Workshop Program

Workshop Day: November 30, 2021

Invited Talk

  • When: November 30, h.14.15
  • Speaker: Fabrizio Silvestri, Sapienza University of Rome
  • Title: Counterfactual Explanations of Machine Learning Models

  • Abstract: This talk will review two counterfactual explanation mechanisms of ML models. We propose an algorithm for tweaking input features to change the output predicted by an existing machine-learned model. Our method is designed to operate on top of any tree-based ensemble binary classier, although it can be extended to multiclass classification. Our proposed algorithm exploits the internals of the model to generate recommendations for transforming true negative instances into positively predicted ones (or vice versa). The second part will review CF-GNNEXPLAINER: the first method for generating counterfactual explanations for GNNs, i.e., the minimal perturbations to the input graph data such that the prediction changes. Using only edge deletions, we find that we can generate counterfactual examples for the majority of instances across three widely used datasets for GNN explanations while removing less than three edges on average, with at least 94% accuracy.

  • Bio: Fabrizio Silvestri is a Full Professor at the Computer Engineering Dept. of the Sapienza University of Rome. Formerly a Research Scientist at Facebook AI in London, his interests are in AI applied to integrity-related problems and the application of Natural Language Processing. In the past, he has worked on web search research, and in particular, his specialization is building systems to better interpret queries s from search users. Prior to Facebook, Fabrizio was a principal scientist at Yahoo where he has worked on sponsored search and native ads within the Gemini project. Fabrizio holds a Ph.D. in Computer Science from the University of Pisa, Italy where he studied problems related to Web Information Retrieval with a particular focus on Efficiency-related problems like Caching, Collection Partitioning, and Distributed IR in general.


  • h.14.00 - 14.10, Workshop Opening
  • Cataldo Musto, University of Bari

  • h.14.10 - 15.00, Invited Talk
  • Fabrizio Silvestri, Sapienza University of Rome- Counterfactual Explanations of Machine Learning Models

  • h.15.00 - 16.00, Session 1
  • (15 min. presentation + 5 min. discussion per paper)
  • Ivan Donadello and Mauro Dragoni - Bridging Signals to Natural Language Explanations With Explanation Graphs

  • Federico Cabitza and Andrea Campagner - Quod erat demonstrandum? Tackling the concept of explanation to make AI explainable

  • Stefano Teso, Andrea Bontempelli, Fausto Giunchiglia and Andrea Passerini - Interactive Label Cleaning with Example-based Explanations

  • h.16.00 - 16.30, Break

  • h.16.30 - 17.50, Session 2
  • (15 min. presentation + 5 min. discussion per paper)
  • Martin Jullum, Annabelle Redelmeier and Kjersti Aas - Efficient and simple prediction explanations with groupShapley: A practical perspective

  • Andrea Apicella, Salvatore Giugliano, Francesco Isgrò and Roberto Prevete - Explanations in terms of Hierarchically organised Middle Level Features

  • Rodolfo Delmonte - What’s Wrong with Deep Learning for Meaning Understanding

  • Purin Sukpanichnant, Antonio Rago, Piyawat Lertvittayakumjorn and Francesca Toni - LLRP-Based Argumentative Explanations for Neural Networks

  • h.17.50 - 18.00, Workshop Closing