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

2026-01-27

AI Summary

This work addresses the challenges of optimizing top-K accuracy in recommender systems, which are often hindered by high computational costs, complex ranking dependencies, and distributional shifts. The authors propose Talos, a novel loss function that uniquely integrates learnable quantile thresholds with ranking objectives. By leveraging sampling-based regression to efficiently estimate these thresholds and incorporating a constraint term to mitigate score inflation, Talos enhances both optimization stability and generalization. Furthermore, a tailored continuous surrogate function is introduced to improve robustness. Extensive experiments demonstrate that the proposed method significantly boosts recommendation accuracy, training efficiency, convergence stability, and resilience to distributional shifts across multiple benchmark datasets.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Search and Optimization: Learning to Search
• Data Mining & Knowledge Management: Recommender Systems

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

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.

Problem

• Top-K accuracy
• recommender systems
• distribution shift
• ranking optimization
• computational overhead

Innovation

• Top-K optimization
• quantile-based loss
• distributional robustness
• threshold estimation
• recommendation accuracy