GESF: A Universal Discriminative Mapping Mechanism for Graph Representation Learning
This addresses the flexibility limitations in graph representation learning for applications like social network analysis, though it appears incremental as it builds on set function techniques.
The paper tackles the problem of graph node embedding by proposing GESF, a method that learns arbitrary representation functions from neighborhoods and automatically determines neighbor significance, outperforming state-of-the-art approaches on benchmark datasets for classification tasks.
Graph embedding is a central problem in social network analysis and many other applications, aiming to learn the vector representation for each node. While most existing approaches need to specify the neighborhood and the dependence form to the neighborhood, which may significantly degrades the flexibility of representation, we propose a novel graph node embedding method (namely GESF) via the set function technique. Our method can 1) learn an arbitrary form of representation function from neighborhood, 2) automatically decide the significance of neighbors at different distances, and 3) be applied to heterogeneous graph embedding, which may contain multiple types of nodes. Theoretical guarantee for the representation capability of our method has been proved for general homogeneous and heterogeneous graphs and evaluation results on benchmark data sets show that the proposed GESF outperforms the state-of-the-art approaches on producing node vectors for classification tasks.