SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2107.01495 · 2021

On Positional and Structural Node Features for Graph Neural Networks on Non-attributed Graphs

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

Graph neural networks (GNNs) have been widely used in various graph-related problems such as node classification and graph classification, where superior performance is mainly established when natural node features are available. However, it is not well understood how GNNs work without natural node features, especially regarding the various ways to construct artificial ones. In this paper, we point out the two types of artificial node features, i.e., positional and structural node features, and provide insights on why each of them is more appropriate for certain tasks, i.e., positional node classification, structural node classification, and graph classification. Extensive experimental results on 10 benchmark datasets validate our insights, thus leading to a practical guideline on the choices between different artificial node features for GNNs on non-attributed graphs. The code is available at https://github.com/zjzijielu/gnn-positional-structural-node-features.

For agents

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

get_harvested_code_for_paper("2107.01495")
get_code_for_paper("2107.01495")
have("2107.01495")

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

curl https://syntology.ai/api/ran/2107.01495.json

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

[![Syntology run record](https://syntology.ai/api/ran/2107.01495.svg)](https://syntology.ai/paper/2107.01495)

Connect an agent — have() is free.