Graph Random Neural Features for Distance-Preserving Graph Representations
arXiv:1909.03790
Abstract
We present Graph Random Neural Features (GRNF), a novel embedding method from graph-structured data to real vectors based on a family of graph neural networks. The embedding naturally deals with graph isomorphism and preserves the metric structure of the graph domain, in probability. In addition to being an explicit embedding method, it also allows us to efficiently and effectively approximate graph metric distances (as well as complete kernel functions); a criterion to select the embedding dimension trading off the approximation accuracy with the computational cost is also provided. GRNF can be used within traditional processing methods or as a training-free input layer of a graph neural network. The theoretical guarantees that accompany GRNF ensure that the considered graph distance is metric, hence allowing to distinguish any pair of non-isomorphic graphs.
arXiv commentto be published in Proceedings of the 37th International Conference on Machine Learning, 2020
References in corpus (12)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Inductive Representation Learning on Large Graphs
- Deep learning for molecular design - a review of the state of the art
- Equivalence of distance-based and RKHS-based statistics in hypothesis testing
- The fundamental advantages of temporal networks
- Generalization Properties of Learning with Random Features
- Universal Invariant and Equivariant Graph Neural Networks
- A Fair Comparison of Graph Neural Networks for Graph Classification
- Orthogonal Random Features
- Invariant and Equivariant Graph Networks
- Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds
- D2KE: From Distance to Kernel and Embedding