Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 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

Scalable Algorithms for Individual Preference Stable Clustering (2403.10365v1)

Published 15 Mar 2024 in cs.DS, cs.AI, cs.CY, and cs.LG

Abstract: In this paper, we study the individual preference (IP) stability, which is an notion capturing individual fairness and stability in clustering. Within this setting, a clustering is $\alpha$-IP stable when each data point's average distance to its cluster is no more than $\alpha$ times its average distance to any other cluster. In this paper, we study the natural local search algorithm for IP stable clustering. Our analysis confirms a $O(\log n)$-IP stability guarantee for this algorithm, where $n$ denotes the number of points in the input. Furthermore, by refining the local search approach, we show it runs in an almost linear time, $\tilde{O}(nk)$.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (58)
  1. Constant approximation for individual preference stable clustering. Advances in Neural Information Processing Systems, 36, 2023.
  2. Fair clustering via equitable group representations. In Proceedings of the Conference on Fairness, Accountability, and Transparency (FAccT), page 504–514, 2021.
  3. M. Ackerman and S. Ben-David. Clusterability: A theoretical study. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2009.
  4. Individual preference stability for clustering. In International Conference on Machine Learning, pages 197–246, 2022.
  5. Clustering without over-representation. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pages 267–275, 2019.
  6. Distributional individual fairness in clustering. arXiv preprint arXiv:2006.12589, 2020.
  7. P. Awasthi and M.-F. Balcan. Center based clustering: A foundational perspective. In Handbook of Cluster Analysis. CRC Press, 2014.
  8. Center-based clustering under perturbation stability. Information Processing Letters, 112(1-2):49–54, 2012.
  9. Scalable fair clustering. In International Conference on Machine Learning, pages 405–413. PMLR, 2019.
  10. M.-F. Balcan and Y. Liang. Clustering under perturbation resilience. SIAM Journal on Computing, 45(1):102–155, 2016.
  11. A discriminative framework for clustering via similarity functions. In Symposium on Theory of computing (STOC), 2008.
  12. Clustering under approximation stability. Journal of the ACM (JACM), 60(2):1–34, 2013.
  13. Envy-free classification. Advances in Neural Information Processing Systems, 32, 2019.
  14. Fair algorithms for clustering. Advances in Neural Information Processing Systems, 32, 2019.
  15. On the cost of essentially fair clusterings. In Approximation, Randomization, and Combinatorial Optimization. Algorithms and Techniques (APPROX/RANDOM 2019). Schloss Dagstuhl-Leibniz-Zentrum fuer Informatik, 2019.
  16. Y. Bilu and N. Linial. Are stable instances easy? Combinatorics, Probability and Computing, 21(5):643–660, 2012.
  17. A. Bogomolnaia and M. O. Jackson. The stability of hedonic coalition structures. Games and Economic Behavior, 38(2):201–230, 2002.
  18. A pairwise fair and community-preserving approach to k-center clustering. In International Conference on Machine Learning (ICML), 2020.
  19. Fairness, semi-supervised learning, and more: A general framework for clustering with stochastic pairwise constraints. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021.
  20. A new notion of individually fair clustering: α𝛼\alphaitalic_α-equitable k𝑘kitalic_k-center. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
  21. Matroid and knapsack center problems. Algorithmica, 75(1):27–52, 2016.
  22. Proportionally fair clustering. In International Conference on Machine Learning, pages 1032–1041, 2019.
  23. Fair clustering through fairlets. Advances in Neural Information Processing Systems, 30, 2017.
  24. How to solve fair k𝑘kitalic_k-center in massive data models. In Proceedings of the International Conference on Machine Learning (ICML), pages 1877–1886, 2020.
  25. Approximating fair clustering with cascaded norm objectives. In Proceedings of the 2022 Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), pages 2664–2683, 2022.
  26. Fair representation clustering with several protected classes. In Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pages 814–823, 2022.
