Predicting Properties of Nodes via Community-Aware Features

Bogumił Kamiński, Paweł Prałat, François Théberge, Sebastian Zając
11/8/2023
cs.SIcs.LGmath.CO

Official code: sebkaz/BetaStar (2 stars, last commit 2026-04-15).

Abstract

This paper shows how information about the network's community structure can be used to define node features with high predictive power for classification tasks. To do so, we define a family of community-aware node features and investigate their properties. Those features are designed to ensure that they can be efficiently computed even for large graphs. We show that community-aware node features contain information that cannot be completely recovered by classical node features or node embeddings (both classical and structural) and bring value in node classification tasks. This is verified for various classification tasks on synthetic and real-life networks.

View on arXivView PDF

Code Implementations(1)

sebkaz/BetaStarOfficial
20Julia, PythonAug 31, 20236 months ago

Similar Papers

node2vec: Scalable Feature Learning for Networks

84% match1 repo2.7k2016

The Role of Community Detection Methods in Performance Variations of Graph Mining Tasks

82% match2025

Community Detection Guarantees using Embeddings Learned by Node2Vec

82% match2023

The GECo algorithm for Graph Neural Networks Explanation

82% match1 repo12024

From Node Embedding To Community Embedding

82% match1 repo112016

Community detection in complex networks via node similarity, graph representation learning, and hierarchical clustering

82% match2023

Cite this paper

@article{kamiski2023predicting,
  title  = {Predicting Properties of Nodes via Community-Aware Features},
  author = {Bogumił Kamiński and Paweł Prałat and François Théberge and Sebastian Zając},
  year   = {2023},
  eprint = {2311.04730},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.04730v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.04730.svg)](https://codeofpaper.com/paper/2311.04730)

Discussion