Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
133 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
46 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists (2404.04269v2)

Published 19 Mar 2024 in cs.IR, cs.LG, and cs.SI

Abstract: We investigate algorithmic collective action in transformer-based recommender systems. Our use case is a music streaming platform where a collective of fans aims to promote the visibility of an underrepresented artist by strategically placing one of their songs in the existing playlists they control. We introduce two easily implementable strategies to select the position at which to insert the song with the goal to boost recommendations at test time. The strategies exploit statistical properties of the learner by targeting discontinuities in the recommendations, and leveraging the long-tail nature of song distributions. We evaluate the efficacy of our strategies using a publicly available recommender system model released by a major music streaming platform. Our findings reveal that through strategic placement even small collectives (controlling less than 0.01\% of the training data) can achieve up to $40\times$ more test time recommendations than an average song with the same number of training set occurrences. Focusing on the externalities of the strategy, we find that the recommendations of other songs are largely preserved, and the newly gained recommendations are distributed across various artists. Together, our findings demonstrate how carefully designed collective action strategies can be effective while not necessarily being adversarial.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (69)
  1. Platforms, power, and promotion: Evidence from spotify playlists. The Journal of Industrial Economics, 69(3):653–691, 2021.
  2. Christine Bauer. Allowing for equal opportunities for artists in music recommendation. In Proceedings of the 1st Workshop on Human-Centric Music Information Research Systems, pages 16–18, 2019.
  3. Christine Bauer. Report on the ISMIR 2020 special session: how do we help artists? ACM SIGIR Forum, 54(2), 2020.
  4. Music recommender systems: challenges and opportunities for non-superstar artists. In 30th Bled eConference, pages 21–32, 2017.
  5. A game-theoretic approach to recommendation systems with strategic content providers. In Advances in Neural Information Processing Systems, volume 31, 2018.
  6. Track Mix Generation on Music Streaming Services Using Transformers. In Proceedings of the 17th ACM Conference on Recommender Systems, pages 112–115, 2023a.
  7. A Scalable Framework for Automatic Playlist Continuation on Music Streaming Services. In Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 464–474, 2023b.
  8. Emily Blake. Data shows 90 percent of streams go to the top 1 percent of artists, 2020. https://www.rollingstone.com/pro/news/top-1-percent-streaming-1055005.
  9. Robin Burke. Multisided fairness for recommendation. ArXiv preprint arXiv:1707.00093, 2017.
  10. Òscar Celma. Music Recommendation and Discovery: The Long Tail, Long Fail, and Long Play in the Digital Music Space. Springer Berlin, Heidelberg, 2010.
  11. Measuring strategization in recommendation: Users adapt their behavior to shape future content. Preprint, 2023a.
  12. User strategization and trustworthy algorithms. ArXiv preprint arXiv:2312.17666, 2023b.
  13. Recsys Challenge 2018: Automatic Music Playlist Continuation. In Proceedings of the 12th ACM Conference on Recommender Systems, RecSys ’18, pages 527–528, 2018.
  14. Digital music and the “death of the long tail”. Journal of Business Research, 101:454–460, 2019.
  15. Music recommendation: Audio neighbourhoods to discover music in the long tail. In Case-Based Reasoning Research and Development, pages 73–87. Springer International Publishing, 2015.
  16. Online algorithmic recourse by collective action. ICML Workshop on Algorithmic Recourse, 2023.
  17. Recommender systems as dynamical systems: Interactions with viewers and creators. In Workshop on Recommendation Ecosystems: Modeling, Optimization and Incentive Design, 2024.
  18. Fairroad: Achieving fairness for recommender systems with optimized antidote data. In Proceedings of the 27th ACM on Symposium on Access Control Models and Technologies, SACMAT ’22, page 173–184, 2022.
  19. What is fair? exploring the artists’ perspective on the fairness of music streaming platforms. In Human-Computer Interaction – INTERACT 2021, volume 12933 of Lecture Notes in Computer Science, pages 562–584, 2021.
  20. Shilling attacks against recommender systems: a comprehensive survey. Artificial Intelligence Review, 42:767–799, 2014.
  21. Contextual and sequential user embeddings for large-scale music recommendation. In Proceedings of the 14th ACM Conference on Recommender Systems, page 53–62, 2020.
  22. Russell Hardin. Collective action. Rff Press, 1982.
  23. Performative prediction: Past and future. arXiv preprint arXiv:2310.16608, 2023.
  24. Algorithmic Collective Action in Machine Learning. In Proceedings of the 40th International Conference on Machine Learning, volume 202, pages 12570–12586. PMLR, 2023.
  25. Recommending to strategic users. ArXiv preprint arXiv:2302.06559, 2023.
  26. Data poisoning attacks to deep learning based recommender systems. In Proceedings 2021 Network and Distributed System Security Symposium, NDSS 2021. Internet Society, 2021.
  27. Group fairness for content creators: the role of human and algorithmic biases under popularity-based recommendations. In Proceedings of the 17th ACM Conference on Recommender Systems, page 863–870, 2023.
  28. Competition, alignment, and equilibria in digital marketplaces. Proceedings of the AAAI Conference on Artificial Intelligence, 37(5):5689–5696, 2023.
  29. What recommenders recommend – an analysis of accuracy, popularity, and sales diversity effects. In User Modeling, Adaptation, and Personalization, pages 25–37. Springer Berlin Heidelberg, 2013.
  30. Algorithmic management and algorithmic competencies: Understanding and appropriating algorithms in gig work. In Information in Contemporary Society, pages 578–589, 2019.
