Work

AMORe: An Agnostic Multi-Objective Framework for Recommendation

Year: 2026
Type: article
Abstract: 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 limit 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 tradeoffs 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 tradeoff 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 .
Language: English
Open Access status: hybrid
OpenAlex ID: W7235165056
FWCI:
Cites: 83
Cited by:
Related to: 10