EUVIMEDEUVIMED entdecken
Crossref

Polarity-Aware and Adaptive Sparse Aggregation for Implicit Heterophilic Graph Classification

Haotian Wang, Yan Ding, Wangdong Yang, Zhuo Tang, Chubo Liu, Kenli Li

IEEE Transactions on Knowledge and Data Engineering · 2026-06 · 38 (6) · 3849-3862

DOI: 10.1109/tkde.2026.3678660 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, 2026-06. Verfasst von Haotian Wang und 5 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Graph-structured data appears in domains such as molecular analysis, social networks, and program optimization, where graphs often exhibit implicit heterogeneity, as nodes may look homogeneous in type yet differ significantly in semantics or functionality. Graph Neural Networks (GNNs), while powerful on homophilic graphs, tend to degrade in such settings due to polarity confusion, over-smoothing, and inefficiency caused by dense propagation. We propose a polarity-aware framework for graph classification that addresses these challenges through adaptive directional sparse aggregation. The framework introduces a polarity-aware propagation mechanism that adaptively reinforces or inverts neighbor signals, mitigating contamination under heterophily. A polarity-guided sparse aggregation operator further alleviates over-smoothing, improves scalability by constraining redundant connections, and condenses information flow into more effective representations, while maintaining unbiased estimation with controlled variance. We provide theoretical analyses that characterize the computational complexity, stability properties, and expressive behavior of signed directional aggregation, offering theoretical insights into its computational, stability, and expressive properties. Extensive experiments on molecular and social graph benchmarks with implicit heterophily demonstrate consistent improvements in graph classification accuracy and efficiency. Our method achieves a 2.36% improvement when compared with the strongest baseline on each dataset. In addition, it improves accuracy by 4.53% on average on program optimization strategy recognition tasks, reaching 80.12% overall.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, H., Ding, Y., Yang, W., Tang, Z., Liu, C., & Li, K. (2026). Polarity-Aware and Adaptive Sparse Aggregation for Implicit Heterophilic Graph Classification. IEEE Transactions on Knowledge and Data Engineering, 38(6), 3849-3862. https://doi.org/10.1109/tkde.2026.3678660

Vancouver

Wang H, Ding Y, Yang W, Tang Z, Liu C, Li K. Polarity-Aware and Adaptive Sparse Aggregation for Implicit Heterophilic Graph Classification. IEEE Transactions on Knowledge and Data Engineering. 2026;38(6):3849-3862. doi:10.1109/tkde.2026.3678660

BibTeX
@article{Wang2026,
  author = {Wang, Haotian and Ding, Yan and Yang, Wangdong and Tang, Zhuo and Liu, Chubo and Li, Kenli},
  title = {Polarity-Aware and Adaptive Sparse Aggregation for Implicit Heterophilic Graph Classification},
  journal = {IEEE Transactions on Knowledge and Data Engineering},
  year = {2026},
  volume = {38},
  number = {6},
  pages = {3849--3862},
  doi = {10.1109/tkde.2026.3678660}
}
Kostenlos starten →