Sun, Zhongtian, Harit, Anoushka, Cristea, Alexandra, Donnelly, Christl A., Liò, Pietro (2026) GLANCE: Graph Logic Attention Network with Cluster Enhancement for heterophilous graph representation learning. In: Knowledge Graphs: 14th International Joint Conference, IJCKG 2025, Heraklion, Crete, Greece, October 15–17, 2025, Proceedings. Lecture Notes in Computer Science Springer (doi:10.1007/978-981-95-5009-8_4) (KAR id:116733)
|
PDF
Author's Accepted Manuscript
Language: English
This work is licensed under a Creative Commons Attribution 4.0 International License.
|
|
|
Download this file (PDF/1MB) |
Preview |
| Request a format suitable for use with assistive technology e.g. a screenreader | |
| Official URL: https://doi.org/10.1007/978-981-95-5009-8_4 |
|
Abstract
Graph Neural Networks (GNNs) have demonstrated significant success in learning from graph-structured data but often struggle on heterophilous graphs, where connected nodes differ in features or class labels. This limitation arises from indiscriminate neighbor aggregation and insufficient incorporation of higher-order structural patterns. To address these challenges, we propose GLANCE (Graph Logic Attention Network with Cluster Enhancement), a novel framework that integrates logic-guided reasoning, dynamic graph refinement, and adaptive clustering to enhance graph representation learning. GLANCE combines a logic layer for interpretable and structured embeddings, multi-head attention-based edge pruning for denoising graph structures, and clustering mechanisms for capturing global patterns. Experimental results in benchmark datasets, including Cornell, Texas, and Wisconsin, demonstrate that GLANCE achieves competitive performance, offering robust and interpretable solutions for heterophilous graph scenarios. The proposed framework is lightweight, adaptable, and uniquely suited to the challenges of heterophilous graphs.
| Item Type: | Conference proceeding |
|---|---|
| DOI/Identification number: | 10.1007/978-981-95-5009-8_4 |
| Additional information: | For the purpose of open access, the author(s) has applied a Creative Commons Attribution (CC BY) licence to any Author Accepted Manuscript version arising. |
| Subjects: | Q Science > QA Mathematics (inc Computing science) |
| Institutional Unit: | Schools > School of Computing |
| Former Institutional Unit: |
There are no former institutional units.
|
| Funders: | University of Kent (https://ror.org/00xkeyj56) |
| Depositing User: | Zhongtian Sun |
| Date Deposited: | 06 Oct 2026 09:24 UTC |
| Last Modified: | 17 Nov 2026 13:19 UTC |
| Resource URI: | https://kar.kent.ac.uk/id/eprint/116733 (The current URI for this page, for reference purposes) |
- Link to SensusAccess
- Export to:
- RefWorks
- EPrints3 XML
- BibTeX
- CSV
- Depositors only (login required):

https://orcid.org/0000-0003-0489-5203
Altmetric
Altmetric