EUVIMEDEUVIMED entdecken
Crossref

Matryoshka Representation Learning for Recommendation with Layer- and Hardness-Adaptive Negative Sampling

Riwei Lai, Li Chen, Weixin Chen, Rui Chen

ACM Transactions on Intelligent Systems and Technology · 31.08.2026 · 17 (4) · 1-25

DOI: 10.1145/3800942 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Intelligent Systems and Technology, online erschienen am 28.04.2026. Verfasst von Riwei Lai und 3 weiteren Autor:innen. Die Arbeit nennt 66 Literaturangaben. Gefördert von: Hong Kong Baptist University Key Research Partnership Scheme, NSFC/RGC Joint Research Scheme, Heilongjiang Key R&D Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Representation learning is essential for deep-neural-network-based recommender systems to capture user preferences and item features within fixed-dimensional user and item vectors. Unlike existing representation learning methods that either treat each user preference and item feature uniformly or categorize them into discrete clusters, we argue that in the real world, user preferences and item features are naturally expressed and organized in a hierarchical manner, leading to a new direction for representation learning. In this article, we introduce a novel matryoshka representation learning method for recommendation (MRL4Rec) , by which we restructure user and item vectors into matryoshka representations with nested vector spaces to explicitly represent user preferences and item features at different hierarchical layers. We theoretically establish that training with the same triplets for each sliced vector cannot guarantee representation learning with hierarchical structures. Subsequently, we propose the layer- and hardness-adaptive negative sampling (LHANS) mechanism to construct training triplets, which further ensures the soundness of learned matryoshka representations in capturing hierarchical user preferences and item features. The experiments demonstrate that MRL4Rec can consistently and substantially outperform a number of state-of-the-art competitors on several real-life datasets. Our code is publicly available at https://github.com/Riwei-HEU/MRL .

Förderung

  • Hong Kong Baptist University Key Research Partnership Scheme
  • NSFC/RGC Joint Research Scheme
  • Heilongjiang Key R&D Program of China

Zitieren

APA

Lai, R., Chen, L., Chen, W., & Chen, R. (2026). Matryoshka Representation Learning for Recommendation with Layer- and Hardness-Adaptive Negative Sampling. ACM Transactions on Intelligent Systems and Technology, 17(4), 1-25. https://doi.org/10.1145/3800942

Vancouver

Lai R, Chen L, Chen W, Chen R. Matryoshka Representation Learning for Recommendation with Layer- and Hardness-Adaptive Negative Sampling. ACM Transactions on Intelligent Systems and Technology. 2026;17(4):1-25. doi:10.1145/3800942

BibTeX
@article{Lai2026,
  author = {Lai, Riwei and Chen, Li and Chen, Weixin and Chen, Rui},
  title = {Matryoshka Representation Learning for Recommendation with Layer- and Hardness-Adaptive Negative Sampling},
  journal = {ACM Transactions on Intelligent Systems and Technology},
  year = {2026},
  volume = {17},
  number = {4},
  pages = {1--25},
  doi = {10.1145/3800942}
}
Kostenlos starten →