List of accepted papers.
11am TAILOR workshop (Chair: Francesco Giannini) - hybrid
11:00-11:05 – Opening
11:05-11:20 – Towards a survey and unified benchmark for neural-symbolic AI – Luc De Raedt and Robin Manhaeve
11:20-11:30 – Neuro-Symbolic Continual Learning: Harnessing Knowledge for Drifting NeSy Scenarios – Emanuele Marconato
11:30-11:40 – Entity Linking Benchmark in Computational Food: Combining Text Mining, Logical Reasoning, and LLM Prompting – Agnieszka Lawrynowicz
11:40-11:50 – Challenges for Neuro-Symbolic Approaches: Case Study on Legal Analytics and Argument Mining – Federico Ruggeri
11:50-12:00 – A neuro symbolic setup for link prediction in KGEs – Michelangelo Diligenti
12:00-12:10 – Three New Benchmarks for Neuro-Symbolic Systems – Fabrizio Riguzzi
12:10-12:20 – V-LoL: A Diagnostic Dataset for Visual Logical Learning – Devendra Singh Dhami
12:20-13:00 – Round Table Discussion - Michelangelo Diligenti and Francesco Giannini
1pm Lunch
2pm Opening (Tarek Besold, Artur d’Avila Garcez, Ernesto Jimenez-Ruiz, Marco Gori)
2:10pm Yann LeCun, Towards Machines that can Learn, Reason, and Plan (Chair: Eleonora Giunchiglia)
3:00pm Q&A with Yann LeCun
3:15pm Introduction to WebCrow Challenge and ROAD-R NeurIPS2023 Challenge (Marco Maggini and Eleonora Giunchiglia)
3:30pm Poster pitch 1 (chair: Tarek Besold) - 1min 45sec each
Maurizio Proietti and Francesca Toni. A roadmap for neuro-argumentative learning.
Kwun Ho Ngan, James Phelan, Esma Mansouri-Benssassi, Joe Townsend and Artur d'Avila Garcez. Closing the Neural-Symbolic Cycle: Knowledge Extraction, User Intervention and Distillation from Convolutional Neural Networks.
Luca Salvatore Lorello and Marco Lippi. The Challenge of Learning Symbolic Representations.
Mattijs Baert, Sam Leroux and Pieter Simoens. Learning Logic Constraints From Demonstration.
Jingyuan Sha, Hikaru Shindo, Kristian Kersting and Devendra Singh Dhami. Neural-Symbolic Predicate Invention: Learning Relational Concepts from Visual Scenes.
Davide Beretta, Stefania Monica and Federico Bergenti. Preliminary results on a state-driven method for rule construction in neural-symbolic reinforcement learning.
Thomas Eiter, Nelson Higuera and Johannes Oetsch. A Modular Neurosymbolic Approach for Visual Graph Question Answering.
Jędrzej Potoniec. Is the proof length a good indicator of hardness for reason-able embeddings?
Emanuele Marconato, Stefano Teso and Andrea Passerini. Neuro-Symbolic Reasoning Shortcuts: Mitigation Strategies and their Limitations.
Rory Ward, Muhammad Jaleed Khan, Edward Curry and John Breslin. Knowledge-Guided Colorization: Overview, Prospects and Challenges.
Gaia Saveri and Luca Bortolussi. Towards Invertible Semantic-Preserving Embeddings of Logical Formulae.
Matthew Brown, M. Wasil Wahi-Anwar, Youngwon Choi, Morgan Daly, Liza Shrestha, Koon-Pong Wong, Jonathan Goldin and Dieter Enzmann. Implementing trustworthy AI in real-world medical imaging using the SimpleMind software environment.
Kristian Hammond and David Leake. Large Language Models Need Symbolic AI.
Sofoklis Kyriakopoulos and Artur S. d'Avila Garcez. Continual Reasoning: Non-monotonic Reasoning in Neurosymbolic AI using Continual Learning.
Gabriele Ciravegna, Pietro Barbiero, Francesco Giannini, Marco Gori, Pietro Lio, Marco Maggini and Stefano Melacci. Logic Explained Networks.
