Causal Adaptive Reweighting Meta‐Learning With Dynamic Strength for Imbalanced Cold‐Start Sequential Recommendation
Concurrency and Computation: Practice and Experience · 2026-07 · 38 (14)
DOI: 10.1002/cpe.70842 ↗Kurz gefasst
Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 15.07.2026. Verfasst von Jiahong Lu und 6 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
Sequential recommendation systems face significant challenges in accurately modeling user preferences, particularly for cold‐start users with limited interaction histories and imbalanced rating distributions. Traditional meta‐learning approaches treat all samples equally, ignoring the varying informativeness of rare ratings and the heterogeneous nature of user engagement patterns. In this paper, we propose Causal Adaptive Reweighting Meta‐Learning (CARML), a novel framework that integrates causal inference principles with model‐agnostic meta‐learning for sequential recommendation. Our approach introduces three key innovations: (1) a propensity score network that identifies and upweights rare rating samples through inverse propensity weighting, (2) a counterfactual prediction network that quantifies prediction uncertainty via entropy‐based measures, and (3) an uncertainty‐based dynamic causal strength mechanism that adaptively adjusts the intensity of causal correction based on user interaction frequency and prediction confidence. The dynamic strength module employs learnable combination weights to balance length‐based decay factors and uncertainty‐driven adjustments, enabling personalized treatment for users across the activity spectrum. Extensive experiments conducted on four real‐world datasets and one industrial dataset demonstrate that CARML achieves the best RMSE across all five datasets, with an average improvement of 8.11%, and the best MAE on four out of five datasets. The most pronounced gains are observed on datasets with severe rating imbalance and limited user populations, confirming the effectiveness of causal correction under the cold‐start conditions it is designed to address.
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Lu, J., Yu, L., Li, S., Xu, Z., Jiang, P., Liu, S., & Wang, Y. (2026). Causal Adaptive Reweighting Meta‐Learning With Dynamic Strength for Imbalanced Cold‐Start Sequential Recommendation. Concurrency and Computation: Practice and Experience, 38(14). https://doi.org/10.1002/cpe.70842
Vancouver
Lu J, Yu L, Li S, Xu Z, Jiang P, Liu S, et al. Causal Adaptive Reweighting Meta‐Learning With Dynamic Strength for Imbalanced Cold‐Start Sequential Recommendation. Concurrency and Computation: Practice and Experience. 2026;38(14). doi:10.1002/cpe.70842
BibTeX
@article{Lu2026,
author = {Lu, Jiahong and Yu, Liya and Li, Shaobo and Xu, Zhao and Jiang, Pei and Liu, Shanhui and Wang, Yingwan},
title = {Causal Adaptive Reweighting Meta‐Learning With Dynamic Strength for Imbalanced Cold‐Start Sequential Recommendation},
journal = {Concurrency and Computation: Practice and Experience},
year = {2026},
volume = {38},
number = {14},
doi = {10.1002/cpe.70842}
}
EUVIMED