AIxIA 2021


PROGRAM


Main Conference, December 1 - 3, 2021

online event

Program at a glance (download).

December 1, 2021

December 1, 2021

9:00-9:10am

Welcome and opening session

Piero Poccianti - President of AIxIA


Stefania Bandini - General Chair of AIxIA 2021

University of Milano-Bicocca and RCAST - The University of Tokyo


9:10-9.20am


Roberto Viola

Director-General, DG Connect, European Commission

9:20-9:30am

Luigia Carlucci Aiello

Celebration of the AIxIA honorary membership to the Nobel Prize Giorgio Parisi


Technical Session #1

Planning and strategies

9.30-11.10am

Chair

Andrea Orlandini

9:30-9:50am

Hossein Karami, Antony Thomas, Fulvio Mastrogiovanni

Task Allocation for Multi-Robot Task and Motion Planning: a case for Object Picking in Cluttered Workspaces (video)

9:50-10:10am

Hossein Karami, Alessandro Carfì, Fulvio Mastrogiovanni

Branched AND/OR Graphs: Toward Flexible and Adaptable Human-Robot Collaboration (video)

10:10-10.30am

Francesco Percassi, Enrico Scala, Mauro Vallati

A Sound (but Incomplete) Polynomial Translation from Discretised PDDL+ to Numeric Planning (video)

10:30-10:50am

Riccardo De Benedictis, Gloria Beraldo, Rami Reddy Devaram, Amedeo Cesta, Gabriella Cortellessa

Enhancing Telepresence Robots with AI: Combining Services to Personalize and React (video)

10:50-11:10am

Roberto Gallotta, Roberto Capobianco

Tafl-ES: Exploring Evolution Strategies for Asymmetrical Board Games (video)


Little Break

11:10-11:20am


Technical Session #2

Machine learning for argumentation, explanation, and exploration

11:20am-1:00pm

Chair

Angelo Ferrando

11:20-11:40am

Federico Cerutti

Supporting Trustworthy Artificial Intelligence via Bayesian Argumentation (video)

11:40-12:00pm

Biagio La Rosa, Roberto Capobianco, Daniele Nardi

Explainable Inference on Sequential Data via Memory-Tracking (video)

12:00-12:20pm

Nicola Picchiotti, Marco Gori

Logic Constraints to Feature Importances (video)

12:20-12:40pm

Nicola Picchiotti,Marco Gori

Clustering-Based Interpretation of Deep ReLU Network (video)

12:40-1:00pm

Jim Martin Catacora Ocaña, Roberto Capobianco, Daniele Nardi

Exploration-Intensive Distractors: Two Environment Proposals and a Benchmarking (video)


Lunch Break

1:00-2:00pm


Technical Session #3

Knowledge representation, reasoning, and learning

2:00-3:40pm

Chair

Viviana Mascardi

2.:00-2:20pm

Valeria Fionda, Gianluigi Greco, Marco Mastratisi

Reasoning about Smart Contracts encoded in LTL (video)

2:20-2:40pm

Sagar Malhotra, Luciano Serafini

A Combinatorial Approach to Weighted Model Counting in the Two Variable Fragment with Cardinality Constraints (video)

2:40-3:00pm

Valeria Fionda, Giuseppe Pirrò

From Node Embeddings to Triple Embeddings (video)

3:00-3:20pm

Laura Giordano, Daniele Theseider Dupré

Multilayer Perceptrons as Weighted Conditional Knowledge Bases: an Overview (video)

3:20-3:40pm

Jason Dellaluce, Roberta Calegari, Giovanni Ciatto

Probabilistic Logic Programming in 2p-kt (video)


Little Break

3:40-4:00pm


Invited Talk

Chair

Giuseppe Vizzari

4:00-5:00pm


Pascal Hitzler

Department of Computer Science, Kansas State University (USA)

Neuro-Symbolic Deep Deductive Reasoning (video)


Technical Session #4

Constraints and logic programming

5:00-6:00pm

Chair

Roberta Calegari

5:00-5:20pm

Fernanda N. T. Furukita, Fernando J. M. Marcellino, Jaime Sichman

Combining DCOP and MILP for Complex Local Optimization Problems (video)

