NeSy 2023
17th International Workshop on Neural-Symbolic Learning and Reasoning

Table of Contents

• Preface
  Summary: There were 67 papers submitted for peer-review to this workshop. Out of these, 48 papers were accepted for this volume.

Research papers track

• A Roadmap for Neuro-argumentative Learning (short paper) 1-8
  Maurizio Proietti, Francesca Toni
• What's Wrong with Gradient-based Complex Query Answering? 9-18
  Ouns El Harzli, Samy Badreddine, Tarek R. Besold
• Closing the Neural-Symbolic Cycle: Knowledge Extraction, User Intervention and Distillation from Convolutional Neural Networks 19-43
  Kwun Ho Ngan, James Phelan, Esma Mansouri-Benssassi, Joe Townsend, Artur S. d'Avila Garcez
• The Challenge of Learning Symbolic Representations 44-61
  Luca Salvatore Lorello, Marco Lippi
• Exploring Mathematical Conjecturing with Large Language Models 62-77
  Moa Johansson, Nicholas Smallbone
• Learning Logic Constraints From Demonstration (short paper) 78-84
  Mattijs Baert, Sam Leroux, Pieter Simoens
• From Axioms over Graphs to Vectors, and Back Again: Evaluating the Properties of Graph-based Ontology Embeddings 85-102
  Fernando Zhapa-Camacho, Robert Hoehndorf
• Neural-Symbolic Predicate Invention: Learning Relational Concepts from Visual Scenes 103-117
  Jingyuan Sha, Hikaru Shindo, Kristian Kersting, Devendra Singh Dhami
• Semantic Interpretability of Convolutional Neural Networks by Taxonomy Extraction 118-127
  Vitor A. C. Horta, Robin Sobczyk, Maarten C. Stol, Alessandra Mileo
• Preliminary Results on a State-Driven Method for Rule Construction in Neural-Symbolic Reinforcement Learning 128-138
  Davide Beretta, Stefania Monica, Federico Bergenti
• A Modular Neurosymbolic Approach for Visual Graph Question Answering 139-149
  Thomas Eiter, Nelson Higuera Ruiz, Johannes Oetsch
• Is the Proof Length a Good Indicator of Hardness for Reason-able Embeddings? 150-161
  Jędrzej Potoniec
• Neuro-Symbolic Reasoning Shortcuts: Mitigation Strategies and their Limitations (short paper) 162-166
  Emanuele Marconato, Stefano Teso, Andrea Passerini
• Knowledge-Guided Colorization: Overview, Prospects and Challenges (short paper) 167-173
  Rory Ward, M. Jaleed Khan, John G. Breslin, Edward Curry
• Towards Invertible Semantic-Preserving Embeddings of Logical Formulae 174-194
  Gaia Saveri, Luca Bortolussi
• Implementing Trustworthy AI in Real-world Medical Imaging using the SimpleMind Software Environment (short paper) 195-203
  Matthew S. Brown, M. Wasil Wahi-Anwar, Youngwon Choi, Morgan Daly, Liza Shrestha, Koon-Pong Wong, Jonathan G. Goldin, Dieter R. Enzmann
• Large Language Models Need Symbolic AI (short paper) 204-209
  Kristian Hammond, David Leake
• Continual Reasoning: Non-monotonic Reasoning in Neurosymbolic AI using Continual Learning 210-222
  Sofoklis Kyriakopoulos, Artur S. d'Avila Garcez
• Designing Logic Tensor Networks for Visual Sudoku Puzzle Classification 223-232
  Lia Morra, Alberto Azzari, Letizia Bergamasco, Marco Braga, Luigi Capogrosso, Federico Delrio, Giuseppe Di Giacomo, Simone Eiraudo, Giorgia Ghione, Rocco Giudice, Alkis Koudounas, Luca Piano, Daniele Rege Cambrin, Matteo Risso, Marco Rondina, Alessandro Sebastien Russo, Marco Russo, Francesco Taioli, Lorenzo Vaiani, Chiara Vercellino
• Inductive Future Time Prediction on Temporal Knowledge Graphs with Interval Time (short paper) 233-240
  Roxana Pop, Egor V. Kostylev
• Challenge Problems in Developing a Neuro-Symbolic OODA Loop (short paper) 241-247
  Alberto Speranzon, Christian H. Debrunner, David Rosenbluth, Mauricio Castillo-Effen, Anthony R. Nowicki, Kevin Alcedo, Andrzej Banaszuk
• How to Think About Benchmarking Neurosymbolic AI? (short paper) 248-254
  Johanna Ott, Arthur Ledaguenel, Céline Hudelot, Mattis Hartwig
• Visual Reward Machines 255-267
  Elena Umili, Francesco Argenziano, Aymeric Barbin, Roberto Capobianco
• PhysWM: Physical World Models for Robot Learning 268-278
  Marc Otto, Octavio Arriaga, Chandandeep Singh, Jichen Guo, Frank Kirchner
• Decoding Superpositions of Bound Symbols Represented by Distributed Representations 279-288
  Michael Hersche, Zuzanna Opala, Geethan Karunaratne, Abu Sebastian, Abbas Rahimi
• A Hybrid System for Systematic Generalization in Simple Arithmetic Problems 289-301
  Flavio Petruzzellis, Alberto Testolin, Alessandro Sperduti
• VSA-based Positional Encoding Can Replace Recurrent Networks in Emergent Symbol Binding 302-326
  Francesco S. Carzaniga, Michael Hersche, Kaspar Schindler, Abbas Rahimi
• On the Benefits of OWL-based Knowledge Graphs for Neural-Symbolic Systems (short paper) 327-335
  David Herron, Ernesto Jiménez-Ruiz, Tillman Weyde
• Causality Prediction with Neural-Symbolic Systems: A Case Study in Smart Grids 336-347
  Katrin Schreiberhuber, Marta Sabou, Fajar J. Ekaputra, Peter Knees, Peb Ruswono Aryan, Alfred Einfalt, Ralf Mosshammer
• Towards Explainable Decision Making with Neural Program Synthesis and Library Learning 348-368
  Manuel Eberhardinger, Johannes Maucher, Setareh Maghsudi
• Exploiting T-norms for Deep Learning in Autonomous Driving 369-380
  Mihaela C. Stoian, Eleonora Giunchiglia, Thomas Lukasiewicz
• FB15k-CVT: A Challenging Dataset for Knowledge Graph Embedding Models 381-394
  Mouloud Iferroudjene, Victor Charpenay, Antoine Zimmermann
• Explainable Classification of Internet Memes 395-409
  Abhinav Kumar Thakur, Filip Ilievski, Hông-Ân Sandlin, Zhivar Sourati, Luca Luceri, Riccardo Tommasini, Alain Mermoud

