Skip to Main content Skip to Navigation
Conference papers

On Graph Reconstruction via Empirical Risk Minimization: Fast Learning Rates and Scalability

Guillaume Papa 1 Stéphan Clémençon 1 Aurélien Bellet 2
2 MAGNET - Machine Learning in Information Networks
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : The problem of predicting connections between a set of data points finds many applications, in systems biology and social network analysis among others. This paper focuses on the \textit{graph reconstruction} problem, where the prediction rule is obtained by minimizing the average error over all n(n-1)/2 possible pairs of the n nodes of a training graph. Our first contribution is to derive learning rates of order O(log n / n) for this problem, significantly improving upon the slow rates of order O(1/√n) established in the seminal work of Biau & Bleakley (2006). Strikingly, these fast rates are universal, in contrast to similar results known for other statistical learning problems (e.g., classification, density level set estimation, ranking, clustering) which require strong assumptions on the distribution of the data. Motivated by applications to large graphs, our second contribution deals with the computational complexity of graph reconstruction. Specifically, we investigate to which extent the learning rates can be preserved when replacing the empirical reconstruction risk by a computationally cheaper Monte-Carlo version, obtained by sampling with replacement B << n² pairs of nodes. Finally, we illustrate our theoretical results by numerical experiments on synthetic and real graphs.
Complete list of metadata
Contributor : Aurélien Bellet Connect in order to contact the contributor
Submitted on : Tuesday, January 3, 2017 - 12:03:16 PM
Last modification on : Thursday, January 20, 2022 - 4:16:39 PM


Files produced by the author(s)


  • HAL Id : hal-01367546, version 2


Guillaume Papa, Stéphan Clémençon, Aurélien Bellet. On Graph Reconstruction via Empirical Risk Minimization: Fast Learning Rates and Scalability. Annual Conference on Neural Information Processing Systems (NIPS 2016), Dec 2016, Barcelone, Spain. ⟨hal-01367546v2⟩



Les métriques sont temporairement indisponibles