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

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 neighbor...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2022-02, Vol.44 (2), p.770-782
Main Authors: Gui, Shupeng, Zhang, Xiangliang, Zhong, Pan, Qiu, Shuang, Wu, Mingrui, Ye, Jieping, Wang, Zhengdao, Liu, Ji
Format: Article
Language:English
Subjects:
Aggregates
Cognitive tasks
Embedding
Games
Graph embedding
Graph neural networks
Graphs
Invariants
Laplace equations
Machine learning
Matrix decomposition
Nodes
partial permutation invariant set function
Permutations
Reinforcement learning
representation learning
Representations
Task analysis
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 dependencies 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. Empirical evaluation results on benchmark data sets show that our proposed PINE method outperforms the state-of-the-art approaches on producing node vectors for various learning tasks of both homogeneous and heterogeneous graphs.
ISSN:0162-8828
1939-3539
2160-9292
DOI:10.1109/TPAMI.2021.3061162