Personalized Layer Selection for Graph Neural Networks
Abstract: Graph Neural Networks (GNNs) combine node attributes over a fixed granularity of the local graph structure around a node to predict its label. However, different nodes may relate to a node-level property with a different granularity of its local neighborhood, and using the same level of smoothing for all nodes can be detrimental to their classification. In this work, we challenge the common fact that a single GNN layer can classify all nodes of a graph by training GNNs with a distinct personalized layer for each node. Inspired by metric learning, we propose a novel algorithm, MetSelect, to select the optimal representation layer to classify each node. In particular, we identify a prototype representation of each class in a transformed GNN layer and then, classify using the layer where the distance is smallest to a class prototype after normalizing with that layer’s variance. Results on 10 datasets and 3 different GNNs show that we significantly improve the node classification accuracy of GNNs in a plug-and-play manner. We also find that using variable layers for prediction enables GNNs to be deeper and more robust to poisoning attacks. We hope this work can inspire future works to learn more adaptive and personalized graph representations.
Submission Length: Regular submission (no more than 12 pages of main content)
Changes Since Last Submission: - Fixed typos
- Extended the discussion with layer aggregation methods (JK-Net)
- Added an experiment to show effectiveness over GCN with self-loops
- Added an experiment to show how MetSelect can be compared against layer aggregation methods
Video: https://www.canva.com/design/DAGlG0T0eSA/IHzAoaf5D6owFMxiE4Y0YA/view?utm_content=DAGlG0T0eSA&utm_campaign=designshare&utm_medium=link&utm_source=recording_view
Code: https://github.com/Ksartik/metselect/
Assigned Action Editor: ~Sheng_Li3
Submission Number: 3826
Loading