mlsanityData to 14 Oct 2026

(Debiased) Contrastive Learning Loss for Recommendation (Technical Report)

arXiv 2312.08517 ↗First posted 13 Dec 2023cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In this paper, we perform a systemic examination of the recommendation losses, including listwise (softmax), pairwise(BPR), and pointwise (mean-squared error, MSE, and Cosine Contrastive Loss, CCL) losses through the lens of contrastive learning. We introduce and study both debiased InfoNCE and mutual information neural estimator (MINE), for the first time, under the recommendation setting. We also relate and differentiate these two losses with the BPR loss through the lower bound analysis. Furthermore, we present the debiased pointwise loss (for both MSE and CCL) and theoretically certify both iALS and EASE, two of the most popular linear models, are inherently debiased. The empirical experimental results demonstrate the effectiveness of the debiased losses and newly introduced mutual-information losses outperform the existing (biased) ones.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 30 of its 59 references that are in the map. First posted on arXiv 13 Dec 2023.

Builds on

30 of 59 references.

References · 30

  1. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  2. 2017Graph Attention Networkscited by 8,923
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Contrastive Multiview Codingcited by 1,301
  5. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,139
  6. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,138
  7. 2019Neural Graph Collaborative Filteringcited by 661
  8. 2020Debiased Contrastive Learningcited by 356
  9. 2018Variational Autoencoders for Collaborative Filteringcited by 310
  10. 2020Self-supervised Graph Learning for Recommendationcited by 305
  11. 2020Neural Collaborative Filtering vs. Matrix Factorization Revisitedcited by 123
  12. 2017Fast Matrix Factorization for Online Recommendation with Implicit Feedbackcited by 101
18 more
  1. 2019Embarrassingly Shallow Autoencoders for Sparse Datacited by 94
  2. 2014On Using Very Large Target Vocabulary for Neural Machine Translationcited by 80
  3. 2015Modeling User Exposure in Recommendationcited by 69
  4. 2021SimpleX: A Simple and Strong Baseline for Collaborative Filteringcited by 65
  5. 2022Towards Representation Alignment and Uniformity in Collaborative Filteringcited by 57
  6. 2019On the Difficulty of Evaluating Baselines: A Study on Recommender Systemscited by 46
  7. 2020Contrastive Learning for Debiased Candidate Generation in Large-Scale Recommender Systemscited by 38
  8. 2020Simplify and Robustify Negative Sampling for Implicit Collaborative Filteringcited by 34
  9. 2021Revisiting the Performance of iALS on Item Recommendation Benchmarkscited by 21
  10. 2021On Sampling Top-K Recommendation Evaluationcited by 20
  11. 2021Item Recommendation from Implicit Feedbackcited by 18
  12. 2021Towards a Better Understanding of Linear Models for Recommendationcited by 18
  13. 2018A Study of Position Bias in Digital Library Recommender Systemscited by 13
  14. 2023BotTriNet: A Unified and Efficient Embedding for Social Bots Detection via Metric Learningcited by 13
  15. 2021On Estimating Recommendation Evaluation Metrics under Samplingcited by 9
  16. 2022Towards Reliable Item Sampling for Recommendation Evaluationcited by 6
  17. 2022Generation-Augmented Query Expansion For Code Retrievalcited by 6
  18. 2021iALS++: Speeding up Matrix Factorization with Subspace Optimizationcited by 3

Built on by

Not cited yet.