Recommendation Is a Dish Better Served Warm

• URL: http://arxiv.org/abs/2508.07856v1
• Date: Mon, 11 Aug 2025 11:14:49 GMT
• Title: Recommendation Is a Dish Better Served Warm
• Abstract summary: We systematically explore the cold-start boundary by examining the criteria used to determine whether a user or an item should be considered cold.<n>Our findings show that inconsistent selection of cold-start thresholds can either result in the unnecessary removal of valuable data or lead to the misclassification of cold instances as warm.
• Score: 0.6827423171182154
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In modern recommender systems, experimental settings typically include filtering out cold users and items based on a minimum interaction threshold. However, these thresholds are often chosen arbitrarily and vary widely across studies, leading to inconsistencies that can significantly affect the comparability and reliability of evaluation results. In this paper, we systematically explore the cold-start boundary by examining the criteria used to determine whether a user or an item should be considered cold. Our experiments incrementally vary the number of interactions for different items during training, and gradually update the length of user interaction histories during inference. We investigate the thresholds across several widely used datasets, commonly represented in recent papers from top-tier conferences, and on multiple established recommender baselines. Our findings show that inconsistent selection of cold-start thresholds can either result in the unnecessary removal of valuable data or lead to the misclassification of cold instances as warm, introducing more noise into the system.

