BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:The Interpretability of Graph Neural Networks - Han Xuanyuan\, Dep
 t of Computer Science and Technology\, University of Cambridge
DTSTART:20221125T150000Z
DTEND:20221125T160000Z
UID:TALK193025@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:Graph neural networks (GNNs) have demonstrated great performan
 ce on graph-based data. However\, like many machine learning models\, GNNs
  lack transparency and are not interpretable. Due to a lack of trust\, pra
 ctitioners may be reluctant to deploy them in high-stake and safety-critic
 al applications in the real world. This motivates us to develop methods fo
 r the explainability of GNNs. In this talk\, I provide an overview of the 
 current trends in the frontier of this research area\, aiming to discuss t
 he general challenges researchers are currently solving. I then present my
  recent work accepted to AAAI 2023: an investigation into the behaviour of
  individual GNN neurons. We find that GNN neurons behave like concept dete
 ctors\, and can be used to extract insights from the model which align wit
 h human intuition. We then use neuron-level concepts to construct global e
 xplanations\, outperforming the previous state-of-the-art approach in term
 s of explanation quality. \n\nJoin Zoom Meeting\nhttps://zoom.us/j/9916695
 5895?pwd=SzI0M3pMVEkvNmw3Q0dqNDVRalZvdz09\n\n
LOCATION:FW11 + zoom
END:VEVENT
END:VCALENDAR