User-user social networks are widely utilized as side information in recommendation and have been shown to improve performance. We argue that current social recommenders still have room for improvement. First, for social data utilization, most methods focus mainly on positive trust relations, while failing to effectively use negative distrust relations, which can also provide useful signals for recommendation. Second, in terms of modeling architecture, most methods rely on linear or nonlinear transformation structures (e.g., multi-layer perceptrons) as their foundational building blocks. Kolmogorov-Arnold Networks (KANs), recently introduced for their strong data-fitting ability, offer a promising alternative. To this end, in this paper, we propose SocialKAN, a novel KAN-based trust-distrust-aware social recommender method. Specifically, SocialKAN introduces three KAN-based graph learning channels to model the user-item interaction graph, user trust graph, and user distrust graph, respectively. To better enable effective cross-view adaptation among the three channels, we design a semantic routing module for knowledge sharing at the embedding level and an adaptive consensus knowledge distillation strategy for output alignment at the optimization level. Experimental results on the three datasets show that our proposed SocialKAN method achieves strong performance. Ablation studies further validate the rationality and effectiveness of the components designed in our SocialKAN.

SocialKAN: Learning User Preferences on Signed Social Graphs with Kolmogorov-Arnold Networks / A. Li, E.C. - In: CIKM '26 / [a cura di] A. Poggi, N. Ferro. - [s.l] : Association for Computing Machinery (ACM), 2026. - ISBN 979-8-4007-2539-5. - pp. 2560-2569 (( 35. International Conference on Information and Knowledge Management : November, 7th - 11th Roma 2026 [10.1145/3799682.3840728].

SocialKAN: Learning User Preferences on Signed Social Graphs with Kolmogorov-Arnold Networks

E. Casiraghi
Penultimo
;
2026

Abstract

User-user social networks are widely utilized as side information in recommendation and have been shown to improve performance. We argue that current social recommenders still have room for improvement. First, for social data utilization, most methods focus mainly on positive trust relations, while failing to effectively use negative distrust relations, which can also provide useful signals for recommendation. Second, in terms of modeling architecture, most methods rely on linear or nonlinear transformation structures (e.g., multi-layer perceptrons) as their foundational building blocks. Kolmogorov-Arnold Networks (KANs), recently introduced for their strong data-fitting ability, offer a promising alternative. To this end, in this paper, we propose SocialKAN, a novel KAN-based trust-distrust-aware social recommender method. Specifically, SocialKAN introduces three KAN-based graph learning channels to model the user-item interaction graph, user trust graph, and user distrust graph, respectively. To better enable effective cross-view adaptation among the three channels, we design a semantic routing module for knowledge sharing at the embedding level and an adaptive consensus knowledge distillation strategy for output alignment at the optimization level. Experimental results on the three datasets show that our proposed SocialKAN method achieves strong performance. Ablation studies further validate the rationality and effectiveness of the components designed in our SocialKAN.
Settore INFO-01/A - Informatica
2026
Special Interest Group on Hypertext, Hypermedia and Web (SIGWEB)
Special Interest Group on Information Retrieval (SIGIR)
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
CIKM26_SocialKAN.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Licenza: Creative commons
Dimensione 2.29 MB
Formato Adobe PDF
2.29 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I metadati presenti in AIR sono rilasciati con licenza CCO mentre i file delle pubblicazioni sono rilasciati con licenza CC BY-SA, salvo diversa indicazione. In caso di violazione di copyright, contattare l'assistenza di AIR

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/1277696
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact