AMORe: An Agnostic Multi-Objective Framework for Recommendation
ACM Transactions on Information Systems · 16.11.2026
DOI: 10.1145/3857349 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Information Systems, online erschienen am 16.11.2026. Verfasst von Vincenzo Paparella und 4 weiteren Autor:innen. Die Arbeit nennt 91 Literaturangaben.
Abstract (Originalsprache)
Recommender systems increasingly need to balance relevance with beyond-accuracy objectives, including fairness and long-tail exposure. Existing multi-objective approaches often rely on objective-specific loss designs, which limits reuse when target metrics or their numerical scales change. We propose AMORe, a scale-aware framework for optimizing multiple decomposable top- k recommendation objectives within gradient-based recommender training. AMORe combines differentiable ranking approximators with a lightweight top- k smoothing component and a unified loss that minimizes normalized deviations from user-specified utopia points. Experiments on four public datasets and three recommendation backbones show that AMORe exposes controllable trade-offs between relevance and beyond-accuracy objectives, with improvements in beyond-accuracy metrics over corresponding vanilla backbones in most evaluated settings. Comparisons with representative fairness-aware baselines, together with ablation and efficiency analyses, clarify when AMORe improves trade-off stability and quantify the computational overhead introduced by multi-objective training. We release code and datasets at: https://github.com/vincpapa/Agnostic-Multi-Objective-Recommendation .
Zitieren
APA
Paparella, V., Anelli, V. W., Nardini, F. M., Perego, R., & Noia, T. D. (2026). AMORe: An Agnostic Multi-Objective Framework for Recommendation. ACM Transactions on Information Systems. https://doi.org/10.1145/3857349
Vancouver
Paparella V, Anelli VW, Nardini FM, Perego R, Noia TD. AMORe: An Agnostic Multi-Objective Framework for Recommendation. ACM Transactions on Information Systems. 2026. doi:10.1145/3857349
BibTeX
@article{Paparella2026,
author = {Paparella, Vincenzo and Anelli, Vito Walter and Nardini, Franco Maria and Perego, Raffaele and Noia, Tommaso Di},
title = {AMORe: An Agnostic Multi-Objective Framework for Recommendation},
journal = {ACM Transactions on Information Systems},
year = {2026},
doi = {10.1145/3857349}
}
EUVIMED