ML p(r)ior | Log-Normal Matrix Completion for Large Scale Link Prediction

Log-Normal Matrix Completion for Large Scale Link Prediction

2016-01-28
1601.07714 | cs.SI
The ubiquitous proliferation of online social networks has led to the widescale emergence of relational graphs expressing unique patterns in link formation and descriptive user node features. Matrix Factorization and Completion have become popular methods for Link Prediction due to the low rank nature of mutual node friendship information, and the availability of parallel computer architectures for rapid matrix processing. Current Link Prediction literature has demonstrated vast performance improvement through the utilization of sparsity in addition to the low rank matrix assumption. However, the majority of research has introduced sparsity through the limited L1 or Frobenius norms, instead of considering the more detailed distributions which led to the graph formation and relationship evolution. In particular, social networks have been found to express either Pareto, or more recently discovered, Log Normal distributions. Employing the convexity-inducing Lovasz Extension, we demonstrate how incorporating specific degree distribution information can lead to large scale improvements in Matrix Completion based Link prediction. We introduce Log-Normal Matrix Completion (LNMC), and solve the complex optimization problem by employing Alternating Direction Method of Multipliers. Using data from three popular social networks, our experiments yield up to 5% AUC increase over top-performing non-structured sparsity based methods.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2017-05-08
1705.02801 | cs.SI

Graphs, such as social networks, word co-occurrence networks, and communication networks, occur natu… show more
PDF

Highlights - Most important sentences from the article

2018-07-17

In this work, we consider the problem of combining link, content and temporal analysis for community… show more
PDF

Highlights - Most important sentences from the article

2017-09-30

Online social networks, World Wide Web, media and technological networks, and other types of so-call… show more
PDF

Highlights - Most important sentences from the article

2019-02-22

Predicting the potential relations between nodes in networks, known as link prediction, has long bee… show more
PDF

Highlights - Most important sentences from the article

2019-03-26

We apply the network Lasso to classify partially labeled data points which are characterized by high… show more
PDF

Highlights - Most important sentences from the article

2017-12-30
1801.00132 | cs.SI

The discovery of community structures in social networks has gained significant attention since it i… show more
PDF

Highlights - Most important sentences from the article

2019-03-24
1904.00791 | cs.LG

The goal in network state prediction (NSP) is to classify the global state (label) associated with f… show more
PDF

Highlights - Most important sentences from the article

2019-04-24

The network embedding problem aims to map nodes that are similar to each other to vectors in a Eucli… show more
PDF

Highlights - Most important sentences from the article

2018-04-25

We derive and analyse a new iterative algorithm for detecting network core--periphery structure. Usi… show more
PDF

Highlights - Most important sentences from the article

2018-12-27

Hyperspectral remote sensing is a prominent research topic in data processing. Most of the spectral … show more
PDF

Highlights - Most important sentences from the article

2018-12-11

Dynamic link prediction is a research hot in complex networks area, especially for its wide applicat… show more
PDF

Highlights - Most important sentences from the article

2019-04-23
1904.10146 | cs.LG

Semi-supervised classification on graph-structured data has received increasing attention, where lab… show more
PDF

Highlights - Most important sentences from the article

2019-01-10
1901.03425 | cs.SI

Studying networks to predict the emerging interactions is a common research problem for both fields … show more
PDF

Highlights - Most important sentences from the article

2018-07-12
1807.04680 | stat.ME

The problem of learning a correspondence relationship between nodes of two networks has drawn much a… show more
PDF

Highlights - Most important sentences from the article

2018-04-27

We consider the problem of matrix completion with side information (\textit{inductive matrix complet… show more
PDF

Highlights - Most important sentences from the article

2018-05-19
1805.07544 | stat.ML

Network Embeddings (NEs) map the nodes of a given network into $d$-dimensional Euclidean space $\mat… show more
PDF