5:20-5:40pm

Stefano Demarchi, Marco Menapace, Armando Tacchella

Automated Design of Elevator Systems: Experimenting with Constraint-Based Approaches (video)

5:40-6:00pm

Roberta Calegari, Giuseppe Contissa, Giuseppe Pisano, Galileo Sartor, Giovanni Sartor

Modular logic argumentation in Arg-tuProlog (video)


OPEN EVENT (in Italian)

INTELLIGENZA ARTIFICIALE PER LA SOSTENIBILITA'

6:00-7:30PM

Chair

Piero Poccianti - Presidente AIxIA


In questo evento, aperto al pubblico esterno, verrà presentato il libro "L'Intelligenza Artifiale per lo Sviluppo Sostenibile", scaricabile da VOLUME FULL 14 digital LIGHT.pdf (cnr.it).


Il volume parte dalla fotografia di cosa sia l’Intelligenza Artificiale (IA) oggi al di là dei miti e degli stereotipi, per evidenziarne potenzialità e rischi in relazione alle diverse sfide globali: cuore del libro è, infatti, la relazione tra questa disciplina e i 17 Sustainable Development Goals definiti dall’Agenda 2030 dell’ONU quali fame, salute, riduzione delle diseguaglianze, crisi ambientale, eccetera. La motivazione per un contributo cosi’ corposo nasce dal constatare che il diffuso timore sui risultati che l'Intelligenza Artificiale sta portando. In realtà la crisi che stiamo vivendo non è generata dall'IA, ma da un modello socio economico che si trova ad affrontare sfide senza precedenti nella storia: portare benessere a 7,6 milirdi di persone senza distruggere il pianeta che ci permette di vivere. Per far questo avremo bisogno di tutti gli strumenti che possiamo mettere in campo e l'Intelligenza Artificiale in questo momento è uno dei più potenti.


Partecipanti:


Emanuela Girardi

Founder e Ceo di POP AI


Francesca Lisi

Università di Bari


L'evento prosegue con una interessante competizione tra studenti delle scuole superiori sul tema dell'evento stesso.


Per partecipare all'evento:


Intelligenza Artificiale per lo Sviluppo Sostenibile Biglietti, Mer, 01 dic 2021 alle 18:00 | Eventbrite


Link per la partecipazione:


http://s.unimib.it/iasostenibile


December 2, 2021

Technical Session #5

Signal processing

9:00-11:00am

Chair

Francesca Gasparini

9:00-9:20am

Dalila Ressi, Mara Pistellato, Andrea Albarelli, Filippo Bergamasco

A Relevance-Based CNN Trimming Method for Low-Resources Embedded Vision (video)

9:20-9:40am

Giorgio De Magistris, Riccardo Caprari, Giulia Castro, Samuele Russo, Daniele Nardi, Luca Iocchi, Christian Napoli

Vision-based holistic scene understanding for context-aware human-robot interaction (video)

9:40-10:00am

Sergio Caputo, Giovanna Castellano, Francesco Greco, Corrado Mencar, Niccolò Petti, Gennaro Vessio

Human Detection in Drone Images Using YOLO for Search-and-Rescue Operations (video)

10:00-10:20am

Veronica Juliana Schmalz

Real-time Italian Sign Language Recognition with Deep Learning (video)

10:20-10:40am

Simone Bianco, Luigi Celona, Intissar Khalifa, Paolo Napoletano, Alexey Petrovsky, Flavio Piccoli, Raimondo Schettini Ivan Shanin

ArabCeleb: Speaker Recognition in Arabic (video)

10:40-11:00am

Intissar Khalifa, Ridha Ejbali, Paolo Napoletano, Raimondo Schettini and Mourad Zaied

Static, Dynamic and Acceleration Features for CNN-based Speech Emotion Recognition (video)


Little Break

11:00-11:20am


Technical Session #6

Natural language processing

11:20am-1:00pm

Chair

Elisabetta Fersini

11:20-11:40am

Manuel Borroto, Francesco Ricca, Bernardo Cuteri

A neural-machine-translation system resilient to out of vocabulary words for translating natural language to SPARQL (video)

