Near-Perfect Recovery in the One-Dimensional Latent Space Model
Pages 1932 - 1942
Abstract
Suppose a graph G is stochastically created by uniformly sampling vertices along a line segment and connecting each pair of vertices with a probability that is a known decreasing function of their distance. We ask if it is possible to reconstruct the actual positions of the vertices in G by only observing the generated unlabeled graph. We study this question for two natural edge probability functions — one where the probability of an edge decays exponentially with the distance and another where this probability decays only linearly. We initiate our study with the weaker goal of recovering only the order in which vertices appear on the line segment. For a segment of length n and a precision parameter δ, we show that for both exponential and linear decay edge probability functions, there is an efficient algorithm that correctly recovers (up to reflection symmetry) the order of all vertices that are at least δ apart, using only samples (vertices). Building on this result, we then show that vertices (samples) are sufficient to additionally recover the location of each vertex on the line to within a precision of δ. We complement this result with an lower bound on samples needed for reconstructing positions (even by a computationally unbounded algorithm), showing that the task of recovering positions is information-theoretically harder than recovering the order. We give experimental results showing that our algorithm recovers the positions of almost all points with high accuracy.
References
[1]
Emmanuel Abbe. 2018. Community Detection and Stochastic Block Models: Recent Developments. Journal of Machine Learning Research 18, 177 (2018), 1–86.
[2]
Michael Aizenman and Charles M Newman. 1986. Discontinuity of the percolation density in one dimensional 1/|x − y|2 percolation models. Communications in Mathematical Physics 107, 4 (1986), 611–647.
[3]
Sergei Bernstein. 1924. On a modification of Chebyshev’s inequality and of the error formula of Laplace. Ann. Sci. Inst. Sav. Ukraine, Sect. Math 1, 4 (1924), 38–49.
[4]
Don Coppersmith, David Gamarnik, and Maxim Sviridenko. 2002. The diameter of a long range percolation graph. In Proceedings of the thirteenth annual ACM-SIAM symposium on Discrete algorithms. Society for Industrial and Applied Mathematics, 329–337.
[5]
Yash Deshpande, Subhabrata Sen, Andrea Montanari, and Elchanan Mossel. 2018. Contextual Stochastic Block Models. In Advances in Neural Information Processing Systems. 8581–8593.
[6]
Jacob C Fisher. 2019. Social Space Diffusion: Applications of a Latent Space Model to Diffusion with Uncertain Ties. Sociological Methodology(2019), 0081175018820075.
[7]
Mark S Handcock, Adrian E Raftery, and Jeremy M Tantrum. 2007. Model-based clustering for social networks. Journal of the Royal Statistical Society: Series A (Statistics in Society) 170, 2(2007), 301–354.
[8]
Peter D Hoff, Adrian E Raftery, and Mark S Handcock. 2002. Latent space approaches to social network analysis. Journal of the american Statistical association 97, 460(2002), 1090–1098.
[9]
Peter D Hoff and Michael D Ward. 2004. Modeling dependencies in international relations networks. Political Analysis 12, 2 (2004), 160–175.
[10]
Chuyang Ke and Jean Honorio. 2018. Information-theoretic Limits for Community Detection in Network Models. In Advances in Neural Information Processing Systems. 8324–8333.
[11]
Chuyang Ke and Jean Honorio. 2019. Exact Recovery in the Latent Space Model. arXiv preprint arXiv:1902.03099(2019).
[12]
Lucien Le Cam. 2012. Asymptotic methods in statistical decision theory. Springer Science & Business Media.
[13]
Charles M Newman and Lawrence S Schulman. 1986. One dimensional 1/|j − i|S percolation models: The existence of a transition for S ≤ 2. Communications in Mathematical Physics 104, 4 (1986), 547–571.
[14]
Tin Lok James Ng, Thomas Brendan Murphy, Ted Westling, Tyler H McCormick, and Bailey K Fosdick. 2018. Modeling the social media relationships of Irish politicians using a generalized latent space stochastic blockmodel. arXiv preprint arXiv:1807.06063(2018).
[15]
Adrian E Raftery, Xiaoyue Niu, Peter D Hoff, and Ka Yee Yeung. 2012. Fast inference for the latent space network model using a case-control approximate likelihood. Journal of Computational and Graphical Statistics 21, 4(2012), 901–919.
[16]
Purnamrita Sarkar, Deepayan Chakrabarti, and Andrew W. Moore. 2011. Theoretical Justification of Popular Link Prediction Heuristics. In IJCAI 2011, Proceedings of the 22nd International Joint Conference on Artificial Intelligence, Barcelona, Catalonia, Spain, July 16-22, 2011. 2722–2727. https://doi.org/10.5591/978-1-57735-516-8/IJCAI11-453
[17]
Lawrence S Schulman. 1983. Long range percolation in one dimension. Journal of Physics A: Mathematical and General 16, 17 (1983), L639.
[18]
Bin Yu. 1997. Assouad, Fano, and Le Cam. In Festschrift for Lucien Le Cam. Springer, 423–435.
[19]
A Zygmund 1953. HG Hardy, JE Littlewood and G. Pólya, Inequalities. Bull. Amer. Math. Soc. 59, 4 (1953), 411–412.
Index Terms
- Near-Perfect Recovery in the One-Dimensional Latent Space Model
Index terms have been assigned to the content through auto-classification.
Recommendations
Reconstruction number of graphs with unique pendant vertex
AbstractA vertex-deleted subgraph of a graph G is called a card of G . The reconstruction number of G is the minimum number of cards of G that suffices to determine G uniquely. A P-graph (Yongzhi, 1988) is a connected graph of order p with ...
On chordal and perfect plane near-triangulations
AbstractA plane near-triangulation G can be decomposed into a collection of induced subgraphs, described here as the W-components of G, such that G is perfect (respectively, chordal) if and only if each of its W-components is perfect (...
Split-Perfect Graphs: Characterizations and Algorithmic Use
Two graphs G and H with the same vertex set V are P4-isomorphic if every four vertices {a,b,c,d} \subseteq V$ induce a chordless path (denoted by P4) in G if and only if they induce a P4 in H. We call a graph split-perfect if it is P4-isomorphic to a ...
Comments
Information & Contributors
Information
Published In
April 2020
3143 pages
Copyright © 2020 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 20 April 2020
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
WWW '20
Sponsor:
Acceptance Rates
Overall Acceptance Rate 1,899 of 8,196 submissions, 23%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 176Total Downloads
- Downloads (Last 12 months)5
- Downloads (Last 6 weeks)1
Reflects downloads up to 27 Jul 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format