Learning Graph While Training: An Evolving Graph Convolutional Neural Network
arXiv:1708.04675
Abstract
Convolution Neural Networks on Graphs are important generalization and extension of classical CNNs. While previous works generally assumed that the graph structures of samples are regular with unified dimensions, in many applications, they are highly diverse or even not well defined. Under some circumstances, e.g. chemical molecular data, clustering or coarsening for simplifying the graphs is hard to be justified chemically. In this paper, we propose a more general and flexible graph convolution network (EGCN) fed by batch of arbitrarily shaped data together with their evolving graph Laplacians trained in supervised fashion. Extensive experiments have been conducted to demonstrate the superior performance in terms of both the acceleration of parameter fitting and the significantly improved prediction accuracy on multiple graph-structured datasets.
10 pages, submitted to NIPS 2017
References in corpus (11)
- Semi-Supervised Classification with Graph Convolutional Networks
- The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
- Spectral Networks and Locally Connected Networks on Graphs
- Deep Convolutional Networks on Graph-Structured Data
- Learning Convolutional Neural Networks for Graphs
- AtomNet: A Deep Convolutional Neural Network for Bioactivity Prediction in Structure-based Drug Discovery
- Atomic Convolutional Networks for Predicting Protein-Ligand Binding Affinity
- Deep Learning with Dynamic Computation Graphs
- MoleculeNet: A Benchmark for Molecular Machine Learning
- Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
- Low Data Drug Discovery with One-shot Learning