11:40am-12:00pm

Emilio Sulis, Llio Bryn Humphreys, Davide Audrito, Luigi Di Caro

Exploiting textual similarity techniques in harmonization of laws (video)

12:00-12:20pm

Marco Anteghini, Jennifer D'Souza, Vitor A.P. Martins Dos Santos, Sören Auer

Easy Semantification of Bioassays (video)

12:20-12:40pm

Melika Golestani, Seyedeh Zahra Razavi, Zeinab Borhanifard, Farnaz Tahmasebian, Hesham Faili

Pruned Graph Neural Network for Short Story (video)

12:40-1:00pm

Temirlan Auyespek, Thomas Mach and Zhenisbek Assylbekov

Hyperbolic Embedding for Finding Syntax in BERT (video)


Lunch Break

1:00-2:00pm


Presentazione dei candidati al ruolo di Membri del Direttivo AIxIA

2:00-3:00pm

Link per il collegamento:

https://unimib.webex.com/unimib/j.php?MTID=maed0ce78971572d7b8682f4f5b79c991

Event number: 2673 750 2271

Event password: brCZxpWq534 (27299797 from phones)

Join by phone

+39 0230410 440 Italy toll

+39-06-9974-8087 Italy Toll 2

Access code: 267 375 02271 --


AIxIA awards

Chair presentation

Stefania Costantini

3:00-3:05pm

Premio tesi di laurea

13:05-3:15pm

Premio tesi di dottorato

3:15-3:30pm

Premio giovane ricercatore

3:30-3:45pm


Little Break

3:45-4:00pm


Invited Talk

4:00-5:00pm

Chair

Matteo Palmonari


Evelina Fedorenko

Massachussets Institute for Tecnology (USA)

The language system in the human brain (video)


Pre-Assemblea dei soci AIxIA

5:00-7:00pm

Link per il collegamento:

https://unimib.webex.com/unimib/j.php?MTID=m125c7e9c23516b125db6b7d67c7b6c5d

Event number: 2673 887 1397

Event password: 4EkwPYSr5K3 (43597977 from phones)

Join by phone

+39 0230410 440 Italy toll

+39-06-9974-8087 Italy Toll 2

Access code: 267 388 71397

December 3, 2021

Technical Session #7

Machine learning and applications 1

9:00-11:00am

Chair

Cataldo Musto

9:00-9:20am

Kaveena Persand, Andrew Anderson, David Gregg

Domino Saliency Metrics: Improving Existing Channel Saliency Metrics with Structural Information (video)

9:20-9:40am

Domenico Amato, Giosue Lo Bosco, Raffaele Giancarlo

Learned Sorted Table Search and Static Indexes in Small Model Space (video)

9:40-10:00am

Luigi Quaranta, Fabio Calefato, Filippo Lanubile

A Taxonomy of Tools for Reproducible Machine Learning Experiments (video)

10:00-10:20am

Giuseppina Andresini, Annalisa Appice, Domenico Dell'Olio, Donato Malerba

Siamese Networks with Transfer Learning for Change Detection in Sentinel-2 Images (video)

10:20-10:40am

Salvatore Gaglio, Andrea Giammanco, Giuseppe Lo Re, Marco Morana

Adversarial Machine Learning in e-Health: attacking a Smart Prescription System (video)

10:40-11:00am

Tuan Pham

Deep Learning of Recurrence Texture in Physiological Signals (video)


Little Break

11.00-11.20


Technical Session #8

AI and applications

11:20am-1:00pm

Chair

Matteo Baldoni

11:20-11:40am

Allegra De Filippo, Michele Lombardi, Michela Milano

Robust optimization models for local flexibility characterization of Virtual Power Plants (video)

11:40am-12:00pm

Feras Batarseh, Dominick Perini, Qasim Wani, Laura Freeman

Explainable Artificial Intelligence for Technology Policy Making Using Attribution Networks (video)

12:00-12:20pm

Giovanna Castellano, Gennaro Vessio

Understanding Art with AI: Our Research Experience (video)