Eleonora Misino, Giuseppe Marra and Emanuele Sansone. VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming.
3:55pm Best Paper Award (chair: Ernesto Jimenez-Ruiz)
4pm Coffee break
4:30pm-6pm Poster session 1
Maurizio Proietti and Francesca Toni. A roadmap for neuro-argumentative learning.
Kwun Ho Ngan, James Phelan, Esma Mansouri-Benssassi, Joe Townsend and Artur d'Avila Garcez. Closing the Neural-Symbolic Cycle: Knowledge Extraction, User Intervention and Distillation from Convolutional Neural Networks.
Luca Salvatore Lorello and Marco Lippi. The Challenge of Learning Symbolic Representations.
Mattijs Baert, Sam Leroux and Pieter Simoens. Learning Logic Constraints From Demonstration.
Jingyuan Sha, Hikaru Shindo, Kristian Kersting and Devendra Singh Dhami. Neural-Symbolic Predicate Invention: Learning Relational Concepts from Visual Scenes.
Davide Beretta, Stefania Monica and Federico Bergenti. Preliminary results on a state-driven method for rule construction in neural-symbolic reinforcement learning.
Thomas Eiter, Nelson Higuera and Johannes Oetsch. A Modular Neurosymbolic Approach for Visual Graph Question Answering.
Jędrzej Potoniec. Is the proof length a good indicator of hardness for reason-able embeddings?
Emanuele Marconato, Stefano Teso and Andrea Passerini. Neuro-Symbolic Reasoning Shortcuts: Mitigation Strategies and their Limitations.
Rory Ward, Muhammad Jaleed Khan, Edward Curry and John Breslin. Knowledge-Guided Colorization: Overview, Prospects and Challenges.
Gaia Saveri and Luca Bortolussi. Towards Invertible Semantic-Preserving Embeddings of Logical Formulae.
Matthew Brown, M. Wasil Wahi-Anwar, Youngwon Choi, Morgan Daly, Liza Shrestha, Koon-Pong Wong, Jonathan Goldin and Dieter Enzmann. Implementing trustworthy AI in real-world medical imaging using the SimpleMind software environment.
Kristian Hammond and David Leake. Large Language Models Need Symbolic AI.
Sofoklis Kyriakopoulos and Artur S. d'Avila Garcez. Continual Reasoning: Non-monotonic Reasoning in Neurosymbolic AI using Continual Learning.
Gabriele Ciravegna, Pietro Barbiero, Francesco Giannini, Marco Gori, Pietro Lio, Marco Maggini and Stefano Melacci. Logic Explained Networks.
Eleonora Misino, Giuseppe Marra and Emanuele Sansone. VAEL: Bridging Variational Autoencoders and Probabilistic Logic Programming.
7pm Dinner
9am Spotlight 1 (chair: Michelangelo Diligenti)
9am Cristina Cornelio, Jan Stuemer, Shell Xu Hu and Timothy Hospedales, Learning Where and When to Reason in Neuro-Symbolic Inference.
9:30am Michael Hersche, Mustafa Zeqiri, Luca Benini, Abu Sebastian and Abbas Rahimi, Solving Raven’s Progressive Matrices via a Neuro-Vector-Symbolic Architecture.
10am Ouns El Harzli, Samy Badreddine and Tarek Besold, What's Wrong with Gradient-based Complex Query Answering?
10:30am Poster pitch 2 (chair: Tarek Besold) - 1min 45sec each
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 and Chiara Vercellino. Designing Logic Tensor Networks for Visual Sudoku puzzle classification.
Roxana Pop and Egor V. Kostylev. Inductive Future Time Prediction on Temporal Knowledge Graphs with Interval Time.
Alberto Speranzon, Christian H. Debrunner, David Rosenbluth, Mauricio Castillo-Effen, Anthony R. Nowicki, Kevin Alcedo and Andrzej Banaszuk. Challenge Problems in Developing a NS OODA Loop.
