Timezone: »

Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous GNNs
Hao Tang · Zhiao Huang · Jiayuan Gu · Bao-Liang Lu · Hao Su

Thu Dec 10 09:00 PM -- 11:00 PM (PST) @ Poster Session 6 #1837

Current graph neural networks (GNNs) lack generalizability with respect to scales (graph sizes, graph diameters, edge weights, etc..) when solving many graph analysis problems. Taking the perspective of synthesizing graph theory programs, we propose several extensions to address the issue. First, inspired by the dependency of iteration number of common graph theory algorithms on graph size, we learn to terminate the message passing process in GNNs adaptively according to the computation progress. Second, inspired by the fact that many graph theory algorithms are homogeneous with respect to graph weights, we introduce homogeneous transformation layers that are universal homogeneous function approximators, to convert ordinary GNNs to be homogeneous. Experimentally, we show that our GNN can be trained from small-scale graphs but generalize well to large-scale graphs for a number of basic graph theory problems. It also shows generalizability for applications of multi-body physical simulation and image-based navigation problems.

Author Information

Hao Tang (Shanghai Jiao Tong University)
Zhiao Huang (University of California San Diego)
Jiayuan Gu (University of California, San Diego)
Bao-Liang Lu (Shanghai Jiao Tong University)
Hao Su (UCSD)

More from the Same Authors