12:20-12:40pm

Salvatore Iiritano, Massimiliano Ruffolo, Simone Vizza, Giuseppe Benvenuto, Pasquale Piccione, Luigi Mirto, Francesco Ricca, Manuel Borroto

Hydrocontrol IT: an attempt to mitigate water losses in Italy towns (video)

12:40-1:00pm

Thomas Cecconello, Lucas Puerari, Giuseppe Vizzari

Unsupervised Data Pattern Discovery on the Cloud (video)


Lunch Break

1:00-2:00pm


Technical Session #9

Machine learning and applications 2

2:00-3:40pm

Chair

Fabio Stella

2:00-2:20pm

Ahmed Badar, Arnav Varma, Adrian Staniec, Mahmoud Gamal, Omar Magdy, Haris Iqbal, Elahe Arani, Bahram Zonooz

Highlighting the Importance of Reducing Research Bias and Carbon Emissions in CNNs (video)

2:20-2:40pm

Vitor Horta, Alessandra Mileo

Generating textual explanations for CNNs using knowledge graphs (video)

40-3:00pm

Sayo M. Makinwa, Biagio La Rosa, Roberto Capobianco

Detection Accuracy for Evaluating Compositional Explanations of Units (video)

3:00-3:20pm

Daniele Margiotta, Danilo Croce, Marco Rotoloni, Barbara Cacciamani, Roberto Basili

Knowledge-based neural pre-training for Intelligent Document Management (video)

3:20-3:40pm

Youness Moukafih, Nada Sbihi, Mounir Ghogho, Kamel Smaili

Improving Machine Translation of Arabic Dialects through Multi-Task Learning (video)


Little Break

3:40-4:00pm


Technical Session #10

AI for content and social media analysis

4:00-5:00pm

Chair

Marco Viviani

4:00-4:20pm

Cataldo Musto, Pasquale Lops, Giovanni Semeraro

Fairness: Popularity Bias in Recommender Systems: an Empirical Evaluation (video)

4:20-4:40pm

Vincenzo Auletta, Antonio Coppola, Diodato Ferraioli

On the Impact of Social Media Recommendations on Opinion Consensus (video)

40-5.00pm

Elisabetta Fersini, Giulia Rizzi, Aurora Saibene, Francesca Gasparini

Misogynous MEME Recognition: A Preliminary Study (video)


Closing session and greetings

5:00-5:15pm

Piero Poccianti

Presidente AIxIA


Stefania Bandini

Conference General Chair


Francesca Gasparini

Organization Chair


Viviana Mascardi, Matteo Palmonari, Giuseppe Vizzari

Program Chairs

Invited Speakers

Massachusetts Institute of Technology (USA)


Recording of the Invited Talk: video

Dr. Fedorenko is a cognitive neuroscientist who studies the human language system. She received her bachelor’s degree from Harvard University in 2002, and her Ph.D. from the Massachusetts Institute of Technology in 2007. She was then awarded a K99R00 career development award from the National Institute for Child Health and Human Development at the U.S. National Institutes of Health. In 2014, she joined the faculty at Harvard Medical School/Massachusetts General Hospital in Boston, and in 2019 she returned to MIT where she is currently the Frederick A. (1971) and Carole J. Middleton Career Development Associate Professor of Neuroscience in the Brain and Cognitive Sciences Department and the McGovern Institute for Brain Research. Dr. Fedorenko uses fMRI, intracranial recordings and stimulation, EEG/ERPs, MEG, as well as computational modeling, to study adults and children, including those with developmental and acquired brain disorders.

