English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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

Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks