logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-09082020-232932


Tipo di tesi
Tesi di laurea magistrale
Autore
NUMEROSO, DANILO
URN
etd-09082020-232932
Titolo
Explaining Deep Graph Networks by Structured Counterfactual Generation
Dipartimento
INFORMATICA
Corso di studi
INFORMATICA
Relatori
relatore Dott. Bacciu, Davide
Parole chiave
  • explainability
  • graph generation
  • graph neural network
  • reinforcement learning
Data inizio appello
09/10/2020
Consultabilità
Tesi non consultabile
Riassunto
Deep Graph Networks are a set of powerful models for solving complex graph-related tasks and have become an interesting research topic that has been consistently growing in popularity in the latest years. However, providing explanations for their predictions is an extremely difficult time-demanding task and is still an open research area. In contrast to the significant amount of work that has been done for the interpretation of vectorial deep learning models, explainability on deep graph networks is still a wide unexplored area.
Based on the current literature, this work tackles the explainability problem for deep graph networks by generating counterfactual explanations in a chemical context. Given an instance and its prediction made by the deep graph network being explained, the generation is formulated as a reinforcement learning problem, in which the generative agent learns to modify the original query graph the least, in order to obtain a substantial change of prediction. Finally, we employ GNNExplainer, a model-agnostic local interpretation method, to produce explanations on both the input graph and its counterfactual explanations, in order to analyse how it behaves in the range of a given input.
File