EUVIMEDEUVIMED entdecken
Crossref

Dataset Recommendation for Heterogeneous and Dynamic Scholarly Graphs via Multimodal Representation Learning

Ornella Irrera, Matteo Lissandrini, Daniele Dell'Aglio, Gianmaria Silvello

ACM Transactions on Recommender Systems · 12.11.2026

DOI: 10.1145/3862642 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Recommender Systems, online erschienen am 12.11.2026. Verfasst von Ornella Irrera und 3 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Researchers struggle to find relevant datasets amid the volume of data across repositories and the growth of scholarly publications. Manual dataset retrieval is time-consuming and often fails to surface valuable resources not easily discoverable through direct links or popularity metrics. Dataset recommendation — identifying datasets relevant to a paper, author, or query — has become essential for improving dataset discoverability and reuse. Yet this task is difficult because Scholarly Knowledge Graphs (SKGs) are large-scale, heterogeneous, dynamic, and incomplete. Although openly available SKGs organize scientific knowledge by linking scholarly outcomes, they often lack meaningful connections between datasets, leaving them isolated and underutilized. These graphs contain millions of evolving relations but still suffer from missing or inaccurate metadata, duplicate records, and weak dataset integration. This work presents the Multimodal Scholarly Attention Network (MM-SAN), a heterogeneous multimodal graph representation learning method for recommending datasets relevant to a research publication within real-world SKGs. MM-SAN combines topology-aware and text-based embeddings, enabling effective recommendations even when textual metadata is limited or absent. It operates in transductive, semi-inductive, and fully inductive settings, adapting to evolving SKGs without retraining. Experiments show that MM-SAN surpasses state-of-the-art methods, providing a robust, scalable solution for dataset recommendation.

Zitieren

APA

Irrera, O., Lissandrini, M., Dell'Aglio, D., & Silvello, G. (2026). Dataset Recommendation for Heterogeneous and Dynamic Scholarly Graphs via Multimodal Representation Learning. ACM Transactions on Recommender Systems. https://doi.org/10.1145/3862642

Vancouver

Irrera O, Lissandrini M, Dell'Aglio D, Silvello G. Dataset Recommendation for Heterogeneous and Dynamic Scholarly Graphs via Multimodal Representation Learning. ACM Transactions on Recommender Systems. 2026. doi:10.1145/3862642

BibTeX
@article{Irrera2026,
  author = {Irrera, Ornella and Lissandrini, Matteo and Dell'Aglio, Daniele and Silvello, Gianmaria},
  title = {Dataset Recommendation for Heterogeneous and Dynamic Scholarly Graphs via Multimodal Representation Learning},
  journal = {ACM Transactions on Recommender Systems},
  year = {2026},
  doi = {10.1145/3862642}
}
Kostenlos starten →