Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks
arXiv:2010.13547
Abstract
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 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.
arXiv commentTo appear at NeurIPS 2020
References in corpus (13)
- Graph Embedding Techniques, Applications, and Performance: A Survey
- Graph Neural Networks: A Review of Methods and Applications
- Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
- Adaptive Computation Time for Recurrent Neural Networks
- Graph networks as learnable physics engines for inference and control
- Origins of power-law degree distribution in the heterogeneity of human activity in social networks
- Attentional Pooling for Action Recognition
- LanczosNet: Multi-Scale Deep Graph Convolutional Networks
- Learning a SAT Solver from Single-Bit Supervision
- What Can Neural Networks Reason About?
- Graph Neural Ordinary Differential Equations
- Graph Neural Networks for Social Recommendation
- Relational Pooling for Graph Representations