Sparse Contrastive Learning for Content-Based Cold Item Recommendation

• URL: http://arxiv.org/abs/2604.12990v1
• Date: Tue, 14 Apr 2026 17:24:25 GMT
• Title: Sparse Contrastive Learning for Content-Based Cold Item Recommendation
• Abstract summary: Item cold-start is a pervasive challenge for collaborative filtering (CF) recommender systems.<n>Existing methods often train cold-start models by mapping auxiliary item content, such as images or text descriptions, into the embedding space of a CF model.<n>We propose to avoid this limitation with purely content-based modeling of cold items, i.e. without alignment with CF user or item embeddings.
• Score: 5.958603849321135
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Item cold-start is a pervasive challenge for collaborative filtering (CF) recommender systems. Existing methods often train cold-start models by mapping auxiliary item content, such as images or text descriptions, into the embedding space of a CF model. However, such approaches can be limited by the fundamental information gap between CF signals and content features. In this work, we propose to avoid this limitation with purely content-based modeling of cold items, i.e. without alignment with CF user or item embeddings. We instead frame cold-start prediction in terms of item-item similarity, training a content encoder to project into a latent space where similarity correlates with user preferences. We define our training objective as a sparse generalization of sampled softmax loss with the $α$-entmax family of activation functions, which allows for sharper estimation of item relevance by zeroing gradients for uninformative negatives. We then describe how this Sampled Entmax for Cold-start (SEMCo) training regime can be extended via knowledge distillation, and show that it outperforms existing cold-start methods and standard sampled softmax in ranking accuracy. We also discuss the advantages of purely content-based modeling, particularly in terms of equity of item outcomes.

Related papers

• Learning Sparse Representations of Multimodal Content for Enhanced Cold Item Recommendation [5.958603849321135]
  We argue that sparse embeddings have notable advantages over standard dense vectors in this content-based cold-start paradigm.<n>We show that the resulting sparse embeddings achieve significant improvements in cold-start recommendation accuracy over dense embeddings at considerably lower storage costs.
  arXiv  Detail & Related papers  (2026-07-19T10:45:57Z)
• CoreUnlearn: Rethinking Concept Unlearning through Disentangled Component-Level Erasure in Text-guided Diffusion Models [72.22994966489551]
  CoreUnlearn aims to disentangle and remove the erasure-critical component of the undesirable concept.<n>It achieves effective concept erasure with minimal impact on overall model performance.
  arXiv  Detail & Related papers  (2026-06-01T04:09:45Z)
• MDiffFR: Modality-Guided Diffusion Generation for Cold-start Items in Federated Recommendation [21.56907456486488]
  Federated recommendations (FRs) provide personalized services while preserving user privacy by keeping user data on local clients.<n>Due to the strict privacy constraints inherent in FRs, access to user-item interaction data and user profiles across clients is highly restricted.<n>We propose MDiffFR, a novel generation-based modality-guided diffusion method for cold-start items in FRs.
  arXiv  Detail & Related papers  (2025-12-31T08:29:34Z)
• Concept-Aware Batch Sampling Improves Language-Image Pretraining [78.53540190580189]
  Concept-Aware Batch Sampling (CABS) is a simple yet effective batch sampling framework that flexibly constructs batches on-the-fly.<n>We show that CABS significantly benefits CLIP/SigLIP model classes and yields highly performant models.<n>Overall, CABS represents a strong open-source alternative to proprietary online data curation algorithms.
  arXiv  Detail & Related papers  (2025-11-25T18:58:07Z)
• 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)
• Let It Go? Not Quite: Addressing Item Cold Start in Sequential Recommendations with Content-Based Initialization [0.8437187555622164]
  We introduce a small trainable delta to frozen embeddings that enables the model to adapt item representations without letting them go too far from their original semantic structure.<n>This approach demonstrates consistent improvements across multiple datasets and modalities.
  arXiv  Detail & Related papers  (2025-07-25T17:57:31Z)
• Personalized Diffusion Model Reshapes Cold-Start Bundle Recommendation [2.115789253980982]
  We propose a new approach to generate a bundle in distribution space for each user to tackle the cold-start challenge.<n>DisCo relies on a personalized Diffusion backbone, enhanced by disentangled aspects for the user's interest.<n>DisCo outperforms five comparative baselines by a large margin on three real-world datasets.
  arXiv  Detail & Related papers  (2025-05-20T20:52:31Z)
• 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)
• Sequential Recommendation via Stochastic Self-Attention [68.52192964559829]
  Transformer-based approaches embed items as vectors and use dot-product self-attention to measure the relationship between items. We propose a novel textbfSTOchastic textbfSelf-textbfAttention(STOSA) to overcome these issues. We devise a novel Wasserstein Self-Attention module to characterize item-item position-wise relationships in sequences.
  arXiv  Detail & Related papers  (2022-01-16T12:38:45Z)
• SelfCF: A Simple Framework for Self-supervised Collaborative Filtering [72.68215241599509]
  Collaborative filtering (CF) is widely used to learn informative latent representations of users and items from observed interactions. We propose a self-supervised collaborative filtering framework (SelfCF) that is specially designed for recommender scenario with implicit feedback. We show that SelfCF can boost up the accuracy by up to 17.79% on average, compared with a self-supervised framework BUIR.
  arXiv  Detail & Related papers  (2021-07-07T05:21:12Z)
• 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)
• Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-Start Users [111.28351584726092]
  We consider the conversational recommendation for cold-start users, where a system can both ask the attributes from and recommend items to a user interactively. Our Conversational Thompson Sampling (ConTS) model holistically solves all questions in conversational recommendation by choosing the arm with the maximal reward to play.
  arXiv  Detail & Related papers  (2020-05-23T08:56:37Z)

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.