Talos: Optimizing Top-K Accuracy in Recommender Systems
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 30 of its 72 references that are in the map. First posted on arXiv 27 Jan 2026.
Builds on
30 of 72 references.
References · 30
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
- 2017Neural Collaborative Filteringcited by 1,111
- 2020Self-supervised Learning: Generative or Contrastivecited by 694
- 2019Neural Graph Collaborative Filteringcited by 661
- 2020A Survey on Contrastive Self-supervised Learningcited by 554
- 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
- 2020Search-based User Interest Modeling with Lifelong Sequential Behavior Data for Click-Through Rate Predictioncited by 177
- 2015VBPR: Visual Bayesian Personalized Ranking from Implicit Feedbackcited by 151
- 2021AutoDebias: Learning to Debias for Recommendationcited by 68
- 2018A no-regret generalization of hierarchical softmax to extreme multi-label classificationcited by 52
- 2021Recall@k Surrogate Loss with Large Batches and Similarity Mixupcited by 49
18 more
- 2023Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendationcited by 38
- 2020Graph Convolutional Network for Recommendation with Low-pass Collaborative Filterscited by 32
- 2022When AUC meets DRO: Optimizing Partial AUC for Deep Learning with Non-Convex Convergence Guaranteecited by 29
- 2023Empowering Collaborative Filtering with Principled Adversarial Contrastive Losscited by 24
- 2022Joint Optimization of Ranking and Calibration with Contextualized Hybrid Modelcited by 22
- 2024How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspectivecited by 21
- 2023Adap-τ: Adaptively Modulating Embedding Magnitude for Recommendationcited by 19
- 2023On the Theories Behind Hard Negative Sampling for Recommendationcited by 18
- 2024SIGformer: Sign-aware Graph Transformer for Recommendationcited by 12
- 2025MSL: Not All Tokens Are What You Need for Tuning LLM as a Recommendercited by 10
- 2024Lower-Left Partial AUC: An Effective and Efficient Optimization Metric for Recommendationcited by 9
- 2024PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendationcited by 9
- 2025Breaking the Top-K Barrier: Advancing Top-K Ranking Metrics Optimization in Recommender Systemscited by 9
- 2025HatLLM: Hierarchical Attention Masking for Enhanced Collaborative Modeling in LLM-based Recommendationcited by 5
- 2020Learning User Representations with Hypercuboids for Recommender Systemscited by 4
- 2025Field Matters: A Lightweight LLM-enhanced Method for CTR Predictioncited by 4
- 2025Rankformer: A Graph Transformer for Recommendation based on Ranking Objectivecited by 3
- 2025Advancing Loss Functions in Recommender Systems: A Comparative Study with a R'enyi Divergence-Based Solutioncited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.