Skip to yearly menu bar Skip to main content

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

Project Page

Abstract

Transparency is vital for AI’s growth. This led to the design of new methods inexplainable AI. We aim to explore the current state of applied XAI and identifyfuture directions.

Video

Chat is not available.

Schedule

Timezone: America/Los_Angeles

6:50 AM

Opening Remarks Opening

Video

7:00 AM

Explanations: Let's talk about them! Talk

Sameer Singh

Video

7:30 AM

Theoretical guarantees for explainable AI? Talk

Ulrike Luxburg

Video

8:00 AM

Coffee & Games Social

8:30 AM

Explainable AI: where we are and how to move forward for health AI. Talk

Su-In Lee

Video

9:00 AM

Panel Discussion Panel Discussion

Leilani Gilpin · Shai Ben-David · Julius Adebayo · Sameer Singh · Su-In Lee · Kamalika Chaudhuri

Video

10:00 AM

Lunch Lunch

11:30 AM

Confronting the Faithfulness Challenge with Post-hoc Model Explanations. Talk

Julius Adebayo

Video

12:00 PM

Poster Session 1 Poster Session

12:01 PM

GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanations Poster

Kenza Amara · Mennatallah El-Assady · Rex Ying

12:01 PM

FRUNI and FTREE synthetic knowledge graphs for evaluating explainability Poster

Pablo Sanchez-Martin · Tarek R. Besold · Priyadarshini Kumari

12:01 PM

Explainable AI in Music Performance: Case Studies from Live Coding and Sound Spatialisation Poster

Jack Armitage · Nicola Privato · Victor Shepardson · Celeste Betancur Gutierrez

12:01 PM

Towards Explanatory Model Monitoring Poster

Alexander Koebler · Thomas Decker · Michael Lebacher · Ingo Thon · Volker Tresp · Florian Buettner

12:01 PM

Lessons from Usable ML Deployments Applied to Wind Turbine Monitoring Poster

Alexandra Zytek · Wei-En Wang · Sofia Koukoura · Kalyan Veeramachaneni

12:01 PM

DeepDecipher: Accessing and Investigating Neuron Activation in Large Language Models Poster

Albert Garde · Esben Kran · Fazl Barez

12:01 PM

How Well Do Feature-Additive Explainers Explain Feature-Additive Predictors? Poster

Zachariah Carmichael · Walter Scheirer

12:01 PM

Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making Poster

Aliyah Hsu · Yeshwanth Cherapanamjeri · Briton Park · Tristan Naumann · Anobel Odisho · Bin Yu

12:01 PM

AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments Poster

Yang Zhang · Yawei Li · Hannah Brown · Mina Rezaei · Bernd Bischl · Philip Torr · Ashkan Khakzar · Kenji Kawaguchi

12:01 PM

Geometric Remove-and-Retrain (GOAR): Coordinate-Invariant eXplainable AI Assessment Poster

Yong-Hyun Park · Junghoon Seo · 범석 박 · Seongsu Lee · Junghyo Jo

12:01 PM

Utilizing Explainability Techniques for Reinforcement Learning Model Assurance Demo

Alexander Tapley

12:01 PM

Detecting Spurious Correlations via Robust Visual Concepts in Real and AI-Generated Image Classification Poster

Preetam Prabhu Srikar Dammu · Chirag Shah

12:01 PM

Towards the next generation explainable AI that promotes AI-human mutual understanding Poster

