xAI-2024:LB/D/DC
xAI-2024 Late-breaking Work, Demos and Doctoral Consortium Joint Proceedings

Table of Contents

• Preface
  Luca Longo Weiru Liu Grégoire Montavon

Late-Breaking Work

• Explainable Artificial Intelligence Beyond Feature Attributions: The Validity and Reliability of Feature Selection Explanations 1-8
  Raphael Wallsberger, Ricardo Knauer, Stephan Matzka

• Shapley values and fairness 9-16
  Paolo Giudici, Parvati Neelakantan

• Perception and Consideration of the Explainees’ Needs for Satisfying Explanations 17-24
  Michael Erol Schaffer, Lutz Terfloth, Carsten Schulte, Heike M. Buhl

• A proposal for improving EEG microstate generation via interpretable deep clustering with convolutional autoencoders 25-32
  Arjun Vinayak Chikkankod, Luca Longo

• Faithful Attention Explainer: Verbalizing Decisions Based on Discriminative Features 33-40
  Yao Rong, David Scheerer, Enkelejda Kasneci

• Use Bag-of-Patterns Approach to Explore Learned Behaviors of Reinforcement Learning 41-48
  Gulsum Alicioglu, Bo Sun

• Generate Explanations for Time-series classification by ChatGPT 49-56
  Zhechang Xue, Yiran Huang, Hongnan Ma, Michael Beigl

• Model agnostic calibration of image classifiers 57-64
  Paolo Giudici, Giulia Vilone

• Interpreting Black-Box Time Series Classifiers using Parameterised Event Primitives 65-72
  Ephrem T. Mekonnen, Luca Longo, Pierpaolo Dondio

• Patch-based Intuitive Multimodal Prototypes Network (PIMPNet) for Alzheimer’s Disease classification 73-80
  Lisa Anita De Santi, Jörg Schlötterer, Meike Nauta, Vincenzo Positano, Christin Seifert

• AnyCBMs: How to Turn Any Black Box into a Concept Bottleneck Model 81-88
  Gabriele Dominici, Pietro Barbiero, Francesco Giannini, Martin Gjoreski, Marc Langeinrich

• Online Explainable Ensemble of Tree Models Pruning for Time Series Forecasting 89-96
  Amal Saadallah

• Towards Mechanistic Interpretability for Autoencoder compression of EEG signals 97-104
  Leon Hegedić, Luka Hobor, Nikola Marić, Martin Ante Rogošić, Mario Brcic

• Integrating XAI for Predictive Conflict Analytics 105-112
  Luca Macis, Marco Tagliapietra, Alessandro Castelnovo, Daniele Regoli, Greta Greco, Andrea Claudio Cosentini, Paola Pisano, Edoardo Carroccetto

• Interpretable Vital Sign Forecasting with Model Agnostic Attention Maps 113-120
  Yuwei Liu, Chen Dan, Anubhav Bhatti, Bingjie Shen, Divij Gupta, Suraj Parmar, San Lee,

• Towards Assurance of LLM Adversarial Robustness using Ontology-Driven Argumentation 121-128
  Tomas Bueno Momcilovic, Beat Buesser, Giulio Zizzo, Mark Purcell, Dian Balta

• Looking for the Right Paths to Use XAI in the Judiciary. Which Branches of Law Need Inherently Interpretable Machine Learning Models and Why? 129-136
  Andrzej Porębski

• The Dynamics of Explainability: Diverse Insights from SHAP Explanations using Neighbourhoods 137-144
  Urja Pawar, Ruairi O’Reilly, Christian Beder, Donna O’Shea

• Enhancing the analysis of the P300 event-related potential with integrated gradients on a convolutional neural network trained with superlets 145-152
  Vladimir Marochko, Luca Longo,

• Exploring Commonalities in Explanation Frameworks: A Multi-Domain Survey Analysis 153-160
  Eduard Barbu, Marharytha Domnich, Raul Vicente, Nikos Sakkas

• Investigating Neuron Ablation in Attention Heads: The Case for Peak Activation Centering 161-168
  Nicholas Pochinkov, Ben Pasero, Skylar Shibayama

• CatBoost model with self-explanatory capabilities for predicting SLE in OMAN population 169-176
  Hamza Zidoum, Ali AlShareedah, Aliya Al-Ansari, Batool Al Lawati, Al-Sawafi

• Channel Modeling for Millimeter-Wave UAV Communication based on Explainable Generative Neural Network 177-184
  Ladan Gholami, Pietro Ducange, Pietro Cassará, Alberto Gotta

• Validation of ML Models from the Field of XAI for Computer Vision in Autonomous Driving 185-192
  Antonio Mastroianni, Sibylle D. Sager-Müller

• Second Glance: A Novel Explainable AI to Understand Feature Interactions in Neural Networks using Higher-Order Partial Derivatives 193-200
  Zohaib Shahid, Yogachandran Rahulamathavan, Safak Dogan

• Mediating Explainer for Human Autonomy Teaming 201-208
  Siri Padmanabhan Poti, Christopher J. Stanton

• Exploring Agent Behaviors in Network Security through Trajectory Clustering 209-216
  Ondrej Lukas, Sebastian Garcia

