mlsanityData to 7 Oct 2026

Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)

arXiv 2312.08520 ↗First posted 13 Dec 2023cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Inspired by the success of contrastive learning, we systematically examine recommendation losses, including listwise (softmax), pairwise (BPR), and pointwise (MSE and CCL) losses. In this endeavor, we introduce InfoNCE+, an optimized generalization of InfoNCE with balance coefficients, and highlight its performance advantages, particularly when aligned with our new decoupled contrastive loss, MINE+. We also leverage debiased InfoNCE to debias pointwise recommendation loss (CCL) as Debiased CCL. Interestingly, our analysis reveals that linear models like iALS and EASE are inherently debiased. Empirical results demonstrates the effectiveness of MINE+ and Debiased-CCL.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 33 of its 55 references that are in the map. First posted on arXiv 13 Dec 2023.

Builds on

33 of 55 references.

References · 33

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  2. 2017Graph Attention Networkscited by 8,854
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  5. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  6. 2017Neural Collaborative Filteringcited by 1,108
  7. 2018MINE: Mutual Information Neural Estimationcited by 680
  8. 2020Debiased Contrastive Learningcited by 354
  9. 2020Self-supervised Graph Learning for Recommendationcited by 305
  10. 2020Bias and Debias in Recommender System: A Survey and Future Directionscited by 239
  11. 2019Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approachescited by 181
  12. 2020Neural Collaborative Filtering vs. Matrix Factorization Revisitedcited by 123
21 more
  1. 2017Fast Matrix Factorization for Online Recommendation with Implicit Feedbackcited by 100
  2. 2019Embarrassingly Shallow Autoencoders for Sparse Datacited by 93
  3. 2014On Using Very Large Target Vocabulary for Neural Machine Translationcited by 80
  4. 2017On Sampling Strategies for Neural Network-based Collaborative Filteringcited by 71
  5. 2015Modeling User Exposure in Recommendationcited by 69
  6. 2021SimpleX: A Simple and Strong Baseline for Collaborative Filteringcited by 65
  7. 2022Towards Representation Alignment and Uniformity in Collaborative Filteringcited by 57
  8. 2019On the Difficulty of Evaluating Baselines: A Study on Recommender Systemscited by 46
  9. 2022Unbiased Supervised Contrastive Learningcited by 40
  10. 2020Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systemscited by 38
  11. 2020Simplify and Robustify Negative Sampling for Implicit Collaborative Filteringcited by 34
  12. 2021Revisiting the Performance of iALS on Item Recommendation Benchmarkscited by 21
  13. 2021On Sampling Top-K Recommendation Evaluationcited by 20
  14. 2021Item Recommendation from Implicit Feedbackcited by 17
  15. 2018A Study of Position Bias in Digital Library Recommender Systemscited by 13
  16. 2023BotTriNet: A Unified and Efficient Embedding for Social Bots Detection via Metric Learningcited by 13
  17. 2021On Estimating Recommendation Evaluation Metrics under Samplingcited by 8
  18. 2022Towards Reliable Item Sampling for Recommendation Evaluationcited by 5
  19. 2022Generation-Augmented Query Expansion For Code Retrievalcited by 5
  20. 2021iALS++: Speeding up Matrix Factorization with Subspace Optimizationcited by 3
  21. 2023Impression-Informed Multi-Behavior Recommender System: A Hierarchical Graph Attention Approachcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 3; 2025: 1; 2026: 1.

5 papers.

  1. 2024A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspectivecited by 9
  2. 2025Future Link Prediction Without Memory or Aggregationcited by 5
  3. 2024Understanding and Scaling Collaborative Filtering Optimization from the Perspective of Matrix Rankcited by 1
  4. 2024Multi-Margin Cosine Loss: Proposal and Application in Recommender Systemscited by 0
  5. 2026Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Losscited by 0