Recently published papers track (extended abstracts)

• GlanceNets: Interpretable, Leak-proof Concept-based Models 410-410
  Emanuele Marconato, Andrea Passerini, Stefano Teso
• Learning Where and When to Reason in Neuro-Symbolic Inference 411-412
  Cristina Cornelio, Jan Stuemer, Shell Xu Hu, Timothy Hospedales
• Semantic Probabilistic Layers for Neuro-Symbolic Learning 413-413
  Kareem Ahmed, Stefano Teso, Kai-Wei Chang, Guy Van den Broeck, Antonio Vergari
• RL-Net: Interpretable Rule Learning with Neural Networks 414-415
  Lucile Dierckx, Rosana Veroneze, Siegfried Nijssen
• Generalizable Neuro-Symbolic Systems for Commonsense Question Answering 416-417
  Alessandro Oltramari, Jonathan Francis, Filip Ilievski, Kaixin Ma, Roshanak Mirzaee
• Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions 418-419
  Alessandro Daniele, Tommaso Campari, Sagar Malhotra, Luciano Serafini
• The Roles of Symbols in Neural-based AI: They are Not What You Think! 420-421
  Daniel L. Silver, Tom M. Mitchell
• Interpretable Neural-Symbolic Concept Reasoning 422-423
  Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini, Mateo Espinosa Zarlenga, Lucie Charlotte Magister, Alberto Tonda, Pietro Liò, Frederic Precioso, Mateja Jamnik, Giuseppe Marra
• Combining Machine Learning and Semantic Web: A Systematic Mapping Study 424-424
  Anna Breit, Laura Waltersdorfer, Fajar J. Ekaputra, Marta Sabou, Andreas Ekelhart, Andreea Iana, Heiko Paulheim, Jan Portisch, Artem Revenko, Frank van Harmelen, Annette ten Teije
• Solving Raven's Progressive Matrices via a Neuro-vector-symbolic Architecture 425-426
  Michael Hersche, Mustafa Zeqiri, Luca Benini, Abu Sebastian, Abbas Rahimi
• Verifying Strategic Abilities of Neural-Symbolic Multi-agent Systems 427-427
  Michael Akintunde, Elena Botoeva, Panagiotis Kouvaros, Alessio Lomuscio
• Safe Reinforcement Learning via Probabilistic Logic Shields 428-429
  Wen-Chi Yang, Giuseppe Marra, Gavin Rens, Luc De Raedt
• Neural Class Expression Synthesis 430-431
  N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir, Axel-Cyrille Ngonga Ngomo
• Logic Explained Networks 432-433
  Gabriele Ciravegna, Pietro Barbiero, Francesco Giannini, Marco Gori, Pietro Liò, Marco Maggini, Stefano Melacci
• VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming 434-435
  Eleonora Misino, Giuseppe Marra, Emanuele Sansone