Signed Graph Diffusion Network

Jinhong Jung, Jaemin Yoo, U Kang

Keywords: graph neural network, signed graph analysis, representation learning, graph diffusion, random walk, link sign prediction

Abstract:

Given a signed social graph, how can we learn appropriate node representations to infer the signs of missing edges?
Signed social graphs have received considerable attention to model trust relationships.
Learning node representations is crucial to effectively analyze graph data, and various techniques such as network embedding and graph convolutional network (GCN) have been proposed for learning signed graphs.
However, traditional network embedding methods are not end-to-end for a specific task such as link sign prediction, and GCN-based methods suffer from a performance degradation problem when their depth increases.
In this paper, we propose Signed Graph Diffusion Network (SGDNet), a novel graph neural network that achieves end-to-end node representation learning for link sign prediction in signed social graphs.
We propose a random walk technique specially designed for signed graphs so that SGDNet effectively diffuses hidden node features.
Through extensive experiments, we demonstrate that SGDNet outperforms state-of-the-art models in terms of link sign prediction accuracy.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: End-to-end graph neural network model for node representation learning using a novel random walk based feature diffusion in signed graphs.

Reviewed Version (pdf): https://openreview.net/references/pdf?id=XeAijTgFyy