EUVIMEDEUVIMED entdecken
Crossref

Adaptive Diffusion-based Augmentation for Recommendation

Na Li, Fanghui Sun, Yan Zou, Yangfu Zhu, Xiatian Zhu, Ying Ma

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (18) · 15117-15125

DOI: 10.1609/aaai.v40i18.38535 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Na Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Recommendation systems often rely on implicit feedback, where only positive user-item interactions can be observed. Negative sampling is therefore crucial to provide proper negative training signals. However, existing methods tend to mislabel potentially positive but unobserved items as negatives and lack precise control over negative sample selection. We aim to address these by generating controllable negative samples, rather than sampling from the existing item pool. In this context, we propose Adaptive Diffusion-based Augmentation for Recommendation (ADAR), a novel and model-agnostic module that leverages diffusion to synthesize informative negatives. Inspired by the progressive corruption process in diffusion, ADAR simulates a continuous transition from positive to negative, allowing for fine-grained control over sample hardness. To mine suitable negative samples, we theoretically identify the transition point at which a positive sample turns negative and derive a score-aware function to adaptively determine the optimal sampling timestep. By identifying this transition point, ADAR generates challenging negative samples that effectively refine the model's decision boundary. Experiments confirm that ADAR is broadly compatible and boosts the performance of existing recommendation models substantially, including collaborative filtering and sequential recommendation, without architectural modifications.

Zitieren

APA

Li, N., Sun, F., Zou, Y., Zhu, Y., Zhu, X., & Ma, Y. (2026). Adaptive Diffusion-based Augmentation for Recommendation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(18), 15117-15125. https://doi.org/10.1609/aaai.v40i18.38535

Vancouver

Li N, Sun F, Zou Y, Zhu Y, Zhu X, Ma Y. Adaptive Diffusion-based Augmentation for Recommendation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(18):15117-15125. doi:10.1609/aaai.v40i18.38535

BibTeX
@article{Li2026,
  author = {Li, Na and Sun, Fanghui and Zou, Yan and Zhu, Yangfu and Zhu, Xiatian and Ma, Ying},
  title = {Adaptive Diffusion-based Augmentation for Recommendation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {18},
  pages = {15117--15125},
  doi = {10.1609/aaai.v40i18.38535}
}
Kostenlos starten →