Related papers

• SwapRec: Warming Up Cold Items Through Training-Time Swaps [0.6716339721155583]
  Cold items negatively impact real-time personalization of ID-based recommender systems.<n>This is because the use of such interactions degrades user preference estimates.<n>One often applied to address this shortcoming at inference time is to replace, i.e., "swap", cold-start items by their most similar "warm" neighbor.
  arXiv  Detail & Related papers  (2026-09-01T08:41:58Z)
• On the Convergent Validity of Offline Evaluation Designs for Recommender Systems [1.7682678511634797]
  We study how offline evaluation design choices affect the validity of recommender system comparisons.<n>We measure the correlation between model rankings obtained from conventional train-test splits on sparse interaction data and rankings from evaluations based on dense ground-truth user feedback.<n>Our results show that the validity of sparse evaluation depends on the dataset and the specific dense evaluation targets, and that there is no uniformly best offline evaluation design.
  arXiv  Detail & Related papers  (2026-07-27T21:54:19Z)
• Denoising Implicit Feedback for Cold-start Recommendation [32.242895545464485]
  We identify that cold items are more prone to noisy samples due to the continuous influx of new items.<n>Previous denoising studies usually identify noisy samples based on higher loss values, and mitigate noise through sample selection or re-weighting.<n>We propose a model-agnostic denoising method called DIF to achieve denoising implicit feedback for cold-start recommendation.
  arXiv  Detail & Related papers  (2026-06-17T23:50:45Z)
• Cold-Starts in Generative Recommendation: A Reproducibility Study [66.21573264364211]
  Cold-start recommendation remains a central challenge in open-world platforms.<n>We present a systematic study of generative recommendation under a unified suite of cold-start protocols.
  arXiv  Detail & Related papers  (2026-03-31T15:06:31Z)
• On Inherited Popularity Bias in Cold-Start Item Recommendation [5.958603849321135]
  Collaborative filtering (CF) recommender systems struggle with making predictions on unseen, or 'cold', items.<n>We show that cold-start systems can inherit popularity bias, a common cause of recommender system unfairness.
  arXiv  Detail & Related papers  (2025-10-13T13:44:13Z)
• Rethinking Purity and Diversity in Multi-Behavior Sequential Recommendation from the Frequency Perspective [48.60281642851056]
  In recommendation systems, users often exhibit multiple behaviors, such as browsing, clicking, and purchasing.<n>Some behavior data will also bring inevitable noise to the modeling of user interests.<n>These studies indicate that low-frequency information tends to be valuable and reliable, while high-frequency information is often associated with noise.
  arXiv  Detail & Related papers  (2025-08-28T04:55:02Z)
• Not Just What, But When: Integrating Irregular Intervals to LLM for Sequential Recommendation [4.929399529593514]
  Time intervals between purchasing items are a crucial factor in sequential recommendation tasks.<n>We propose IntervalLLM, a framework that integrates interval information into LLM.<n>Our experiments show that IntervalLLM achieves 4.4% improvements in average but also the best-performing warm and cold scenarios.
  arXiv  Detail & Related papers  (2025-07-31T03:05:05Z)
• Variations in Relevance Judgments and the Shelf Life of Test Collections [50.060833338921945]
  We reproduce prior work in the neural retrieval setting, showing that assessor disagreement does not affect system rankings.<n>We observe that some models substantially degrade with our new relevance judgments, and some have already reached the effectiveness of humans as rankers.
  arXiv  Detail & Related papers  (2025-02-28T10:46:56Z)
• Firzen: Firing Strict Cold-Start Items with Frozen Heterogeneous and Homogeneous Graphs for Recommendation [34.414081170244955]
  We propose a unified framework incorporating multi-modal content of items and knowledge graphs (KGs) to solve both strict cold-start and warm-start recommendation. Our model yields significant improvements for strict cold-start recommendation and outperforms or matches the state-of-the-art performance in the warm-start scenario.
  arXiv  Detail & Related papers  (2024-10-10T06:48:27Z)
• Cold & Warm Net: Addressing Cold-Start Users in Recommender Systems [10.133475523630139]
  Cold-start recommendation is one of the major challenges faced by recommender systems (RS) In this paper, we propose Cold & Warm Net based on expert models who are responsible for modeling cold-start and warm-up users respectively. The proposed model has also been deployed on an industrial short video platform and achieves a significant increase in app dwell time and user retention rate.
  arXiv  Detail & Related papers  (2023-09-27T13:31:43Z)
• Our Model Achieves Excellent Performance on MovieLens: What Does it Mean? [43.3971105361606]
  We conduct a meticulous analysis of the MovieLens dataset. There are significant differences in user interactions at the different stages when a user interacts with the MovieLens platform. We discuss the discrepancy between the interaction generation mechanism that is employed by the MovieLens system and that of typical real-world recommendation scenarios.
  arXiv  Detail & Related papers  (2023-07-19T13:44:32Z)
• In Search of Insights, Not Magic Bullets: Towards Demystification of the Model Selection Dilemma in Heterogeneous Treatment Effect Estimation [92.51773744318119]
  This paper empirically investigates the strengths and weaknesses of different model selection criteria. We highlight that there is a complex interplay between selection strategies, candidate estimators and the data used for comparing them.
  arXiv  Detail & Related papers  (2023-02-06T16:55:37Z)
• Privileged Graph Distillation for Cold Start Recommendation [57.918041397089254]
  The cold start problem in recommender systems requires recommending to new users (items) based on attributes without any historical interaction records. We propose a privileged graph distillation model(PGD) Our proposed model is generally applicable to different cold start scenarios with new user, new item, or new user-new item.
  arXiv  Detail & Related papers  (2021-05-31T14:05:27Z)
• Probabilistic and Variational Recommendation Denoising [56.879165033014026]
  Learning from implicit feedback is one of the most common cases in the application of recommender systems. We propose probabilistic and variational recommendation denoising for implicit feedback. We employ the proposed DPI and DVAE on four state-of-the-art recommendation models and conduct experiments on three datasets.
  arXiv  Detail & Related papers  (2021-05-20T08:59:44Z)
• Set2setRank: Collaborative Set to Set Ranking for Implicit Feedback based Recommendation [59.183016033308014]
  In this paper, we explore the unique characteristics of the implicit feedback and propose Set2setRank framework for recommendation. Our proposed framework is model-agnostic and can be easily applied to most recommendation prediction approaches.
  arXiv  Detail & Related papers  (2021-05-16T08:06:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.