Johanna Ott, Arthur Ledaguenel, Celine Hudelot and Mattis Hartwig. How to Think About Benchmarking Neurosymbolic AI?
Marc Otto, Octavio Arriaga, Chandandeep Singh, Jichen Guo and Frank Kirchner. PhysWM: Physical World Models for Robot Learning.
Flavio Petruzzellis, Alberto Testolin and Alessandro Sperduti. A hybrid system for systematic generalization in simple arithmetic problems.
Francesco S. Carzaniga, Michael Hersche, Kaspar Schindler and Abbas Rahimi. VSA-based positional encoding can replace recurrent networks in emergent symbol binding.
David Herron, Ernesto Jimenez-Ruiz and Tillman Weyde. On the benefits of OWL-based knowledge graphs for neural-symbolic systems.
Katrin Schreiberhuber, Marta Sabou, Fajar J. Ekaputra, Peter Knees, Peb Ruswono Aryan, Alfred Einfalt and Ralf Mosshammer. Causality prediction with neural-symbolic systems: A case study in smart grids.
Manuel Eberhardinger, Johannes Maucher and Setareh Maghsudi. Towards Explainable Decision Making with Neural Program Synthesis and Library Learning.
Michael Akintunde, Elena Botoeva, Panagiotis Kouvaros and Alessio Lomuscio. Verifying Strategic Abilities of Neural-symbolic Multi-agent Systems.
Wen-Chi Yang, Giuseppe Marra, Gavin Rens and Luc De Raedt. Safe Reinforcement Learning via Probabilistic Logic Shields.
N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir and Axel-Cyrille Ngonga Ngomo. Neural Class Expression Synthesis.
11am Coffee Break
11:30am Poster session 2
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 and Chiara Vercellino. Designing Logic Tensor Networks for Visual Sudoku puzzle classification.
Roxana Pop and Egor V. Kostylev. Inductive Future Time Prediction on Temporal Knowledge Graphs with Interval Time.
Alberto Speranzon, Christian H. Debrunner, David Rosenbluth, Mauricio Castillo-Effen, Anthony R. Nowicki, Kevin Alcedo and Andrzej Banaszuk. Challenge Problems in Developing a NS OODA Loop.
Johanna Ott, Arthur Ledaguenel, Celine Hudelot and Mattis Hartwig. How to Think About Benchmarking Neurosymbolic AI?
Marc Otto, Octavio Arriaga, Chandandeep Singh, Jichen Guo and Frank Kirchner. PhysWM: Physical World Models for Robot Learning.
Flavio Petruzzellis, Alberto Testolin and Alessandro Sperduti. A hybrid system for systematic generalization in simple arithmetic problems.
Francesco S. Carzaniga, Michael Hersche, Kaspar Schindler and Abbas Rahimi. VSA-based positional encoding can replace recurrent networks in emergent symbol binding.
David Herron, Ernesto Jimenez-Ruiz and Tillman Weyde. On the benefits of OWL-based knowledge graphs for neural-symbolic systems.
Katrin Schreiberhuber, Marta Sabou, Fajar J. Ekaputra, Peter Knees, Peb Ruswono Aryan, Alfred Einfalt and Ralf Mosshammer. Causality prediction with neural-symbolic systems: A case study in smart grids.
Manuel Eberhardinger, Johannes Maucher and Setareh Maghsudi. Towards Explainable Decision Making with Neural Program Synthesis and Library Learning.
Michael Akintunde, Elena Botoeva, Panagiotis Kouvaros and Alessio Lomuscio. Verifying Strategic Abilities of Neural-symbolic Multi-agent Systems.
Wen-Chi Yang, Giuseppe Marra, Gavin Rens and Luc De Raedt. Safe Reinforcement Learning via Probabilistic Logic Shields.
N'Dah Jean Kouagou, Stefan Heindorf, Caglar Demir and Axel-Cyrille Ngonga Ngomo. Neural Class Expression Synthesis.
Michael Hersche, Mustafa Zeqiri, Luca Benini, Abu Sebastian and Abbas Rahimi. Solving Raven's Progressive Matrices via a Neuro-vector-symbolic Architecture.
