
Understanding the Message Passing in Graph Neural Networks via Power Iteration
The mechanism of message passing in graph neural networks(GNNs) is still...
read it

A Unified Lottery Ticket Hypothesis for Graph Neural Networks
With graphs rapidly growing in size and deeper graph neural networks (GN...
read it

ENIGMA Anonymous: SymbolIndependent Inference Guiding Machine (system description)
We describe an implementation of gradient boosting and neural guidance o...
read it

On Size Generalization in Graph Neural Networks
Graph neural networks (GNNs) can process graphs of different sizes but t...
read it

Neural Consciousness Flow
The ability of reasoning beyond data fitting is substantial to deep lear...
read it

Learning to Solve NPComplete Problems  A Graph Neural Network for the Decision TSP
Graph Neural Networks (GNN) are a promising technique for bridging diffe...
read it

Learning to Solve NPComplete Problems  A Graph Neural Network for Decision TSP
Graph Neural Networks (GNN) are a promising technique for bridging diffe...
read it
Towards ScaleInvariant Graphrelated Problem Solving by Iterative Homogeneous Graph Neural Networks
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 the 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 smallscale graphs but generalize well to largescale graphs for a number of basic graph theory problems. It also shows generalizability for applications of multibody physical simulation and imagebased navigation problems.
READ FULL TEXT
Comments
There are no comments yet.