PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions

Abstract
Graph node embedding aims at learning a vector representation for all nodes given a graph. It is a central problem in many machine learning tasks (e.g., node classification, recommendation, community detection). The key problem in graph node embedding lies in how to define the dependence to neighbors Existing approaches specify (either explicitly or implicitly) certain dependencies on neighbors, which may lead to loss of subtle but important structural information within the graph and other dependence among neighbors. This intrigues us to ask the question: can we design a model to give the adaptive flexibility of dependencies to each node's neighborhood. In this paper, we propose a novel graph node embedding method (named PINE) via a novel notion of partial permutation invariant set function, to capture any possible dependence. Our method 1) can learn an arbitrary form of the representation function from the neighborhood, without losing any potential dependence structures, and 2) is applicable to both homogeneous and heterogeneous graph embedding, the latter of which is challenged by the diversity of node types. Furthermore, we provide theoretical guarantee for the representation capability of our method for general homogeneous and heterogeneous graphs.

Citation
Gui, S., Zhang, X., Zhong, P., Qiu, S., Wu, M., Ye, J., … Liu, J. (2021). PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–1. doi:10.1109/tpami.2021.3061162

Publisher
Institute of Electrical and Electronics Engineers (IEEE)

Journal
IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI
10.1109/TPAMI.2021.3061162

arXiv
1909.12903

Additional Links
https://ieeexplore.ieee.org/document/9361263/https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9361263

Permanent link to this record