Near-Linear Query Complexity for Graph Inference

Kannan, Sampath; Mathieu, Claire; Zhou, Hang

doi:10.1007/978-3-662-47672-7_63

Cited by 1 publication

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Theoretical work in this area has focused on worst case query complexity. Two representative examples include Angluin's et al work on learning graphs using edge detecting queries [5], and the recent work of Kannan, Mathieu, and Zhou using distance queries [28]. A number of works also consider learning graph parameters such as node count and mixing time by examining random walks traces [30,16,9].…”

Section: Related Workmentioning

confidence: 99%

Learning Networks from Random Walk-Based Node Similarities

Hoskins,

Musco,

Musco

et al. 2018

Preprint

View full text Add to dashboard Cite

Digital presence in the world of online social media entails significant privacy risks [6,10,33,58,34]. In this work we consider a privacy threat to a social network in which an attacker has access to a subset of random walk-based node similarities, such as effective resistances (i.e., commute times) or personalized PageRank scores. Using these similarities, the attacker's goal is to infer as much information as possible about the underlying network, including any remaining unknown pairwise node similarities and edges.For the effective resistance metric, we show that with just a small subset of measurements, the attacker can learn a large fraction of edges in a social network (and in some cases all edges), even when the measurements are noisy. We also show that it is possible to learn a graph which accurately matches the underlying network on all other effective resistances. This second observation is interesting from a data mining perspective, since it can be expensive to accurately compute all effective resistances or other random walk-based similarities. As an alternative, our graphs learned from just a subset of approximate effective resistances can be used as surrogates in a wide range of applications that use effective resistances to probe graph structure, including for graph clustering, node centrality evaluation, and anomaly detection.We obtain our results by formalizing the graph learning objective mathematically, using two optimization problems. One formulation is convex and can be solved provably in polynomial time. The other is not, but we solve it efficiently with projected gradient and coordinate descent. We demonstrate the effectiveness of these methods on a number of social networks obtained from Facebook. We also discuss how our methods can be generalized to other random walk-based similarities, such as personalized PageRank scores. Our code is available at https://github.com/cnmusco/graph-similarity-learning.

show abstract