  27. Clustering is difficult only when it does not matter. arXiv:1205.4891 [cs.LG]], 2012.
  28. J. H. Dreze and J. Greenberg. Hedonic coalitions: Optimality and stability. Econometrica, 48(4):987–1003, 1980.
  29. Fairness through awareness. In Innovations in Theoretical Computer Science (ITCS), 2012.
  30. F. Edward Su. Rental harmony: Sperner’s lemma in fair division. The American mathematical monthly, 106(10):930–942, 1999.
  31. Price of pareto optimality in hedonic games. Artificial Intelligence, 288:103357, 2020.
  32. D. K. Foley. Resource allocation and the public sector. Yale University, 1966.
  33. Which is the fairest (rent division) of them all? In Proceedings of the 2016 ACM Conference on Economics and Computation, pages 67–84, 2016.
  34. Socially fair k𝑘kitalic_k-means clustering. In Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (FAccT), pages 438–448, 2021.
  35. Constant-factor approximation algorithms for socially fair k𝑘kitalic_k-clustering. arXiv preprint arXiv:2206.11210, 2022.
  36. T. F. Gonzalez. Clustering to minimize the maximum intercluster distance. Theoretical Computer Science, 38:293–306, 1985.
  37. Approximation algorithms for fair range clustering. In International Conference on Machine Learning, pages 13270–13284. PMLR, 2023.
  38. Fair k𝑘kitalic_k-centers via maximum matching. In Proceedings of the International Conference on Machine Learning (ICML), pages 4940–4949, 2020.
  39. A center in your neighborhood: Fairness in facility location. In Symposium on Foundations of Responsible Computing (FORC), 2020.
  40. Feature-based individual fairness in k-clustering. In Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2023.
  41. Monte-carlo approximation algorithms for enumeration problems. Journal of algorithms, 10(3):429–448, 1989.
  42. Fair k𝑘kitalic_k-center clustering for data summarization. In 36th International Conference on Machine Learning, ICML 2019, pages 5984–6003. International Machine Learning Society (IMLS), 2019.
  43. The matroid median problem. In Proceedings of the Symposium on Discrete Algorithms (SODA), pages 1117–1130, 2011.
  44. Constant approximation for k𝑘kitalic_k-median and k𝑘kitalic_k-means with outliers via iterative rounding. In Proceedings of the 50th Annual ACM SIGACT Symposium on Theory of Computing, pages 646–659, 2018.
  45. E. Laber and L. Murtinho. Optimization of inter-group criteria for clustering with minimum size constraints. Advances in Neural Information Processing Systems (NeurIPS), 36, 2023.
  46. S. Mahabadi and A. Vakilian. Individual fairness for k𝑘kitalic_k-clustering. In International Conference on Machine Learning (ICML), 2020.
  47. K. Makarychev and Y. Makarychev. Metric perturbation resilience. arXiv preprint arXiv:1607.06442, 2016.
  48. Y. Makarychev and A. Vakilian. Approximation algorithms for socially fair clustering. In Conference on Learning Theory (COLT), pages 3246–3264. PMLR, 2021.
  49. J. Matoušek. Bi-lipschitz embeddings into low-dimensional euclidean spaces. Commentationes Mathematicae Universitatis Carolinae, 31(3):589–600, 1990.
  50. E. Micha and N. Shah. Proportionally fair clustering revisited. In International Colloquium on Automata, Languages, and Programming (ICALP), 2020.
  51. M. Negahbani and D. Chakrabarty. Better algorithms for individually fair k𝑘kitalic_k-clustering. Advances in Neural Information Processing Systems (NeurIPS), 2021.
  52. A. D. Procaccia. Cake cutting: Not just child’s play. Communications of the ACM, 56(7):78–87, 2013.
  53. J. Robertson and W. Webb. Cake-cutting algorithms: Be fair if you can. CRC Press, 1998.
  54. Fair coresets and streaming algorithms for fair k-means. In International Workshop on Approximation and Online Algorithms, pages 232–251. Springer, 2019.
  55. A.-A. Stoica and C. Papadimitriou. Strategic clustering, 2018.
  56. A. Vakilian and M. Yalçıner. Improved approximation algorithms for individually fair clustering. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
  57. H. R. Varian. Equity, envy, and efficiency. Journal of Economic Theory, 9(1):63–91, 1974.
  58. From parity to preference-based notions of fairness in classification. Advances in neural information processing systems, 30, 2017.
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