UTCS Explainable AI Group Meeting

[ Meeting Schedule | Previous Discussions | Subscribe to Email List ]

The goal of Explainable AI (XAI) is to understand how agents, for instance neural networks, make decisions. We focus on generating visual and/or textual explanations for the decision making process. We would also like to understand how networks represent different concepts and explore approaches to gather information from the interpretable concepts to help train networks.

Spring 2021 Meeting Time & Place

• Biweekly meetings on Friday, 9 a.m. - 10 a.m. We will use Zoom for the meeting, please join in via this link

Scheduled Meetings

Date	Time	Place	Paper
04/23/21	9AM	Zoom	Shweta Narkar et al. Model LineUpper: Supporting Interactive Model Comparison at Multiple Levels for AutoML , IUI 2021

* Future meetings subject to rearrangement.

* Please send in suggestions for new papers to discuss

Past Meetings

Date	Time	Place	Paper
04/09/21	9AM	Zoom	Michael Sejr Schlichtkrull et al. Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking , ICLR
03/26/21	9AM	Zoom	Bhavya Ghai et al. Explainable Active Learning (XAL): Toward AI Explanationsas Interfaces for Machine Teachers , CSCW
02/26/21	9AM	Zoom	Vipin Pillai and Hamed Pirsiavash Explainable Models with Consistent Interpretations, AAAI
02/12/21	9AM	Zoom	Suraj Srinivas and Francois Fleuret Rethinking the Role of Gradient-based Attribution Methods for Model Interpretability, ICLR
12/02/20	2PM	Zoom	Neema Kotonya and Francesca Toni Explainable Automated Fact-Checking for Public Health Claims, EMNLP
11/18/20	2PM	Zoom	Sarthak Jain et al. Learning to Faithfully Rationalize by Construction, ACL
11/04/20	2PM	Zoom	Alon Jacovi and Yoav Goldberg Aligning Faithful Interpretations with their Social Attribution, ACL
10/21/20	2PM	Zoom	Pepa Atanasova et al. Generating Fact Checking Explanations, ACL
10/7/20	2PM	Zoom	Sanjay Subramanian et al. Obtaining Faithful Interpretations from Compositional Neural Networks, ACL
09/23/20	2PM	Zoom	Gagan Bansal et al. Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance, ACM
09/09/20	2PM	Zoom	Patrick Schramowsk et al. Making deep neural networks right for the right scientific reasons by interacting with their explanations, Nature
03/04/20	3PM	GDC 3.516	Ann-Kathrin Dombrowski et al Explanations Can Be Manipulated and Geometry is to Blame, NeurIPS 2020
02/05/20	3PM	GDC 3.516	Amirata Ghorbani et al Towards Automatic Concept-based Explanations, NeurIPS 2020
11/15/19	3PM	GDC 3.516	Sofia Serrano and Noah A. Smith Is attention interpretable?, ACL 2019
11/01/19	3PM	GDC 3.516	Forough Poursabzi-Sangdeh et al Manipulating and Measuring Model Interpretability, NIPS 2017 Workshop on Transparent and Interpretable Machine Learning in Safety Critical Environments
10/18/19	3PM	GDC 3.516	Nazneen Fatema Rajani, Bryan McCann, Caiming Xiong, Richard Socher Explain Yourself! Leveraging Language Models for Commonsense Reasoning, ACL 2019
10/04/19	3PM	GDC 3.516	Zachary C. Lipton The Mythos of Model Interpretability, ICML 2016 Human Interpretability in MachineLearning Workshop
09/20/19	3PM	GDC 4.816	Joost Bastings, Wilker Aziz, Ivan Titov Interpretable Neural Predictions with Differentiable Binary Variables, ACL 2019
05/10/19	3PM	GDC 3.516	Ramprasaath R. Selvaraju, Stefan Lee, Yilin Shen, Hongxia Jin, Dhruv Batra, Devi Parikh Taking a HINT: Leveraging Explanations to Make Vision and Language Models More Grounded, ICCV 2019
04/26/19	3PM	GDC 3.516	Andrew Ross, Michael C. Hughes, and Finale Doshi-Velez Right for the Right Reasons: Training Differentiable Models by Constraining their Explanations, IJCAI 2017
04/12/19	3PM	GDC 3.516	Sarthak Jain, Byron C. Wallace Attention is not Explanation, NAACL 2019
03/29/19	3PM	GDC 3.516	Quanshi Zhang, Ying Nian Wu, and Song-Chun Zhu Interpretable CNNs, TPAMI
03/08/19	3PM	GDC 3.516	Chaofan Chen, Oscar Li, Chaofan Tao, Alina Jade Barnett, Jonathan Su, Cynthia Rudin This Looks Like That: Deep Learning for Interpretable Image Recognition,
02/22/19	3PM	GDC 3.516	Cynthia Rudin Please Stop Explaining Black Box Models for High Stakes Decisions, NeurIPS 2018 (Workshop on Critiquing and Correct-ing Trends in Machine Learning)
02/08/19	3PM	GDC 3.516	Bolei Zhou*, Yiyou Sun*, David Bau*, Antonio Torralba Interpretable Basis Decomposition for Visual Explanation, ECCV 2018
11/30/18	3PM	GDC 3.516	Tao Lei, Regina Barzilay and Tommi Jaakkola Rationalizing Neural Predictions, EMNLP 2016
11/16/18	3PM	GDC 3.516	Arjun Chandrasekaran, Viraj Prabhu, Deshraj Yadav, Prithvijit Chattopadhyay, Devi Parikh Do explanations make VQA models more predictable to a human, EMNLP 2018
11/16/18	3PM	GDC 3.516	Yujia Bao, Shiyu Chang, Mo Yu, Regina Barzilay Deriving Machine Attention from Human Rationales, EMNLP 2018
11/02/18	3PM	GDC 3.516	Pang Wei Koh and Percy Liang Understanding Black-box Predictions via Influence Functions, ICML 2017
10/19/18	3PM	GDC 3.516	Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin “Why Should I Trust You?”Explaining the Predictions of Any Classifier, KDD 2016
10/05/18	3PM	GDC 3.516	Ye Zhang, Iain Marshall, Byron C. Wallace Rationale-Augmented Convolutional Neural Networksfor Text Classification, EMNLP 2016
09/21/18	3PM	GDC 3.516	Lisa Anne Hendricks, Ronghang Hu, Trevor Darrell, Zeynep Akata Grounding Visual Explanations, ECCV, 2018

Proposed Papers

Topic	Suggested Papers
Explanation Evaluation	Mustafa Bilgic and Raymond J. Mooney Explaining Recommendations: Satisfaction vs. Promotion, IUI 2005
Trust Score	Heinrich Jiang, Been Kim, Maya Gupta To Trust Or Not To Trust A Classifier, NIPS 2018
Prototypes and Criticisms	Been Kim, Rajiv Khanna, Oluwasanmi Koyejo Examples are not Enough, Learn to Criticize! Criticism for Interpretability, NIPS 2016

If you find a certain paper interesting and would like to recommend reading, please feel free to let us know during the meeting or e-mail Jialin Wu.

---

Subscribe to Email List