Past Events

Qualifying Exam

Explainable Graph Attention Networks


Download as iCal file

Tuesday, April 20, 2021, 02:30pm - 04:00pm


Speaker: David Pham

Location : Remote via Zoom


Professor Yongfeng Zhang

Professor Santosh Nagarakatte

Professor Hao Wang

Professor Sudarasun Kannan

Event Type: Qualifying Exam

Abstract: Graphs are an important structure for data storage and computation. Recent years have seen the success of deep learning on graphs such as Graph Neural Networks (GNN) on various data mining and machine learning tasks. However, most of the deep learning models on graphs cannot easily explain their predictions and are thus often labelled as “black boxes”. For example, Graph Attention Network (GAT) is a frequently used GNN architecture, which adopts the attentionmechanism to carefully select over the neighborhood, nodesfor message passing and aggregation. However, it is difficult to explain why certain neighbors are selected while others are not and how the selected neighbors contribute to the final classification result. In this paper, we present a new graph learning model called Explainable Graph Attention Network (XGAT), which integrates graph attention modeling and explainability. Though in previous work accuracy and explainability were mostly tackled as two different problem spaces and by distinctly different models, we show that in the context of graph attention modeling, we can design a unified neighborhood selection strategy that selects appropriate neighbor-nodes for both better accuracy and enhanced explainability.To justify this, we conduct extensive experiments to better understand the behavior of our model under different conditions and show the increase in both accuracy and explainability.

Join by SIP

Meeting ID: 843 184 6734
Password: 093950
One tap mobile
+13017158592,,8431846734# US (Washington DC)
+13126266799,,8431846734# US (Chicago)

Join By Phone
+1 301 715 8592 US (Washington DC)
+1 312 626 6799 US (Chicago)
+1 646 558 8656 US (New York)
+1 253 215 8782 US (Tacoma)
+1 346 248 7799 US (Houston)
+1 669 900 9128 US (San Jose)
Meeting ID: 843 184 6734
Find your local number:

Join by Skype for Business