EUVIMEDEUVIMED entdecken
Crossref

HC2-GNN: Hierarchical Graph Representation Learning for Efficient Text Classification

Jiejie Fan, Xiaojuan Ban, Zhiyan Zhang, Xi Sun

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (36) · 30611-30619

DOI: 10.1609/aaai.v40i36.40316 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jiejie Fan und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph Neural Networks (GNNs) offer superior modeling capabilities for text classification by capturing complex spatial features within semantic representations. However, existing graph-based approaches often suffer from computational inefficiency and limited ability to model both fine-grained local structures and the sequential nature of text. To address these challenges, we propose HC2-GNN, a Hierarchical Clustering and Coarsening Graph Neural Network, which introduces a novel lightweight graph clustering algorithm called Compromise Conductance Graph Clustering (C2GC). C2GC enables efficient graph clustering while simultaneously preserving both the textual order and the topological coherence of subgraphs. Furthermore, it incorporates a virtue cluster mechanism that expands each subgraph with semantically relevant neighbors, explicitly enabling cross-cluster information propagation without compromising local structural integrity. HC2-GNN aggregates local and global features by combining subgraph-level and full-graph representations, enhancing semantic discriminability for classification. Extensive experiments on benchmark datasets demonstrate that HC2-GNN consistently outperforms existing state-of-the-art text classification methods.

Zitieren

APA

Fan, J., Ban, X., Zhang, Z., & Sun, X. (2026). HC2-GNN: Hierarchical Graph Representation Learning for Efficient Text Classification. Proceedings of the AAAI Conference on Artificial Intelligence, 40(36), 30611-30619. https://doi.org/10.1609/aaai.v40i36.40316

Vancouver

Fan J, Ban X, Zhang Z, Sun X. HC2-GNN: Hierarchical Graph Representation Learning for Efficient Text Classification. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(36):30611-30619. doi:10.1609/aaai.v40i36.40316

BibTeX
@article{Fan2026,
  author = {Fan, Jiejie and Ban, Xiaojuan and Zhang, Zhiyan and Sun, Xi},
  title = {HC2-GNN: Hierarchical Graph Representation Learning for Efficient Text Classification},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {36},
  pages = {30611--30619},
  doi = {10.1609/aaai.v40i36.40316}
}
Kostenlos starten →