Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Randomized algorithms for precise measurement of differentially-private, personalized recommendations (2308.03735v3)

Published 7 Aug 2023 in cs.CR, cs.IR, and cs.LG

Abstract: Personalized recommendations form an important part of today's internet ecosystem, helping artists and creators to reach interested users, and helping users to discover new and engaging content. However, many users today are skeptical of platforms that personalize recommendations, in part due to historically careless treatment of personal data and data privacy. Now, businesses that rely on personalized recommendations are entering a new paradigm, where many of their systems must be overhauled to be privacy-first. In this article, we propose an algorithm for personalized recommendations that facilitates both precise and differentially-private measurement. We consider advertising as an example application, and conduct offline experiments to quantify how the proposed privacy-preserving algorithm affects key metrics related to user experience, advertiser value, and platform revenue compared to the extremes of both (private) non-personalized and non-private, personalized implementations.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Deep learning with differential privacy. In Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, 308–318.
  2. Agrawal, R. 1995. Sample mean based index policies by o (log n) regret for the multi-armed bandit problem. Advances in Applied Probability, 27(4): 1054–1078.
  3. Finite-time analysis of the multiarmed bandit problem. Machine learning, 47(2): 235–256.
  4. Targeting in advertising markets: implications for offline versus online media. The RAND Journal of Economics, 42(3): 417–443.
  5. Federated Learning and Privacy: Building privacy-preserving systems for machine learning and data science on decentralized data. Queue, 19(5): 87–114.
  6. Wide & deep learning for recommender systems. In Proceedings of the 1st workshop on deep learning for recommender systems, 7–10.
  7. Distributed Differential Privacy via Mixnets. CoRR, abs/1808.01394.
  8. Prio: Private, robust, and scalable computation of aggregate statistics. In 14th USENIX symposium on networked systems design and implementation (NSDI 17), 259–282.
  9. Deep neural networks for youtube recommendations. In Proceedings of the 10th ACM conference on recommender systems, 191–198.
  10. Online advertising and privacy. The RAND Journal of Economics, 47(1): 48–72.
  11. The permute-and-flip mechanism is identical to report-noisy-max with exponential noise. arXiv preprint arXiv:2105.07260.
  12. Differential privacy—a primer for the perplexed,”. Joint UNECE/Eurostat work session on statistical data confidentiality, 11.
  13. The algorithmic foundations of differential privacy. Foundations and Trends® in Theoretical Computer Science, 9(3–4): 211–407.
  14. Strategic bidder behavior in sponsored search auctions. Decision support systems, 43(1): 192–198.
  15. Amplification by Shuffling: From Local to Central Differential Privacy via Anonymity. CoRR, abs/1811.12469.
  16. Rappor: Randomized aggregatable privacy-preserving ordinal response. In Proceedings of the 2014 ACM SIGSAC conference on computer and communications security, 1054–1067.
  17. Learning piece-wise linear models from large scale data for ad click prediction. arXiv preprint arXiv:1704.05194.
  18. Privacy-preserving contextual bandits.
  19. Hovaness, B. 2018. Sold, for more than you should have paid! hearts-science.com.
  20. When does improved targeting increase revenue? ACM Transactions on Economics and Computation (TEAC), 5(1): 1–29.
  21. Asymptotically efficient adaptive allocation rules. Advances in applied mathematics, 6(1): 4–22.
  22. Online advertising: Heterogeneity and conflation in market design. American Economic Review, 100(2): 603–607.
  23. Permute-and-Flip: A new mechanism for differentially private selection. Advances in Neural Information Processing Systems, 33: 193–203.
  24. Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics, 1273–1282. PMLR.
  25. Private Federated Statistics in an Interactive Setting. arXiv preprint arXiv:2211.10082.
  26. Differentially private recommender systems: Building privacy into the netflix prize contenders. In Proceedings of the 15th ACM SIGKDD international conference on Knowledge discovery and data mining, 627–636.
  27. Mechanism design via differential privacy. In 48th Annual IEEE Symposium on Foundations of Computer Science (FOCS’07), 94–103. IEEE.
  28. Bid Shading by Win-Rate Estimation and Surplus Maximization. arXiv preprint arXiv:2009.09259.
  29. Targeting and privacy in mobile advertising. Marketing Science, 40(2): 193–218.
  30. Roughgarden, T. 2016. Twenty lectures on algorithmic game theory. Cambridge University Press.
  31. Sayedi, A. 2018. Real-time bidding in online display advertising. Marketing Science, 37(4): 553–568.
  32. Differentially private contextual linear bandits. Advances in Neural Information Processing Systems, 31.
  33. Shen, W. 2017. DeepCTR: Easy-to-use,Modular and Extendible package of deep-learning based CTR models. https://github.com/shenweichen/deepctr.
  34. Privacy-preserving personalized recommendation: An instance-based approach via differential privacy. In 2014 IEEE International Conference on Data Mining, 540–549. IEEE.
  35. Epicrec: Towards practical differentially private framework for personalized recommendation. In Proceedings of the 2016 ACM SIGSAC conference on computer and communications security, 180–191.
  36. Privacy enhanced matrix factorization for recommendation with local differential privacy. IEEE Transactions on Knowledge and Data Engineering, 30(9): 1770–1782.
  37. Reinforcement learning: An introduction. MIT press.
  38. Thompson, W. R. 1933. On the likelihood that one unknown probability exceeds another in view of the evidence of two samples. Biometrika, 25(3-4): 285–294.
  39. Tianchi. 2018. Ad Display/Click Data on Taobao.com.
  40. Adnostic: Privacy preserving targeted advertising.
  41. Warner, S. L. 1965. Randomized response: A survey technique for eliminating evasive answer bias. Journal of the American Statistical Association, 60(309): 63–69.
  42. Yan, Z. 2021. System Design for Recommendations and Search. eugeneyan.com.
  43. MEOW: A Space-Efficient Nonparametric Bid Shading Algorithm. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 3928–3936.
  44. Deep interest network for click-through rate prediction. In Proceedings of the 24th ACM SIGKDD international conference on knowledge discovery & data mining, 1059–1068.
  45. An efficient deep distribution network for bid shading in first-price auctions. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 3996–4004.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Allegra Laro (2 papers)
  2. Yanqing Chen (8 papers)
  3. Hao He (99 papers)
  4. Babak Aghazadeh (1 paper)

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now