Published on Wed Apr 11 2012

Modeling Relational Data via Latent Factor Blockmodel

Sheng Gao, Ludovic Denoyer, Patrick Gallinari

In this paper we address the problem of modeling relational data. Previous studies either consider latent feature-based models but disregarding local structure in the network. We propose a novel model that can simultaneously incorporate the effect of latent features and covariates if any.

0
0
0
Abstract

In this paper we address the problem of modeling relational data, which appear in many applications such as social network analysis, recommender systems and bioinformatics. Previous studies either consider latent feature based models but disregarding local structure in the network, or focus exclusively on capturing local structure of objects based on latent blockmodels without coupling with latent characteristics of objects. To combine the benefits of the previous work, we propose a novel model that can simultaneously incorporate the effect of latent features and covariates if any, as well as the effect of latent structure that may exist in the data. To achieve this, we model the relation graph as a function of both latent feature factors and latent cluster memberships of objects to collectively discover globally predictive intrinsic properties of objects and capture latent block structure in the network to improve prediction performance. We also develop an optimization transfer algorithm based on the generalized EM-style strategy to learn the latent factors. We prove the efficacy of our proposed model through the link prediction task and cluster analysis task, and extensive experiments on the synthetic data and several real world datasets suggest that our proposed LFBM model outperforms the other state of the art approaches in the evaluated tasks.

Fri Jun 16 2017
Machine Learning
Deep Generative Models for Relational Data with Side Information
We present a probabilistic framework for overlapping community discovery and link prediction for relational data. We compare with various state-of-the-art methods and report results, both quantitative and qualitative, on several benchmark data sets.
0
0
0
Wed Oct 09 2013
Machine Learning
Discriminative Relational Topic Models
Rational topic models (RTMs) provide a probabilistic process to describe both the link structure and document contents. Existing RTMs have limitations in both the restricted model expressiveness and incapability of dealing with imbalanced network data. This paper presents three extensions to improve the accuracy of RTMs.
0
0
0
Mon Nov 04 2019
Machine Learning
Scalable Deep Generative Relational Models with High-Order Node Dependence
We propose a probabilistic framework for modelling and exploring the latent structure of relational data. The scalable deep generative relational model (SDREM) builds a deep network architecture that can approximate potential nonlinear mappings between feature information and the nodes' latent representations.
0
0
0
Mon May 21 2012
Machine Learning
Latent Multi-group Membership Graph Model
The Latent Multi-group Membership Graph (LMMG) model is a model of networks with rich node feature structure. The LMMG can be used to summarize the network structure, to predict links between the nodes, and to predict missing features.
0
0
0
Mon Dec 07 2015
Machine Learning
Discriminative Nonparametric Latent Feature Relational Models with Data Augmentation
We present a discriminative nonparametric latent feature relational model for link prediction to automatically infer the dimensionality of latent features. Under the generic RegBayes (regularized Bayesian inference)framework, we handily incorporate the prediction loss with probabilistic Bayesian model.
0
0
0
Fri Feb 21 2020
Machine Learning
Struct-MMSB: Mixed Membership Stochastic Blockmodels with Interpretable Structured Priors
The mixed membership stochastic blockmodel (MMSB) is a popular framework for community detection and network generation. MMSB assumes that the membership distributions of nodes are independently drawn from a Dirichlet distribution, which limits its capability to model highly correlated graph structures that exist in real-world networks. We present a flexible richly structured
0
0
0