TAGDN: type-aligning graph diffusion network for capturing long-range dependencies in heterogeneous graphs without over-squashing and over-smoothing
Neural Computing and Applications · 2025-12 · 37 (34) · 28747-28777
DOI: 10.1007/s00521-025-11684-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Computing and Applications, online erschienen am 22.10.2025. Verfasst von Seong Jin Ahn und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 63 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Institute for Information and Communications Technology Promotion, Korea Advanced Institute of Science and Technology.
Abstract (Originalsprache)
Graph neural networks (GNNs) have seen significant growth in analyzing heterogeneous graphs, which contain different types of nodes and connections. Recent studies have attempted to analyze heterogeneous graphs without relying on manually selected metapaths. However, existing methods often struggle to learn long-range dependencies between distant nodes because of over-squashing and over-smoothing. This paper presents a new approach, type-aligning graph diffusion network (TAGDN), that effectively addresses these challenges. Our main idea is to boost the power of graph diffusion techniques in heterogeneous graphs with a type-adaptive alignment scheme. This approach allows us to exploit long-range dependencies between nodes in heterogeneous graphs without suffering over-squashing and over-smoothing. Through extensive experiments, we show that TAGDN outperforms state-of-the-art heterogeneous GNNs on diverse graph analysis tasks. Ablation studies show that our alignment scheme enhances the capacity of graph diffusion networks in heterogeneous graph analysis, yielding an average improvement of 5.02% in node classification and 25.43% in node clustering. Our implementation is available at https://github.com/SeongJinAhn/TAGDN .
Förderung
- Institute for Information and Communications Technology Promotion
- Korea Advanced Institute of Science and Technology
Zitieren
APA
Ahn, S. J., Kim, M., & Kim, M. (2025). TAGDN: type-aligning graph diffusion network for capturing long-range dependencies in heterogeneous graphs without over-squashing and over-smoothing. Neural Computing and Applications, 37(34), 28747-28777. https://doi.org/10.1007/s00521-025-11684-7
Vancouver
Ahn SJ, Kim M, Kim M. TAGDN: type-aligning graph diffusion network for capturing long-range dependencies in heterogeneous graphs without over-squashing and over-smoothing. Neural Computing and Applications. 2025;37(34):28747-28777. doi:10.1007/s00521-025-11684-7
BibTeX
@article{Ahn2025,
author = {Ahn, Seong Jin and Kim, Min-Soo and Kim, Myoung-Ho},
title = {TAGDN: type-aligning graph diffusion network for capturing long-range dependencies in heterogeneous graphs without over-squashing and over-smoothing},
journal = {Neural Computing and Applications},
year = {2025},
volume = {37},
number = {34},
pages = {28747--28777},
doi = {10.1007/s00521-025-11684-7}
}
EUVIMED