Cristina Cornelio, Jan Stuemer, Shell Xu Hu and Timothy Hospedales. Learning Where and When to Reason in Neuro-Symbolic Inference.
Ouns El Harzli, Samy Badreddine and Tarek Besold. What's Wrong with Gradient-based Complex Query Answering?
1pm Lunch
2pm Leslie Valiant. Augmenting Learning with Reasoning (chair: Artur d’Avila Garcez)
3pm Spotlight 2 (chair: Stefano Melacci)
3:00pm Elena Umili, Francesco Argenziano, Aymeric Barbin and Roberto Capobianco, Visual Reward Machines.
3:30pm Moa Johansson and Nicholas Smallbone, Exploring Mathematical Conjecturing with Large Language Models.
4pm Coffee Break
4:30pm Spotlight 2 (cont.) (chair: Stefano Melacci)
4:30pm Daniel Silver and Tom Mitchell, The Roles of Symbols in Neural-based AI: They are not what you think!
5:00pm-6pm Fosca Giannotti. eXplainable AI (XAI): paradigms in support of synergistic human-machine interaction and collaboration (chair: Tarek Besold)
6:30pm Dinner
9am Spotlight 3 (chair: Ernesto Jimenez-Ruiz)
9am Vitor Horta, Alessandra Mileo, Maarten Stol and Robin Sobczyk, Semantic Interpretability of Convolutional Neural Networks by Taxonomy Extraction.
9:30am Alessandro Daniele, Tommaso Campari, Sagar Malhotra and Luciano Serafini, Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions.
10am Fernando Zhapa-Camacho and Robert Hoehndorf, From axioms over graphs to vectors, and back again: evaluating the properties of graph-based ontology embeddings.
10:30am Poster pitch 3 (chair: Tarek Besold) - 1min 45sec each
Mihaela C. Stoian, Eleonora Giunchiglia and Thomas Lukasiewicz. Exploiting t-norms for deep learning in autonomous driving.
Mouloud Iferroudjene, Victor Charpenay and Antoine Zimmermann. FB15k-CVT: A challenging dataset for knowledge graph embedding models.
Abhinav Thakur, Filip Ilievski, Hong-An Sandlin, Zhivar Sourati, Luca Luceri, Riccardo Tommasini and Alain Mermoud. Explainable Classification of Internet Memes.
Emanuele Marconato, Andrea Passerini and Stefano Teso. GlanceNets: Interpretable, Leak-proof Concept-based Models.
Kareem Ahmed, Stefano Teso, Kai-Wei Chang, Guy Van den Broeck and Antonio Vergari. Semantic Probabilistic Layers for Neuro-Symbolic Learning.
Lucile Dierckx, Rosana Veroneze and Siegfried Nijssen. RL-Net: Interpretable Rule Learning with Neural Networks.
Alessandro Oltramari. Generalizable Neuro-Symbolic Systems for Commonsense Question Answering.
Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini, Mateo Espinosa Zarlenga, Lucie Charlotte Magister, Alberto Tonda, Pietro Lio, Frederic Precioso, Mateja Jamnik and Giuseppe Marra. Interpretable Neural-Symbolic Concept Reasoning.
Anna Breit, Laura Waltersdorfer, Fajar J. Ekaputra, Marta Sabou, Andreas Ekelhart, Andreea Iana, Heiko Paulheim, Jan Portisch, Artem Revenko, Frank Van Harmelen and Annette ten Teije. Combining Machine Learning and Semantic Web: A Systematic Mapping Study.
Michael Hersche, Zuzanna Opala, Geethan Karunaratne, Abu Sebastian and Abbas Rahimi. Decoding Superpositions of Bound Symbols Represented by Distributed Representations.
11am Coffee break
11:30am Posters session 3
Mihaela C. Stoian, Eleonora Giunchiglia and Thomas Lukasiewicz. Exploiting t-norms for deep learning in autonomous driving.
Mouloud Iferroudjene, Victor Charpenay and Antoine Zimmermann. FB15k-CVT: A challenging dataset for knowledge graph embedding models.
