictions Through Class-contrastive Counterfactual Statements (2018 IJCAI), Kacper Sokol, Peter Flach [link]
• Generating Counterfactual Explanations with Natural Language (2018 ICML workshop WHI), Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell, Zeynep Akata [arxiv]

Planning and Reinforcement learning

• Explainable AI Planning (XAIP): Overview and the Case of Contrastive Explanation (2019 Reasoning Web), Jörg Hoffmann, Daniele Magazzeni
• Towards Explainable AI Planning as a Service (2019 ICAPS workshop XAI workshop), Michael Cashmore, Anna Collins, Benjamin Krarup, Senka Krivic, Daniele Magazzeni, David Smith [arxiv]
• Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences (2018), Jasper van der Waa, Jurriaan van Diggelen, Karel van den Bosch, Mark Neerincx [arxiv]