EUVIMEDEUVIMED entdecken
Crossref

VARIUM+: Semantic Expert-Structured Memory-Augmented Variational Autoencoder for Multi-Interest Recommendation

Nhu-Thuat Tran, Hady W. Lauw

ACM Transactions on Intelligent Systems and Technology · 18.06.2026

DOI: 10.1145/3821220 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 18.06.2026. Verfasst von Nhu-Thuat Tran und 1 weiteren Autor:innen. Die Arbeit nennt 64 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Variational autoencoder (VAE) frameworks for multi-interest discovery have demonstrated strong recommendation performance. However, because VAEs model users independently, they fail to capture shared interest patterns among like-minded users, a key limitation of existing approaches. The previous work, Varium [41], addressed this by introducing a flat structured memory with iterative refinement to capture reusable interest patterns across users. In this paper, we extend Varium into Varium+, a novel semantic expert-structured memory-augmented VAE that fundamentally rethinks how shared interests are organized and retrieved. Unlike its predecessor, Varium+ organizes memory as a mixture of semantically-grounded experts, each dedicated to a different modality (textual, visual, collaborative) and composed of multiple prototypes representing fine-grained interest groups. For each user, we first discover multiple intra-user interest factors behind their item adoptions. Intra-user interest factors next attend to these expert memories via cross-attention to retrieve relevant inter-user signals, then pass through self-attention to model interactions among retrieved interests. The resulting shared interest representations are integrated back into each user’s multi-interest profile, enriching personal preferences with collaborative wisdom. Experiments on real-world datasets demonstrate that Varium+ consistently outperforms both its predecessor and a comprehensive set of baselines, with particularly strong gains when leveraging semantic knowledge. Qualitative analysis further reveals that our expert-structured memory organizes the latent interest space into well-separated clusters, validating its ability to discover meaningful shared patterns among users.

Zitieren

APA

Tran, N., & Lauw, H. W. (2026). VARIUM+: Semantic Expert-Structured Memory-Augmented Variational Autoencoder for Multi-Interest Recommendation. ACM Transactions on Intelligent Systems and Technology. https://doi.org/10.1145/3821220

Vancouver

Tran N, Lauw HW. VARIUM+: Semantic Expert-Structured Memory-Augmented Variational Autoencoder for Multi-Interest Recommendation. ACM Transactions on Intelligent Systems and Technology. 2026. doi:10.1145/3821220

BibTeX
@article{Tran2026,
  author = {Tran, Nhu-Thuat and Lauw, Hady W.},
  title = {VARIUM+: Semantic Expert-Structured Memory-Augmented Variational Autoencoder for Multi-Interest Recommendation},
  journal = {ACM Transactions on Intelligent Systems and Technology},
  year = {2026},
  doi = {10.1145/3821220}
}
Kostenlos starten →