Janet Hsiao · Antoni Chan

12:01 PM

Are VideoQA Models Truly Multimodal? Poster

Ishaan Singh Rawal · Shantanu Jaiswal · Basura Fernando · Cheston Tan

12:01 PM

Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning Poster

Maxime Wabartha · Joelle Pineau

12:01 PM

COMET: Cost Model Explanation Framework Poster

Isha Chaudhary · Alex Renda · Charith Mendis · Gagandeep Singh

12:01 PM

Interactive Visual Feature Search Demo

Devon Ulrich · Ruth Fong

12:01 PM

Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable? Poster

Ričards Marcinkevičs · Sonia Laguna · Moritz Vandenhirtz · Julia Vogt

12:01 PM

Estimation of Concept Explanations Should be Uncertainty Aware Poster

Vihari Piratla · Juyeon Heo · Sukriti Singh · Adrian Weller

12:01 PM

Optimising Human-AI Collaboration by Learning Convincing Explanations Poster

Alex Chan · Alihan Hüyük · Mihaela van der Schaar

12:01 PM

Inherent Inconsistencies of Feature Importance Poster

Nimrod Harel · Uri Obolski · Ran Gilad-Bachrach

12:01 PM

ExpLIMEable: An exploratory framework for LIME Demo

Sonia Laguna · Julian Heidenreich · Jiugeng Sun · Nilüfer Cetin · Ibrahim Al Hazwani · Udo Schlegel · Furui Cheng · Mennatallah El-Assady

12:01 PM

Influence Based Approaches to Algorithmic Fairness: A Closer Look Poster

Soumya Ghosh · Prasanna Sattigeri · Inkit Padhi · Manish Nagireddy · Jie Chen

12:01 PM

Explaining black box text modules in natural language with language models Poster

Chandan Singh · Aliyah Hsu · Richard Antonello · Shailee Jain · Alexander Huth · Bin Yu · Jianfeng Gao

12:01 PM

Use Perturbations when Learning from Explanations Poster

Juyeon Heo · Vihari Piratla · Matthew Wicker · Adrian Weller

12:01 PM

Assessment of the Reliablity of a Model's Decision by Generalizing Attribution to the Wavelet Domain Poster

Gabriel Kasmi · Laurent Dubus · Yves-Marie Saint-Drenan · Philippe BLANC

1:00 PM

Coffee & Games Social

1:30 PM

Explaining Self-Driving Cars for Accountable Autonomy. Talk

Leilani Gilpin

Video

2:00 PM

Contributed Talks Talk

Video

2:01 PM

Emergence of Segmentation with Minimalistic White-Box Transformers Spotlight

Yaodong Yu · Tianzhe Chu · Shengbang Tong · Ziyang Wu · Druv Pai · Sam Buchanan · Yi Ma

2:07 PM

Scale Alone Does not Improve Mechanistic Interpretability in Vision Models Spotlight

Roland S. Zimmermann · Thomas Klein · Wieland Brendel

2:14 PM

On Evaluating Explanation Utility for Human-AI Decision-Making in NLP Spotlight

Fateme Hashemi Chaleshtori · Atreya Ghosal · Ana Marasovic

2:21 PM

Understanding Scalable Perovskite Solar Cell Manufacturing with Explainable AI Spotlight

Lukas Klein · Sebastian Ziegler · Felix Laufer · Charlotte Debus · Markus Götz · Klaus Maier-Hein · Ulrich Paetzold · Fabian Isensee · Paul Jaeger

2:30 PM

Poster Session 2 Poster Session

A Critical Survey on Fairness Benefits of XAI Poster

Luca Deck · Jakob Schoeffer · Maria De-Arteaga · Niklas Kuehl

Exploring Practitioner Perspectives On Training Data Attribution Explanations Poster

Elisa Nguyen · Evgenii Kortukov · Jean Song · Seong Joon Oh

Explaining high-dimensional text classifiers Poster

Odelia Melamed · Rich Caruana

Sum-of-Parts Models: Faithful Attributions for Groups of Features Poster

Weiqiu You · Helen Qu · Marco Gatti · Bhuvnesh Jain · Eric Wong

Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test Poster

Anna Hedström · Leander Weber · Sebastian Lapuschkin · Marina Höhne

Stability Guarantees for Feature Attributions with Multiplicative Smoothing Poster

Anton Xue · Rajeev Alur · Eric Wong

On the Consistency of GNN Explainability Methods Poster

Ehsan Hajiramezanali · Sepideh Maleki · Alex Tseng · Aicha BenTaieb · Gabriele Scalia · Tommaso Biancalani

Transparent Anomaly Detection via Concept-based Explanations Poster

Laya Rafiee Sevyeri · Ivaxi Sheth · Farhood Farahnak · Shirin Abbasinejad Enger

Robust Recourse for Binary Allocation Problems Poster

Meirav Segal · Anne-Marie George · Ingrid Yu · Christos Dimitrakakis

Are Large Language Models Post Hoc Explainers? Poster

Nicholas Kroeger · Dan Ley · Satyapriya Krishna · Chirag Agarwal · Himabindu Lakkaraju

Rectifying Group Irregularities in Explanations for Distribution Shift Poster

Adam Stein · Yinjun Wu · Eric Wong · Mayur Naik

Explainable Alzheimer’s Disease Progression Prediction using Reinforcement Learning Poster

Raja Farrukh Ali · Ayesha Farooq · Emmanuel Adeniji · John Woods · Vinny Sun · William Hsu

A Simple Scoring Function to Fool SHAP: Stealing from the One Above Poster

Jun Yuan · Aritra Dasgupta

Explaining Longitudinal Clinical Outcomes using Domain-Knowledge driven Intermediate Concepts Poster

Sayantan Kumar · Thomas Kannampallil · Aristeidis Sotiras · Philip Payne

Visual Topics via Visual Vocabularies Poster

Shreya Havaldar · Weiqiu You · Lyle Ungar · Eric Wong

Extracting human interpretable structure-property relationships in chemistry using XAI and large language models Poster

Geemi Wellawatte · Philippe Schwaller

Interactive Model Correction with Natural Language Poster

Yoonho Lee · Michelle Lam · Helena Vasconcelos · Michael Bernstein · Chelsea Finn

On the Relationship Between Explanation and Prediction: A Causal View Poster

Amir-Hossein Karimi · Krikamol Muandet · Simon Kornblith · Bernhard Schölkopf · Been Kim

ReLax: An Efficient and Scalable Recourse Explanation Benchmarking Library using JAX Poster

Hangzhi Guo · Xinchang Xiong · Wenbo Zhang · Amulya Yadav

Caution to the Exemplars: On the Intriguing Effects of Example Choice on Human Trust in XAI Poster

Tobias Leemann · Yao Rong · Thai-Trang Nguyen · Dr. Enkelejda Kasneci · Gjergji Kasneci

Policy graphs in action: explaining single- and multi-agent behaviour using predicates Poster

Sergio Alvarez-Napagao · Adrián Tormos · Victor Gimenez-Abalos · Dmitry Gnatyshak

Explaining Tree Model Decisions in Natural Language for Network Intrusion Detection Poster

Noah Ziems · Gang Liu · John Flanagan · Meng Jiang

ObEy Anything: Quantifiable Object-based Explainability without Ground Truth Annotations Poster

William Ho · Lennart Schulze · Richard Zemel

Cost-aware counterfactuals for black box explanations Poster

Natalia Martinez · Kanthi Sarpatwar · Sumanta Mukherjee · Roman Vaculin

The Disagreement Problem in Faithfulness Metrics Poster

Brian Barr · Noah Fatsi · Leif Hancox-Li · Peter Richter · Daniel Proano

Empowering Domain Experts to Detect Social Bias in Generative AI with User-Friendly Interfaces Poster

Roy Jiang · Rafal Kocielnik · Adhithya Prakash Saravanan · Pengrui Han · R. Michael Alvarez · Animashree Anandkumar

Do Concept Bottleneck Models Obey Locality? Poster

Naveen Raman · Mateo Espinosa Zarlenga · Juyeon Heo · Mateja Jamnik

Diffusion-Guided Counterfactual Generation for Model Explainability Poster

Nishtha Madaan · Srikanta Bedathur

GLANCE: Global to Local Architecture-Neutral Concept-based Explanations Poster

Avinash Kori · Ben Glocker · Francesca Toni