---
title: "A Centrality-based Graph Learning Framework"
authors:
  - "Jiajun Yu"
  - "Zhihao Wu"
  - "Jielong Lu"
  - "Tianyue Wang"
  - "Haishuai Wang"
doi: "10.24963/ijcai.2025/399"
url: "https://ijcai.org/proceedings/2025/399"
pdf: "https://ijcai.org/proceedings/2025/0399.pdf"
venue: "Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence"
year: 2025
pages: "3588-3596"
track: "Main Track"
keywords:
  - "Data Mining: DM: Mining graphs"
  - "Machine Learning: ML: Representation learning"
---

# A Centrality-based Graph Learning Framework

Jiajun Yu, Zhihao Wu, Jielong Lu, Tianyue Wang, Haishuai Wang

*Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence*, pages 3588-3596. DOI: [10.24963/ijcai.2025/399](https://doi.org/10.24963/ijcai.2025/399)

## Abstract

Graph Neural Networks (GNNs) have become powerful models for both node- and graph-level tasks. While node-level learning focuses on individual nodes and their local structures, graph-level learning encounters challenges in capturing the global properties of graphs. In this paper, we conduct a theoretical and experimental analysis of existing graph-level learning frameworks and find that these frameworks typically adopt a single-view perspective based solely on node degree, which limits their ability to capture comprehensive graph characteristics.
To address these issues, we propose a multi-view approach that leverages different types of centrality measures to capture diverse aspects of graph structure. We design an attention-based mechanism to adaptively integrate these multiple views, and use it as a readout function to perform weighted summation of node embeddings, termed as Adaptive Centrality Readout (ACRead). ACRead demonstrates enhanced flexibility and effectiveness when integrated with various GNN architectures, outperforming state-of-the-art readout methods, including KerRead and Set Transformer.
Additionally, this multi-view centrality approach can serve as a standalone graph-level learning framework without relying on GNNs, referred to as Adaptive Centrality-based Graph Learning (ACGL), which achieves competitive performance by effectively combining different centrality perspectives.