Timezone: »

 
Human Interventions in Concept Graph Networks
Lucie Charlotte Magister · Pietro Barbiero · Dmitry Kazhdan · Federico Siciliano · Gabriele Ciravegna · Fabrizio Silvestri · Mateja Jamnik · Pietro Lió

@
in Human in the Loop Learning (HiLL) Workshop at NeurIPS 2022 »

Deploying Graph Neural Networks requires trustworthy models whose interpretable structure and reasoning can support effective human interactions and model checking. Existing explainers fail to address this issue by providing post-hoc explanations which do not allow human interaction making the model itself more interpretable. To fill this gap, we introduce the Concept Distillation Module, the first differentiable concept-distillation approach for graph networks. The proposed approach is a layer that can be plugged into any graph network to make it explainable by design, by first distilling graph concepts from the latent space and then using these to solve the task. Our results demonstrate that this approach allows graph networks to: (i) support effective human interventions at test time: these can increase human trust as well as significantly improve model performance, (ii) provide high-quality concept-based logic explanations for their prediction, and (iii) attain model accuracy comparable with their equivalent vanilla versions.

[ Poster] 

Author Information

Lucie Charlotte Magister (University of Cambridge)
Lucie Charlotte Magister

I am a Ph.D. student at the University of Cambridge, supervised by Prof. Pietro Lio. My research focuses on the explainability of graph neural networks. My current projects are related to concept extraction in graph neural networks. I have obtained a MPhil in Advanced Computer Science from the University of Cambridge and a BSc in Computer Science from the University of St Andrews.

Pietro Barbiero (University of Cambridge)
Dmitry Kazhdan (University of Cambridge)
Federico Siciliano (Sapienza University of Rome)
Gabriele Ciravegna (LABORATOIRE I3S UCA)
Gabriele Ciravegna

I am a Post Doc in the MAASAI (Models and Algorithms for Artificial Intelligence) research team of Inria. I received the Ph.D. degree with honours from the University of Florence in 2022 under the supervision of Professor Marco Gori. In 2018, I received a master’s degree in Computer Engineering with honours at the Polytechnic of Turin. Besides machine learning, I also like football, volleyball, and playing the piano.

Fabrizio Silvestri (University of Rome, La Sapienza)
Mateja Jamnik (University of Cambridge)
Pietro Lió (University of Cambridge)

More from the Same Authors