Talos: Optimizing Top-$K$ Accuracy in Recommender Systems

TL;DR

Talos is a novel loss function designed to optimize Top-$K$ accuracy in recommender systems by simplifying ranking operations, improving efficiency, and enhancing robustness against distribution shifts.

Contribution

The paper introduces Talos, a new loss function with a quantile-based approach and efficient threshold estimation for better Top-$K$ accuracy optimization in RS.

Findings

Talos improves Top-$K$ accuracy in recommender systems.

It offers computational efficiency over traditional ranking-based methods.

Talos demonstrates robustness to distribution shifts in empirical tests.

Abstract

Recommender systems (RS) aim to retrieve a small set of items that best match individual user preferences. Naturally, RS place primary emphasis on the quality of the Top-$K$ results rather than performance across the entire item set. However, estimating Top-$K$ accuracy (e.g., Precision@$K$, Recall@$K$) requires determining the ranking positions of items, which imposes substantial computational overhead and poses significant challenges for optimization. In addition, RS often suffer from distribution shifts due to evolving user preferences or data biases, further complicating the task. To address these issues, we propose Talos, a loss function that is specifically designed to optimize the Talos recommendation accuracy. Talos leverages a quantile technique that replaces the complex ranking-dependent operations into simpler comparisons between predicted scores and learned score thresholds. We further develop a sampling-based regression algorithm for efficient and accurate threshold estimation, and introduce a constraint term to maintain optimization stability by preventing score inflation. Additionally, we incorporate a tailored surrogate function to address discontinuity and enhance robustness against distribution shifts. Comprehensive theoretical analyzes and empirical experiments are conducted to demonstrate the effectiveness, efficiency, convergence, and distributional robustness of Talos. The code is available at https://github.com/cynthia-shengjia/WWW-2026-Talos.