mlsanityData to 7 Oct 2026

Item Recommendation from Implicit Feedback

arXiv 2101.08769 ↗First posted 21 Jan 2021cs.IR cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

The task of item recommendation is to select the best items for a user from a large catalogue of items. Item recommenders are commonly trained from implicit feedback which consists of past actions that are positive only. Core challenges of item recommendation are (1) how to formulate a training objective from implicit feedback and (2) how to efficiently train models over a large item catalogue. This article provides an overview of item recommendation, its unique characteristics and some common approaches. It starts with an introduction to the problem and discusses different training objectives. The main body deals with learning algorithms and presents sampling based algorithms for general recommenders and more efficient algorithms for dot product models. Finally, the application of item recommenders for retrieval tasks is discussed.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 10 of its 33 references that are in the map. First posted on arXiv 21 Jan 2021.

Builds on

10 of 33 references.

References · 10

  1. 2020Neural Collaborative Filtering vs. Matrix Factorization Revisitedcited by 123
  2. 2019A Troubling Analysis of Reproducibility and Progress in Recommender Systems Researchcited by 65
  3. 2019On the Difficulty of Evaluating Baselines: A Study on Recommender Systemscited by 46
  4. 2015Learning to Hash for Indexing Big Data - A Surveycited by 39
  5. 2017Adaptive Sampled Softmax with Kernel Based Samplingcited by 38
  6. 2019Sampled Softmax with Random Fourier Featurescited by 33
  7. 2018Beyond Greedy Ranking: Slate Optimization via List-CVAEcited by 21
  8. 2016A Generic Coordinate Descent Framework for Learning from Implicit Feedbackcited by 16
  9. 2018Efficient Training on Very Large Corpora via Gramian Estimationcited by 9
  10. 2017TAPAS: Two-pass Approximate Adaptive Sampling for Softmaxcited by 3

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 2; 2023: 7; 2024: 4; 2025: 2.

17 papers.

Sort:

By area:

  1. 2023Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusioncited by 72
  2. 2024On Softmax Direct Preference Optimization for Recommendationcited by 64
  3. 2023gSASRec: Reducing Overconfidence in Sequential Recommendation Trained with Negative Samplingcited by 29
  4. 2021Revisiting the Performance of iALS on Item Recommendation Benchmarkscited by 21
  5. 2024How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspectivecited by 21
  6. 2024Language Representations Can be What Recommenders Need: Findings and Potentialscited by 18
  7. 2023Robust Collaborative Filtering to Popularity Distribution Shiftcited by 12
  8. 2022Revisiting Neighborhood-based Link Prediction for Collaborative Filteringcited by 11
  9. 2024Preference Diffusion for Recommendationcited by 8
  10. 2023Revisiting Recommendation Loss Functions through Contrastive Learning (Technical Report)cited by 5
  11. 2023BSL: Understanding and Improving Softmax Loss for Recommendationcited by 5
  12. 2021iALS++: Speeding up Matrix Factorization with Subspace Optimizationcited by 3
5 more
  1. 2022Bilateral Self-unbiased Learning from Biased Implicit Feedbackcited by 3
  2. 2023UIPC-MF: User-Item Prototype Connection Matrix Factorization for Explainable Collaborative Filteringcited by 0
  3. 2023(Debiased) Contrastive Learning Loss for Recommendation (Technical Report)cited by 0
  4. 2025NDCG-Consistent Softmax Approximation with Accelerated Convergencecited by 0
  5. 2025Extracting Interaction-Aware Monosemantic Concepts in Recommender Systemscited by 0