Abhinav Thakur, Filip Ilievski, Hong-An Sandlin, Zhivar Sourati, Luca Luceri, Riccardo Tommasini and Alain Mermoud. Explainable Classification of Internet Memes.
Emanuele Marconato, Andrea Passerini and Stefano Teso. GlanceNets: Interpretable, Leak-proof Concept-based Models.
Kareem Ahmed, Stefano Teso, Kai-Wei Chang, Guy Van den Broeck and Antonio Vergari. Semantic Probabilistic Layers for Neuro-Symbolic Learning.
Lucile Dierckx, Rosana Veroneze and Siegfried Nijssen. RL-Net: Interpretable Rule Learning with Neural Networks.
Alessandro Oltramari. Generalizable Neuro-Symbolic Systems for Commonsense Question Answering.
Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini, Mateo Espinosa Zarlenga, Lucie Charlotte Magister, Alberto Tonda, Pietro Lio, Frederic Precioso, Mateja Jamnik and Giuseppe Marra. Interpretable Neural-Symbolic Concept Reasoning.
Anna Breit, Laura Waltersdorfer, Fajar J. Ekaputra, Marta Sabou, Andreas Ekelhart, Andreea Iana, Heiko Paulheim, Jan Portisch, Artem Revenko, Frank Van Harmelen and Annette ten Teije. Combining Machine Learning and Semantic Web: A Systematic Mapping Study.
Michael Hersche, Zuzanna Opala, Geethan Karunaratne, Abu Sebastian and Abbas Rahimi. Decoding Superpositions of Bound Symbols Represented by Distributed Representations.
Daniel Silver and Tom Mitchell. The Roles of Symbols in Neural-based AI: They are Not What You Think!
Elena Umili, Francesco Argenziano, Aymeric Barbin and Roberto Capobianco. Visual Reward Machines.
Moa Johansson and Nicholas Smallbone. Exploring Mathematical Conjecturing with Large Language Models.
Vitor Horta, Alessandra Mileo, Maarten Stol and Robin Sobczyk. Semantic Interpretability of Convolutional Neural Networks by Taxonomy Extraction.
Alessandro Daniele, Tommaso Campari, Sagar Malhotra and Luciano Serafini. Deep Symbolic Learning: Discovering Symbols and Rules from Perceptions.
Fernando Zhapa-Camacho and Robert Hoehndorf. From axioms over graphs to vectors, and back again: evaluating the properties of graph-based ontology embeddings.
1pm Lunch
2pm: Applied NeSy session (chairs: Dragos Margineantu and Alberto Speranzon)
2pm Denis Osipychev, Dragos Margineantu and Girish Chowdhary. Remain Well Clear: Reinforcement Learning-Based Air Traffic Deconfliction.
2:20pm Alvaro Velasquez (DARPA Program Manager) Assured Neuro Symbolic Learning and Reasoning program.
3:00pm Kwun Ho Ngan, James Phelan, Esma Mansouri-Benssassi, Joe Townsend and Artur d'Avila Garcez, Closing the Neural-Symbolic Cycle: Knowledge Extraction, User Intervention and Distillation from Convolutional Neural Networks.
3:20pm Mihaela C. Stoian, Eleonora Giunchiglia and Thomas Lukasiewicz. Exploiting T-norms for Deep Learning in Autonomous Driving.
3:40pm Alberto Speranzon, Christian H. Debrunner, David Rosenbluth, Mauricio Castillo-Effen, Anthony R. Nowicki, Kevin Alcedo and Andrzej Banaszuk. Challenge Problems in Developing a Neurosymbolic Observe–Orient–Decide–Act Loop.
4pm Coffee Break
4:30pm NeSy challenge (chair: Pranava Madhyastha)
4:30pm Introduction (Pranava Madhyastha)
4:40pm Murray Campbell, IBM Research (virtual)
5pm-5:30pm Roundtable Discussion
5:30pm NeSy2024 and Closing (Artur d’Avila Garcez, Tarek Besold)