Search for contacts, projects,
courses and publications

Graph Random Neural Features for Distance-Preserving Graph Representations

Additional information

Authors
Zambon D., Alippi C., Livi L.
Type
Article in conference proceedings
Year
2020
Language
English
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.
Conference proceedings
Proceedings of the 37th International Conference on Machine Learning (ICML)
Publisher
PMLR
Series
Proceedings of Machine Learning Research
Start page number
10968
End page number
10977
Meeting place
Virtual