Timezone: »

 
Poster
Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks
Chenxiao Yang · Qitian Wu · Junchi Yan

Thu Dec 01 09:00 AM -- 11:00 AM (PST) @ Hall J #523
in Poster Session 5 »

We study a new paradigm of knowledge transfer that aims at encoding graph topological information into graph neural networks (GNNs) by distilling knowledge from a teacher GNN model trained on a complete graph to a student GNN model operating on a smaller or sparser graph. To this end, we revisit the connection between thermodynamics and the behavior of GNN, based on which we propose Neural Heat Kernel (NHK) to encapsulate the geometric property of the underlying manifold concerning the architecture of GNNs. A fundamental and principled solution is derived by aligning NHKs on teacher and student models, dubbed as Geometric Knowledge Distillation. We develop non- and parametric instantiations and demonstrate their efficacy in various experimental settings for knowledge distillation regarding different types of privileged topological information and teacher-student schemes.

Keywords: Geometric Deep Learning · knowledge distillation · graph neural networks
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Chenxiao Yang (Shanghai Jiao Tong University)
Qitian Wu (Shanghai Jiao Tong University)
Junchi Yan (Shanghai Jiao Tong University)

More from the Same Authors