Current browse context:
cs.SI
Change to browse by:
References & Citations
Computer Science > Social and Information Networks
Title: Predicting Properties of Nodes via Community-Aware Features
(Submitted on 8 Nov 2023 (v1), last revised 26 Apr 2024 (this version, v2))
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.
Submission history
From: François Théberge [view email][v1] Wed, 8 Nov 2023 14:57:35 GMT (339kb,D)
[v2] Fri, 26 Apr 2024 17:05:13 GMT (373kb,D)
Link back to: arXiv, form interface, contact.