UNIGE document Chapitre d'actes
previous document  unige:73192  next document
add to browser collection
Title

Sparsity on Statistical Simplexes and Diversity in Social Ranking

Authors
Published in Proceedings of the 6th Asian Conference on Machine Learning. 2014, p. 16-31
Collection JMLR: Workshop and Conference Proceedings; 39
Abstract Sparsity in R^m has been widely explored in machine learning. We study sparsity on a statistical simplex consisting of all categorical distributions. This is different from the case in R^m because such a simplex is a Riemannian manifold, a curved space. A learner with sparse constraints should be likely to fall to its low-dimensional boundaries. We present a novel analysis on the statistical simplex as a manifold with boundary. The main contribution is an explicit view of the learning dynamics in between high-dimensional models in the interior of the simplex and low-dimensional models on its boundaries. We prove the differentiability of the cost function, the natural gradient with respect to the Riemannian structure, and convexity around the singular regions. We uncover an interesting relationship with L1 regularization. We apply the proposed technique to social network analysis. Given a directed graph, the task is to rank a subset of influencer nodes. Here, sparsity means that the top-ranked nodes should present diversity in the sense of minimizing influence overlap. We present a ranking algorithm based on the natural gradient. It can scale up to graph datasets with millions of nodes. On real large networks, the top-ranked nodes are the most informative among several commonly-used techniques.
Keywords Information geometrySparsity
Full text
Proceedings (Published version) (578 Kb) - public document Free access
Supplemental data (152 Kb) - public document Free access
Structures
Research groups Viper group
Computer Vision and Multimedia Laboratory
Citation
(ISO format)
SUN, Ke, MOHAMED, Hisham, MARCHAND-MAILLET, Stéphane. Sparsity on Statistical Simplexes and Diversity in Social Ranking. In: Proceedings of the 6th Asian Conference on Machine Learning. [s.l.] : [s.n.], 2014. p. 16-31. (JMLR: Workshop and Conference Proceedings; 39) https://archive-ouverte.unige.ch/unige:73192

286 hits

64 downloads

Update

Deposited on : 2015-06-15

Export document
Format :
Citation style :