mlsanityData to 14 Oct 2026

Fighting Fire with Fire: Using Antidote Data to Improve Polarization and Fairness of Recommender Systems

arXiv 1812.01504 ↗First posted 2 Dec 2018cs.IR cs.LG stat.MLcited by 37

Not on the map. Why?

Abstract (arXiv)

The increasing role of recommender systems in many aspects of society makes it essential to consider how such systems may impact social good. Various modifications to recommendation algorithms have been proposed to improve their performance for specific socially relevant measures. However, previous proposals are often not easily adapted to different measures, and they generally require the ability to modify either existing system inputs, the system's algorithm, or the system's outputs. As an alternative, in this paper we introduce the idea of improving the social desirability of recommender system outputs by adding more data to the input, an approach we view as providing `antidote' data to the system. We formalize the antidote data problem, and develop optimization-based solutions. We take as our model system the matrix factorization approach to recommendation, and we propose a set of measures to capture the polarization or fairness of recommendations. We then show how to generate antidote data for each measure, pointing out a number of computational efficiencies, and discuss the impact on overall system accuracy. Our experiments show that a modest budget for antidote data can lead to significant improvements in the polarization or fairness of recommendations.

Key facts. Cited by 37 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 9; 2023: 7; 2024: 10; 2025: 3; 2026: 4.

37 papers.

Sort:

By area:

  1. 2022Achieving Fairness at No Utility Cost via Data Reweighing with Influencecited by 38
  2. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  3. 2021TFROM: A Two-sided Fairness-Aware Recommendation Model for Both Customers and Providerscited by 31
  4. 2022Fairness in Recommender Systems: Research Landscape and Future Directionscited by 30
  5. 2022Fairness in Recommendation: Foundations, Methods and Applicationscited by 27
  6. 2022Performative Reinforcement Learningcited by 27
  7. 2021Measuring Recommender System Effects with Simulated Userscited by 20
  8. 2023Improving Recommendation Fairness via Data Augmentationcited by 18
  9. 2023A Survey on Fairness-aware Recommender Systemscited by 14
  10. 2023Large Language Models Are Better Adversaries: Exploring Generative Clean-Label Backdoor Attacks Against Text Classifierscited by 14
  11. 2021A Survey on Echo Chambers on Social Media: Description, Detection and Mitigationcited by 12
  12. 2024Leave No Patient Behind: Enhancing Medication Recommendation for Rare Disease Patientscited by 12
25 more
  1. 2021Fair Clustering Using Antidote Datacited by 10
  2. 2022Uncertainty Quantification for Fairness in Two-Stage Recommender Systemscited by 10
  3. 2022FairSR: Fairness-aware Sequential Recommendation through Multi-Task Learning with Preference Graph Embeddingscited by 9
  4. 2024Intersectional Two-sided Fairness in Recommendationcited by 8
  5. 2024FairDgcl: Fairness-aware Recommendation with Dynamic Graph Contrastive Learningcited by 8
  6. 2024Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlistscited by 7
  7. 2024CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influencecited by 6
  8. 2022FairRoad: Achieving Fairness for Recommender Systems with Optimized Antidote Datacited by 5
  9. 2024Algorithmic Drift: A Simulation Framework to Study the Effects of Recommender Systems on User Preferencescited by 5
  10. 2024Path-Specific Causal Reasoning for Fairness-aware Cognitive Diagnosiscited by 4
  11. 2023Interpolating Item and User Fairness in Multi-Sided Recommendationscited by 3
  12. 2025Stairway to Fairness: Connecting Group and Individual Fairnesscited by 3
  13. 2023Consumer-side Fairness in Recommender Systems: A Systematic Survey of Methods and Evaluationcited by 2
  14. 2023FITNESS: A Causal De-correlation Approach for Mitigating Bias in Machine Learning Softwarecited by 2
  15. 2024Fair Recommendations with Limited Sensitive Attributes: A Distributionally Robust Optimization Approachcited by 2
  16. 2023Seller-side Outcome Fairness in Online Marketplacescited by 1
  17. 2024A Unified Causal Framework for Auditing Recommender Systems for Ethical Concernscited by 1
  18. 2026Efficient Edge Rewiring Strategies for Enhancing PageRank Fairnesscited by 1
  19. 2026Measuring Individual User Fairness with User Similarity and Effectiveness Disparitycited by 1
  20. 2026Polarization by Default: Auditing Recommendation Bias in LLM-Based Content Curationcited by 1
  21. 2022Towards User-Centered Metrics for Trustworthy AI in Immersive Cyberspacecited by 0
  22. 2024Salutary Labeling with Zero Human Annotationcited by 0
  23. 2025Bias vs Bias -- Dawn of Justice: A Fair Fight in Recommendation Systemscited by 0
  24. 2025Producer-Fairness in Sequential Bundle Recommendationcited by 0
  25. 2026Fairness Attacks on Recommender Systemscited by 0