xAI-2023:LB-D-DC
xAI-2023 Late-breaking Work, Demos and Doctoral Consortium Joint Proceedings

Table of Contents

• Preface
  Luca Longo

Late-Breaking Work

• Why Industry 5.0 Needs XAI 2.0? 1-6
  Szymon Bobek , Sławomir Nowaczyk , Joao Gama , Sepideh Pashami , Rita P. Ribeiro , Zahra Taghiyarrenani , Bruno Veloso , Lala Rajaoarisoa , Maciej Szelazėk , Grzegorz J. Nalepa

• Trustworthy Enough? Evaluation of an AI Decision Support System for Healthcare Professionals 7-11
  Kristýna Sirka Kacafírková , Sara Polak , Myriam Sillevis Smitt , Shirley A. Elprama , An Jacobs

• Interpreting Forecasted Vital Signs Using N-BEATS in Sepsis Patients 12-17
  Anubhav Bhatti , Naveen Thangavelu , Marium Hassan , Choongmin Kim , San Lee , Yonghwan Kim , Jang Yong Kim

• AutoXplain: Towards Automated Interpretable Model Selection 18-23
  Tessel Haagen , Heysem Kaya , Joop Snijder , Melchior Nierman

• Explaining ANN-modeled fMRI Data with Path-Weights and Layer-Wise Relevance Propagation 24-29
  José Diogo Marques dos Santos , José Paulo Marques dos Santos

• Examining the Nexus between Explainability of AI Systems and User's Trust: A Preliminary Scoping Review 30-35
  Sofia Morandini , Federico Fraboni , Gabriele Puzzo , Davide Giusino , Lucia Volpi , Hannah Brendel , Enzo Balatti , Marco De Angelis , Andrea De Cesarei , Luca Pietrantoni

• A Prototype of an Interactive Clinical Decision Support System with Counterfactual Explanations 36-41
  Felix Liedeker , Philipp Cimiano

• Is the Common Approach used to Identify Social Biases in Artificial Intelligence also Biased? 42-46
  Ana Bucchi , Gabriel M. Fonseca

• Local Interpretable Model-Agnostic Explanations for Multitarget Image Regression 47-52
  Kira Vinogradova , Gene Myers

• An Examination of the Effect of the Inconsistency Budget in Weighted Argumentation Frameworks and their Impact on the Interpretation of Deep Neural Networks 53-58
  Giulia Vilone , Luca Longo

• Machine Learning Explanations by Surrogate Causal Models (MaLESCaMo) 59-64
  Alberto Termine , Alessandro Antonucci , Alessandro Facchini

• Latent Space Interpretation and Visualisation for Understanding the Decisions of Convolutional Variational Autoencoders Trained with EEG Topographic Maps 65-70
  Taufique Ahmed , Luca Longo

• Explaining Deep Learning Time Series Classification Models using a Decision Tree-Based Post-Hoc XAI Method 71-76
  Ephrem T. Mekonnen , Pierpaolo Dondio , Luca Longo

• Evaluation of Explainable AI methods for Classification Tasks in Visual Inspection 77-82
  Björn Forcher , Patrick Menold , Moritz Weixler , Jörg Schmitt , Samuel Wagner

• User-Driven Counterfactual Generator: A Human Centered Exploration 83-88
  Isacco Beretta , Eleonora Cappuccio , Marta Marchiori Manerba

• Optimizing Deep Q-Learning Experience Replay with SHAP Explanations: Exploring Minimum Experience Replay Buffer Sizes in Reinforcement Learning 89-94
  Robert S. Sullivan , Luca Longo

• Uncovering Decision-making Process of Cost-sensitive Tree-based Classifiers using the Adaptation of TreeSHAP 95-100
  Marija Kopanja , Sanja Brdar , Stefan Hačko

• Explaining the Transfer Learning Ability of a Deep Neural Networks by Means of Representations 101-106
  German Magai , Artem Soroka

• Investigating Poor Performance Regions of Black Boxes: LIME-based Exploration in Sepsis Detection 107-111
  Mozhgan Salimiparsa , Surajsinh Parmar , San Lee , Choongmin Kim , Yonghwan Kim , Jang Yong Kim

• An Explainable AI User Interface for Facilitating Collaboration between Domain Experts and AI Researchers 112-116
  Meng Shi , Celal Savur , Elizabeth Watkins , Ramesh Manuvinakurike , Gesem Gudino Mejia , Richard Beckwith , Giuseppe Raffa

• The Metric-aware Kernel-width Choice for LIME 117-122
  Aurelio Barrera-Vicent , Eduardo Paluzo-Hidalgo , Miguel A. Gutiérrez-Naranjo

• Integration of Explainable Deep Neural Network with Blockchain Technology: Medical Indemnity Insurance 123-128
  Swati Sachan , Jericho Muwanga

• When Attention Turn To Be Explanation. A Case Study in Recommender Systems 129-134
  Ricardo Anibal Matamoros Aragon , Italo Zoppis , Sara Manzoni

• Low-Impact Feature Reduction Regularization Term: How to Improve Artificial Intelligence with Explainability 135-139
  Iván Sevillano-García , Julian Luengo , Francisco Herrera

• Revitalize the Potential of Radiomics: Interpretation and Feature Stability in Medical Imaging Analyses through Groupwise Feature Importance 140-145
  Anna Theresa Stüber , Stefan Coors , Michael Ingrisch

Demos

• eXplego: An interactive Tool that Helps you Select Appropriate XAI-methods for your Explainability Needs 146-151
  Martin Jullum , Jacob Sjødin , Robindra Prabhu , Anders Løland

• FCAS Ethical AI Demonstrator 152-157
  Florian Osswald , Roman Bartolosch , Torsten Fiolka , Engelbert Hartmann , Bernhard Krach , Jan Feil , Martin Lederer

• Argumentation-based Explainable Machine Learning ArgEML: α-Version Technical Details 158-163
  Nicoletta Prentzas

• Federated Learning of Explainable Artificial Intelligence Models: A Proof-of-Concept for Video-streaming Quality Forecasting in B5G/6G networks 164-168
  José Luis Corcuera Bárcena , Mattia Daole , Pietro Ducange , Francesco Marcelloni , Giovanni Nardini , Alessandro Renda , Giovanni Stea

Doctoral Consortium

• Probabilistic Modelling for Design and Verification of Trustworthy Autonomous Systems 169-176
  Franca Corradini

• Deep Clustering as a Unified Method for Representation Learning and Clustering of EEG Data for Microstate Theory 177-184
  Arjun Vinayak Chikkankod

• Real-Time Explainable Plausibility Verification for DNN-based Automotive Perception 185-192
  Mert Keser

• Extending Merlin-Arthur Classifiers for Improved Interpretability 193-200
  Berkant Turan

• Designing an Evaluation Framework for eXplainable AI in the Healthcare Domain 201-208
  Ivania Donoso-Guzmán

• Personalized Human-Robot Interaction in Companion Social Robots 209-216
  Bahram Salamat Ravandi

• Accelerating Implementation of Artificial Intelligence in Radiotherapy through Explainability 217-224
  Luca Heising

• Lung images Classification with Textural Characteristics and Hybrid Classification Schemes 225-232
  Oleksandr Davydko

• Explain and Interpret Few-Shot Learning 233-240
  Andrea Fedele

• Fairness Auditing, Explanation and Debiasing in Linguistic Data and Language Models 241-248
  Marta Marchiori Manerba

• Post Hoc Explanations for RNNs using State Transition Representations for Time Series Data 249-255
  Gargi Gupta