preprint · arXiv (Cornell University) · 2021

Asymmetric Graph Representation Learning

Cited by 2Open access

Abstract

Despite the enormous success of graph neural networks (GNNs), most existing GNNs can only be applicable to undirected graphs where relationships among connected nodes are two-way symmetric (i.e., information can be passed back and forth). However, there is a vast amount of applications where the information flow is asymmetric, leading to directed graphs where information can only be passed in one direction. For example, a directed edge indicates that the information can only be conveyed forwardly from the start node to the end node, but not backwardly. To accommodate such an asymmetric structure of directed graphs within the framework of GNNs, we propose a simple yet remarkably effective framework for directed graph analysis to incorporate such one-way information passing. We define an incoming embedding and an outgoing embedding for each node to model its sending and receiving features respectively. We further develop two steps in our directed GNN model with the first one to aggregate/update the incoming features of nodes and the second one to aggregate/update the outgoing features. By imposing the two roles for each node, the likelihood of a directed edge can be calculated based on the outgoing embedding of the start node and the incoming embedding of the end node. The log-likelihood of all edges plays a natural role of regularization for the proposed model, which can alleviate the over-smoothing problem of the deep GNNs. Extensive experiments on multiple real-world directed graphs demonstrate outstanding performances of the proposed model in both node-level and graph-level tasks.

Cite this paper

APA 7

Tan, Z., Liu, B., & Yin, G. (2021). Asymmetric Graph Representation Learning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2110.07436

MLA 9

Tan, Zhuo, et al. “Asymmetric Graph Representation Learning.” arXiv (Cornell University), 2021, https://doi.org/10.48550/arxiv.2110.07436.

Chicago

Tan, Zhuo, Bin Liu, and Guosheng Yin. 2021. “Asymmetric Graph Representation Learning.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2110.07436.

Harvard

Tan, Z., Liu, B. and Yin, G. (2021) ‘Asymmetric Graph Representation Learning’, arXiv (Cornell University). Available at: https://doi.org/10.48550/arxiv.2110.07436.

BibTeX

@misc{tan2021asymmetric,
  title = {{Asymmetric Graph Representation Learning}},
  author = {Tan, Zhuo and Liu, Bin and Yin, Guosheng},
  journal = {arXiv (Cornell University)},
  year = {2021},
  doi = {10.48550/arxiv.2110.07436}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.