Attendace

Following the AIxIA 2020 organization, the workshop will be fully virtual. The presentations will be based on short videos, on short discussions (live) and on a further discussion forum (by the Slack platform). Videos of the presentations will be made available to the participants 4 - 5 days before the events. The AIxIA Slack MLDM channel will be also used for the communications and to announce the links to the live sessions.
Please, see the full attendace information at https://aixia2020.di.unito.it/venue/attendance

MLDM.it 2020 Program

Abstracts of contributions are linked in the titles.
(*) = open challenge contribution

14.40 Contributions (5 min video presentation + 5 min discussion)

Improving the Union Bound: a Distribution Dependent Approach
(Luca Oneto, Sandro Ridella, and Davide Anguita)

Estimating Correlations of Random Classifiers on Large Data Sets
(Věra Kůrková, Marcello Sanguineti)

A Closed form for Weighted Model Counting in C2
(Sagar Malhotra, Luciano Serafini)

Graph–based integration of histone modifications profiles: haematopoietic cell differentiation as a case study
(Federica Baccini, Monica Bianchini, Filippo Geraci)

Cluster analysis of single-cell RNA sequencing data via deep variational autoencoders (*)
(Silvia Galfrè, Francesco Morandin, Rosa Gini, Maurizio Parton)

DeepMind AlphaFold explained (*)
(Maurizio Parton, Silvia Galfrè, Rosa Gini, Francesco Morandin)

10.40 Contributions (5 min video presentation + 5 min discussion)

Non-Linear Activation Functions in Quantum Neural Networks (*)
(Antonio Macaluso, Stefano Lodi, Claudio Sartori)

CleanAir: a neural network approach to city pollution monitoring
(Alessandro Abluton, Attilio Giordana, Luigi Portinale)

Open challenges in speech emotion recognition (*)
(Stefano Rovetta, Zied Mnasri, Alberto Cabri, Francesco Masulli)

Detecting and Explaining Unfairness in Consumer Contracts with Memory Networks (*)
(Francesca Lagioia, Marco Lippi, Federico Ruggeri, Paolo Torroni)

Memory augmented networks for multiple trajectory prediction
(Francesco Marchetti, Federico Becattini, Lorenzo Seidenari, Alberto Del Bimbo)

Exploiting VAE distribution to detect anomalies
(Fabrizio Angiulli, Fabio Fassetti, Luca Ferragina)

A SOM-based implementation of DeepSets for Graph Convolutional Networks
(Luca Pasa, Nicolò Navarin, Alessandro Sperduti)

Molecular Graph Generation with Graph Neural Networks
(Pietro Bongini, Monica Bianchini, Franco Scarselli)

Challenges in Graph Representation Learning: Robustness and Interpretability (*)
(Simone Scardapane, Indro Spinelli, Beatrice Bevilacqua)

10.40 Contributions (5 min video presentation + 5 min discussion)

Probabilistic Learning in logic
(Marco Alberti, Damiano Azzolini, Elena Bellodi, Giuseppe Cota, Michele Fraccaroli, Evelina Lamma, Arnaud Nguembang Fadja, Fabrizio Riguzzi, Riccardo Zese)

Exploiting auto-encoders for explaining black box classifiers
(Riccardo Guidotti, Anna Monreale)

Global eXplainable Artificial Intelligence measures
(Paolo Giudici, Emanuela Raffinetti)

Current and Future of Meta-Learning
(Lorenzo Vaccaro, Giuseppe Sansonetti, Alessandro Micarelli)

Probabilistic Reconciliation of Hierarchical Forecast via Bayes’ Rule
(Giorgio Corani, Dario Azzimonti, Joo P.S.C. Augusto, Marco Zaffalon)

Efficient Generation of Structured Objects with Constrained Adversarial Networks
(Luca Di Liello, Pierfrancesco Ardino, Jacopo Gobbi, Paolo Morettin, Stefano Teso, Andrea Passerini)

Machine learning for early outcome detection in COVID-19 patients
(Alina Sirbu, Greta Barbieri, Francesco Faita, Paolo Ferragina, Luna Gargani, Lorenzo Ghiadoni, Corrado Priami)

Integrating Actionable Ethics and Neural Learning
(Danilo Croce, Daniele Rossini, Roberto Basili)