SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2302.05889 · AAAI · 2023

USER: Unsupervised Structural Entropy-Based Robust Graph Neural Network

Yifei Wang, Jiamou Liu, Zeyu Zhang, Song Yang, Kaiqi Zhao, Yupan Wang

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Unsupervised/self-supervised graph neural networks (GNN) are susceptible to the inherent randomness in the input graph data, which adversely affects the model's performance in downstream tasks. In this paper, we propose USER, an unsupervised and robust version of GNN based on structural entropy, to alleviate the interference of graph perturbations and learn appropriate representations of nodes without label information. To mitigate the effects of undesirable perturbations, we analyze the property of intrinsic connectivity and define the intrinsic connectivity graph. We also identify the rank of the adjacency matrix as a crucial factor in revealing a graph that provides the same embeddings as the intrinsic connectivity graph. To capture such a graph, we introduce structural entropy in the objective function. Extensive experiments conducted on clustering and link prediction tasks under random-perturbation and meta-attack over three datasets show that USER outperforms benchmarks and is robust to heavier perturbations. 1

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2302.05889")
get_code_for_paper("2302.05889")
have("2302.05889")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2302.05889.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2302.05889.svg)](https://syntology.ai/paper/2302.05889)

Connect an agent — have() is free.