The language system in the human brain

The goal of my research program is to understand the representations and computations that enable us to share complex thoughts with one another via language, and their neural implementation. A decade ago, I developed a robust new approach to the study of language in the brain based on identifying language-responsive cortex functionally in individual participants. Originally developed for fMRI, we have since extended this approach to other modalities, like intracranial recordings. Using this functional-localization approach, I identified and characterized a set of frontal and temporal brain areas that i) support language comprehension and production (spoken and written); ii) are robustly separable from the lower-level perceptual (e.g., speech processing) and motor (e.g., articulation) brain areas; iii) are spatially and functionally similar across diverse languages (>40 languages from 11 language families); and iv) form a functionally integrated system with substantial redundancy across different components. In this talk, I will highlight a few discoveries from the last decade and argue that the primary goal of language is efficient information transfer rather than enabling complex thought, as has been argued in one prominent philosophical and linguistic tradition (e.g., Wittgenstein, 1921; Berwick & Chomsky, 2016). I will use two kinds of evidence to make this argument. */First/*, I will examine the relationship between language and other aspects of cognition, including social cognitive abilities and complex thought/reasoning. I will show that the language brain regions are highly selective for language over diverse non-linguistic processes while also showing a deep and intriguing link with a system that supports social cognition. And /*second*/, I will examine different properties of language and argue that language both has a) properties that make it well-suited for communication, and b) properties that make it not suitable for complex thought. Both of these lines of evidence support the communicative function of language, and suggest that the idea that language evolved to allow for more complexity in thought is unlikely.

Department of Computer Science at Kansas State University (USA)


Recording of the Invited Talk: video

Pascal Hitzler is Professor and endowed Lloyd T. Smith Creativity in Engineering Chair and Director of the Center for Artificial Intelligence and Data Science (CAIDS) at the Department of Computer Science at Kansas State University. Until July 2019 he was endowed NCR Distinguished Professor, Brage Golding Distinguished Professor of Research, and Director of Data Science at the Department of Computer Science and Engineering at Wright State University in Dayton, Ohio, U.S.A. He is director of the Data Semantics (DaSe) Lab. From 2004 to 2009, he was Akademischer Rat at the Institute for Applied Informatics and Formal Description Methods (AIFB) at the University of Karlsruhe in Germany, and from 2001 to 2004 he was postdoctoral researcher at the Artificial Intelligence institute at TU Dresden in Germany. In 2001 he obtained a PhD in Mathematics from the National University of Ireland, University College Cork, and in 1998 a Diplom (Master equivalent) in Mathematics from the University of Tübingen in Germany. His research record lists over 400 publications in such diverse areas as semantic web, artificial intelligence, neural-symbolic integration, knowledge representation and reasoning, machine learning, denotational semantics, and set-theoretic topology. His research is highly cited. He is founding Editor-in-chief of the Semantic Web journal, the leading journal in the field, and of the IOS Press book series Studies on the Semantic Web. He is co-author of the W3C Recommendation OWL 2 Primer, and of the book Foundations of Semantic Web Technologies by CRC Press, 2010, which was named as one out of seven Outstanding Academic Titles 2010 in Information and Computer Science by the American Library Association's Choice Magazine, and has translations into German and Chinese. He is on the editorial board of several journals and book series and a founding steering committee member of the Neural-Symbolic Learning and Reasoning Association and the Association for Ontology Design and Patterns, and he frequently acts as conference chair in various functions, including e.g. General Chair (ESWC2019, us2ts2019), Program Chair (FOIS 2018, AIMSA2014), Track Chair (ISWC2018, ESWC2018, ISWC2017, ISWC2016, AAAI-15), Workshop Chair (K-Cap2013), Sponsor Chair (ISWC2013, RR2009, ESWC2009), PhD Symposium Chair (ESWC 2017). For more information about him, see http://www.pascal-hitzler.de.

Neuro-Symbolic Deep Deductive Reasoning

Symbolic knowledge representation and reasoning and deep learning are fundamentally different approaches to artificial intelligence with complementary capabilities. The former are transparent and data-efficient, but they are sensitive to noise and cannot be applied to non-symbolic domains where the data is ambiguous. The latter can learn complex tasks from examples, are robust to noise, but are black boxes; require large amounts of - not necessarily easily obtained - data, and are slow to learn and prone to adversarial examples. Either paradigm excels at certain types of problems where the other paradigm performs poorly. In order to develop stronger AI systems, integrated neuro-symbolic systems that combine artificial neural networks and symbolic reasoning are being sought. In this context, one of the fundamental open problems is how to perform logic-based deductive reasoning over knowledge bases by means of trainable artificial neural networks. In this talk we will present and discuss recent advances made on this topic, and concrete pointers to open research questions.