• A geometric XAI approach to protein pocket detection 217-224
  Giovanni Bocchi, Patrizio Frosini, Alessandra Micheletti, Alessandro Pedretti, Gianluca Palermo, Davide Gadioli, Carmen Gratteri, Filippo Lunghini, Andrea Rosario Beccari, Anna Fava, Carmine Talarico

• An Empirical Investigation of Users’ Assessment of XAI Explanations: Identifying the Sweet Spot of Explanation Complexity and Value 225-232
  Felix Liedeker, Christoph Düsing, Marcel Nieveler, Philipp Cimiano

• A Two-Stage Algorithm for Cost-Efficient Multi-instance Counterfactual Explanations 233-240
  André Artelt, Andreas Gregoriades

• Interactive xAI-dashboard for Semantic Segmentation 241-248
  Finn Schürmann, Sibylle D. Sager-Müller

• XAI for Group-AI Interaction: Towards Collaborative and Inclusive Explanations 249-256
  Mohammad Naiseh, Catherine Webb, Tim Underwood, Gopal Ramchurn, Zoe Walters Navamayooran Thavanesan, Ganesh Vigneswaran

• Unraveling Anomalies: Explaining Outliers with DTOR 257-264
  Riccardo Crupi, Daniele Regoli, Alessandro Damiano Sabatino, Immacolata Marano, Massimiliano Brinis, Luca Albertazzi, Andrea Cirillo, Andrea Claudio Cosentini

Demos

• CaBRNet, An Open-Source Library For Developing And Evaluating Case-Based Reasoning Models 265-272
  Romain Xu-Darme, Aymeric Varasse, Alban Grastien, Julien Girard-Satabin, Zakaria Chihani

• XAgent: A Conversational XAI Agent Harnessing the Power of Large Language Models 273-280
  Van Bach Nguyen, Jörg Schlötterer, Christin Seifert

• mlr3summary: Concise and interpretable summaries for machine learning models 281-288
  Susanne Dandl, Marc Becker, Bernd Bischl, Giuseppe Casalicchio, Ludwig Bothmann,

• Democratizing Advanced Attribution Analyses of Generative Language Models with the Inseq Toolkit 289-296
  Gabriele Sarti, Nils Feldhus, Jirui Qi, Malvina Nissim, Arianna Bisazza

• Human-in-the-loop testing of the explainability of robot navigation algorithms in extended reality 297-304
  Jérôme Guzzi, Alessandro Giusti

• Rulex Platform: leveraging domain knowledge and data-driven rules to support decisions in the fintech sector through eXplainable AI models 305-312
  Claudio Muselli, Damiano Verda, Enrico Ferrari, Claire Thomas Gaggiotti, Marco Muselli

• Building Personalised XAI Experiences Through iSee: a Case-Based Reasoning-Driven Platform 313-320
  Marta Caro-Martínez, Anne Liret, Belén Díaz-Agudo, Juan A. Recio-García, Jesús Darias, Nirmalie Wiratunga, Anjana Wijekoon, Kyle Martin, Ikechukwu Nkisi-Orji, David Corsar, Chamath Palihawadana, Craig Pirie, Derek Bridge, Preeja Pradeep, Bruno Fleisch

Doctoral Consortium

• Fostering Human-AI interaction: development of a Clinical Decision Support System enhanced by eXplainable AI and Natural Language Processing 321-328
  Laura Bergomi

• Optimizing Synthetic Data from Scarcity: Towards Meaningful Data Generation in High-Dimensional Low-Sample Size Domains 329-336
  Danilo Danese

• Assesing the Interpretability of the Statistical Radiomic Features via Image Saliency Maps in Medical Image Classification Tasks 337-344
  Oleksandr Davydko

• Explainable AI as a Crucial Factor for Improving Human-AI Decision-Making Processes 345-352
  Regina de Brito Duarte

• Counterfactual generating Variational Autoencoder for Anomaly Detection 353-360
  Renate Ernst

• Privacy Implications of Explainable AI in Data-Driven Systems 361-368
  Fatima Ezzeddine

• XAI-driven Model Improvements in Interpretable Image Segmentation 369-376
  Rokas Gipiškis

• Design Guidelines for XAI in the Healthcare Domain 377-384
  Iris Heerlien

• Explainable MLOps: A Methodological Framework for the Development of Explainable AI in Practice 385-392
  Annemarie Jutte

• A Novel Model-Agnostic xAI Method Guided by Cost-Sensitive Tree Models and Argumentative Decision Graphs 393-400
  Marija Kopanja

• Explainable Artificial Intelligence and Reasoning in the Context of Large Neural Network Models 401-408
  Stefanie Krause

• Artificial Representative Trees as Interpretable Surrogates for Random Forests 409-416
  Lea Louisa Kronziel

• Can Reduction of Bias Decrease the Need for Explainability? Working with Simplified Models to Understand Complexity 417-424
  Pedro M. Marques

• Towards XAI for Optimal Transport 425-432
  Philip Naumann

• Knowledge Graphs and Explanations for Improving Detection of Diseases in Images of Grains 433-440
  Lenka Tětková

• Topological Data Analysis for Trustworthy AI 441-448
  Victor Toscano Durán

• Explainable Deep Reinforcement Learning through Introspective Explanations 449-456
  Nils Wenninghoff

• Explainable and Debiased Misogyny Identification In Code-Mixed Hinglish using Artificial Intelligence Models 457-464
  Sargam Yadav