How robust are reconstruction thresholds for community detection?
Name
1511.01473.pdf
Size
424.87 KB
Format
Adobe PDF
Checksum (MD5)
11548544d27fb18379eed5fb4df605c0
Author(s)
Moitra, Ankur
Perry, Amelia E.
Wein, Alexander Spence
Date Issued
June 2016
Journal
Proceedings of the 48th Annual ACM SIGACT Symposium on Theory of Computing - STOC 2016
Publisher
Association for Computing Machinery (ACM)
Citation
Moitra, Ankur, William Perry, and Alexander S. Wein. “How Robust Are Reconstruction Thresholds for Community Detection?” Proceedings of the 48th Annual ACM SIGACT Symposium on Theory of Computing - STOC 2016 (2016), pp. 828-831.
Version
Original manuscript
Abstract
The stochastic block model is one of the oldest and most ubiquitous models for studying clustering and community detection. In an exciting sequence of developments, motivated by deep but non-rigorous ideas from statistical physics, Decelle et al. conjectured a sharp threshold for when community detection is possible in the sparse regime. Mossel, Neeman and Sly and Massoulié proved the conjecture and gave matching algorithms and lower bounds. Here we revisit the stochastic block model from the perspective of semirandom models where we allow an adversary to make 'helpful' changes that strengthen ties within each community and break ties between them. We show a surprising result that these 'helpful' changes can shift the information-theoretic threshold, making the community detection problem strictly harder. We complement this by showing that an algorithm based on semidefinite programming (which was known to get close to the threshold) continues to work in the semirandom model (even for partial recovery). This suggests that algorithms based on semidefinite programming are robust in ways that any algorithm meeting the information-theoretic threshold cannot be. These results point to an interesting new direction: Can we find robust, semirandom analogues to some of the classical, average-case thresholds in statistics? We also explore this question in the broadcast tree model, and we show that the viewpoint of semirandom models can help explain why some algorithms are preferred to others in practice, in spite of the gaps in their statistical performance on random models.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Massachusetts Institute of Technology. Department of Mathematics
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1145/2897518.2897573