  31. Facing the cold start problem in recommender systems. Expert Systems with Applications, 41(4, Part 2):2065–2073, 2014.
  32. Lee Marshall. ‘let’s keep music special. f—spotify’: on-demand streaming and the controversy over artist royalties. Creative Industries Journal, 8(2):177–189, 2015.
  33. The critical mass in collective action. Cambridge University Press, 1993.
  34. Towards a fair marketplace: Counterfactual evaluation of the trade-off between relevance, fairness & satisfaction in recommendation systems. In Proceedings of the 27th ACM International Conference on Information and Knowledge Management, page 2243–2251, 2018.
  35. Optimizing long-term social welfare in recommender systems: a constrained matching approach. In Proceedings of the 37th International Conference on Machine Learning, ICML’20, 2020.
  36. Exploiting sequential music preferences via optimisation-based sequencing. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, page 4759–4765, 2023.
  37. Philip M. Napoli. Requiem for the long tail: Towards a political economy of content aggregation and fragmentation. International Journal of Media & Cultural Politics, 12(3):341–356, 2016.
  38. Rank list sensitivity of recommender systems to interaction perturbations. In Proceedings of the 31st ACM International Conference on Information & Knowledge Management, page 1584–1594, 2022.
  39. Mancur Olson. The logic of collective action: public goods and the theory of groups. Harvard University Press, 1965.
  40. Collaborative recommendation: A robustness analysis. ACM Trans. Internet Technol., 4(4):344–377, 2004.
  41. A classification of feedback loops and their relation to biases in automated decision-making systems. In Proceedings of the 3rd ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization, 2023.
  42. Performative Prediction. In Proceedings of the 37th International Conference on Machine Learning, volume 119, pages 7599–7609. PMLR, 2020.
  43. Platform pop: disentangling spotify’s intermediary role in the music industry. Information, Communication & Society, 25(1):74–92, 2022.
  44. Fighting fire with fire: Using antidote data to improve polarization and fairness of recommender systems. In Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, page 231–239, 2019.
  45. Methods and metrics for cold-start recommendations. In Proceedings of the 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, page 253–260, 2002.
  46. Poison frogs! targeted clean-label poisoning attacks on neural networks. In Advances in Neural Information Processing Systems, volume 31, 2018.
  47. Glaze: Protecting artists from style mimicry by text-to-image models. ArXiv preprint arXiv:2302.04222, 2023.
  48. Shilling attacks against collaborative recommender systems: a review. Artificial Intelligence Review, 53:291–319, 2020.
  49. Understanding shilling attacks and their detection traits: A comprehensive survey. IEEE Access, 8:171703–171715, 2020.
  50. Revisiting adversarially learned injection attacks against recommender systems. In Proceedings of the 14th ACM Conference on Recommender Systems, page 318–327, 2020.
  51. Distributed computing in practice: the condor experience. Concurrency and Computation: Practice and Experience, 17(2-4):323–356, 2005.
  52. A comprehensive survey on poisoning attacks and countermeasures in machine learning. ACM Comput. Surv., 55(8), 2022.
  53. “Splendid Isolation”: The reproduction of music industry inequalities in Spotify’s recommendation system. New Media & Society, 25(7):1580–1604, 2023.
  54. Automatic music playlist generation via simulation-based reinforcement learning. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD ’23, page 4948–4957, 2023.
  55. Designing AI Tools to Address Power Imbalances in Digital Labor Platforms, pages 121–137. Springer International Publishing, 2023.
  56. Five approaches to collecting tags for music. In ISMIR, 2008.
  57. Union of Musicians and Allied Workers. Justice at Spotify, mar 2021. URL https://weareumaw.org/justice-at-spotify.
  58. Can "Conscious Data Contribution" Help Users to Exert "Data Leverage" Against Technology Companies? Proc. ACM Hum.-Comput. Interact., 5(CSCW1), apr 2021.
  59. “Data Strikes”: Evaluating the Effectiveness of a New Form of Collective Action Against Technology Companies. In The World Wide Web Conference, pages 1931–1943, 2019.
  60. Data Leverage: A Framework for Empowering the Public in Its Relationship with Technology Companies. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency, FAccT ’21, pages 215–227, 2021.
  61. Addressing interpretability and cold-start in matrix factorization for recommender systems. IEEE Transactions on Knowledge and Data Engineering, 31(7):1253–1266, 2019.
  62. Triple adversarial learning for influence based poisoning attack in recommender systems. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, KDD ’21, page 1830–1840, 2021.
  63. Noah Yoo. Could Spotify’s New Discovery Mode Be Considered Payola?, nov 2020. URL https://pitchfork.com/thepitch/could-spotifys-new-discovery-mode-be-considered-payola.
  64. Black-box attacks on sequential recommenders via data-free model extraction. In Proceedings of the 15th ACM Conference on Recommender Systems, page 44–54, 2021.
  65. Defending substitution-based profile pollution attacks on sequential recommenders. In Proceedings of the 16th ACM Conference on Recommender Systems, page 59–70, 2022.
  66. An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation. ACM Trans. Intell. Syst. Technol., 10(5), sep 2019.
  67. Fairness in ranking, part ii: Learning-to-rank and recommender systems. ACM Comput. Surv., 55(6), dec 2022. ISSN 0360-0300.
  68. Practical data poisoning attack against next-item recommendation. In Proceedings of The Web Conference 2020, page 2458–2464, 2020.
  69. Data poisoning attack against recommender system using incomplete and perturbed data. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, KDD ’21, page 2154–2164, 2021.
Citations (1)
View on Semantic Scholar

Summary

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

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

Tweets