EUVIMEDEUVIMED entdecken
Crossref

ASRA-GNN: ADAPTIVE SIGNED RELATION-AWARE GRAPH NEURAL NETWORK FOR FRIEND RECOMMENDATION

Pharsana Parveen M, Stanis Arul Mary A

International journal of Computer Networks & Communications · 28.07.2026 · 18 (4) · 17-35

DOI: 10.5121/ijcnc.2026.18402 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International journal of Computer Networks & Communications, online erschienen am 28.07.2026. Verfasst von Pharsana Parveen M und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Existing Signed Graph Neural Networks optimize link sign prediction objectives fundamentally misaligned with friend recommendation, while discarding trust asymmetry, edge strength, and adaptive social theory application. We present ASRA-GNN, addressing these gaps through three contributions: Sign-Aware Structural Role Attention (SSRA) grounded in four social network theories; a Locally Adaptive Theory Mixing (LATM) gate replacing TrustSGCN's binary global threshold with a continuous per-node end-toend learned mixing function; and a Signed Contrastive Recommendation Loss providing the first ranking objective for signed user-user graphs using observed positive-negative pairs as natural contrastive anchors. Experiments on Bitcoin-OTC and Bitcoin-Alpha demonstrate an average of Recall@10 of 0.0599, NDCG@10 of 0.4280, and Precision@10 of 0.0840, outperforming all other baselines.

Zitieren

APA

M, P. P., & A, S. A. M. (2026). ASRA-GNN: ADAPTIVE SIGNED RELATION-AWARE GRAPH NEURAL NETWORK FOR FRIEND RECOMMENDATION. International journal of Computer Networks & Communications, 18(4), 17-35. https://doi.org/10.5121/ijcnc.2026.18402

Vancouver

M PP, A SAM. ASRA-GNN: ADAPTIVE SIGNED RELATION-AWARE GRAPH NEURAL NETWORK FOR FRIEND RECOMMENDATION. International journal of Computer Networks & Communications. 2026;18(4):17-35. doi:10.5121/ijcnc.2026.18402

BibTeX
@article{M2026,
  author = {M, Pharsana Parveen and A, Stanis Arul Mary},
  title = {ASRA-GNN: ADAPTIVE SIGNED RELATION-AWARE GRAPH NEURAL NETWORK FOR FRIEND RECOMMENDATION},
  journal = {International journal of Computer Networks & Communications},
  year = {2026},
  volume = {18},
  number = {4},
  pages = {17--35},
  doi = {10.5121/ijcnc.2026.18402}
}
Kostenlos starten →