mlsanityData to 7 Oct 2026

Cold-start Bundle Recommendation via Popularity-based Coalescence and Curriculum Heating

arXiv 2310.03813 ↗First posted 5 Oct 2023cs.IR cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

How can we recommend cold-start bundles to users? The cold-start problem in bundle recommendation is crucial because new bundles are continuously created on the Web for various marketing purposes. Despite its importance, existing methods for cold-start item recommendation are not readily applicable to bundles. They depend overly on historical information, even for less popular bundles, failing to address the primary challenge of the highly skewed distribution of bundle interactions. In this work, we propose CoHeat (Popularity-based Coalescence and Curriculum Heating), an accurate approach for cold-start bundle recommendation. CoHeat first represents users and bundles through graph-based views, capturing collaborative information effectively. To estimate the user-bundle relationship more accurately, CoHeat addresses the highly skewed distribution of bundle interactions through a popularity-based coalescence approach, which incorporates historical and affiliation information based on the bundle's popularity. Furthermore, it effectively learns latent representations by exploiting curriculum learning and contrastive learning. CoHeat demonstrates superior performance in cold-start bundle recommendation, achieving up to 193% higher nDCG@20 compared to the best competitor.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 38 of its 77 references that are in the map. First posted on arXiv 5 Oct 2023.

Builds on

38 of 77 references.

References · 38

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  3. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,168
  4. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  5. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  6. 2020Contrastive Learning with Hard Negative Samplescited by 619
  7. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  8. 2020Self-supervised Graph Learning for Recommendationcited by 305
  9. 2021ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfercited by 231
  10. 2021Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendationcited by 173
  11. 2022SimGRACE: A Simple Framework for Graph Contrastive Learning without Data Augmentationcited by 171
  12. 2014Collaborative Deep Learning for Recommender Systemscited by 95
26 more
  1. 2021Contrastive Learning for Cold-Start Recommendationcited by 77
  2. 2023LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendationcited by 72
  3. 2019Warm Up Cold-start Advertisements: Improving CTR Predictions via Learning to Learn ID Embeddingscited by 65
  4. 2019POG: Personalized Outfit Generation for Fashion Recommendation at Alibaba iFashioncited by 63
  5. 2022Towards Representation Alignment and Uniformity in Collaborative Filteringcited by 57
  6. 2020Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systemscited by 38
  7. 2021Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translationcited by 28
  8. 2023Heterogeneous Graph Contrastive Learning for Recommendationcited by 28
  9. 2022CrossCBR: Cross-view Contrastive Learning for Bundle Recommendationcited by 26
  10. 2020Bundle Recommendation with Graph Convolutional Networkscited by 24
  11. 2022Multi-view Intent Disentangle Graph Networks for Bundle Recommendationcited by 22
  12. 2019Personalized Bundle List Recommendationcited by 21
  13. 2021Personalized Bundle Recommendation in Online Gamescited by 15
  14. 2023Contrastive Collaborative Filtering for Cold-Start Item Recommendationcited by 15
  15. 2020Curriculum Learning with Hindsight Experience Replay for Sequential Object Manipulation Taskscited by 10
  16. 2022Bundle MCR: Towards Conversational Bundle Recommendationcited by 10
  17. 2019A Hierarchical Self-Attentive Model for Recommending User-Generated Item Listscited by 9
  18. 2022Towards Personalized Bundle Creative Generation with Contrastive Non-Autoregressive Decodingcited by 9
  19. 2022Improving Item Cold-start Recommendation via Model-agnostic Conditional Variational Autoencodercited by 8
  20. 2022Accurate Action Recommendation for Smart Home via Two-Level Encoders and Commonsense Knowledgecited by 8
  21. 2019Consistency-Aware Recommendation for User-Generated ItemList Continuationcited by 7
  22. 2021Density-Based Dynamic Curriculum Learning for Intent Detectioncited by 7
  23. 2022SUGER: A Subgraph-based Graph Convolutional Network Method for Bundle Recommendationcited by 5
  24. 2019Data Context Adaptation for Accurate Recommendation with Additional Informationcited by 3
  25. 2022Accurate Bundle Matching and Generation via Multitask Learning with Partially Shared Parameterscited by 3
  26. 2022Diversely Regularized Matrix Factorization for Accurate and Aggregately Diversified Recommendationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Personalized Diffusion Model Reshapes Cold-Start Bundle Recommendationcited by 3
  2. 2025Does Knowledge Distillation Matter for Large Language Model based Bundle Generation?cited by 1
  3. 2026Dual-Enhancement Product Bundling: Bridging Interactive Graph and Large Language Modelcited by 0
  4. 2026Denoising Implicit Feedback for Cold-start Recommendationcited by 0