# Modeling homophily and stochastic equivalence in symmetric relational data

@inproceedings{Hoff2007ModelingHA, title={Modeling homophily and stochastic equivalence in symmetric relational data}, author={Peter D. Hoff}, booktitle={NIPS}, year={2007} }

This article discusses a latent variable model for inference and prediction of symmetric relational data. The model, based on the idea of the eigenvalue decomposition, represents the relationship between two nodes as the weighted inner-product of node-specific vectors of latent characteristics. This "eigenmodel" generalizes other popular latent variable models, such as latent class and distance models: It is shown mathematically that any latent class or distance model has a representation as an… Expand

#### 228 Citations

Generalized Relational Topic Models with Data Augmentation

- Mathematics, Computer Science
- IJCAI
- 2013

Experimental results demonstrate the significance of three extensions of relational topic models on improving the prediction performance, and the time efficiency can be dramatically improved with a simple fast approximation method. Expand

Universal Latent Space Model Fitting for Large Networks with Edge Covariates

- Computer Science
- J. Mach. Learn. Res.
- 2020

Two universal fitting algorithms for networks with edge covariates are presented: one based on nuclear norm penalization and the other based on projected gradient descent, motivated by maximizing the likelihood function for an existing class of inner-product models. Expand

Nonparametric Bayesian matrix factorization for assortative networks

- Mathematics, Computer Science
- 2015 23rd European Signal Processing Conference (EUSIPCO)
- 2015

The gamma process edge partition model is described, which links the binary edges of an undirected and unweighted relational network with a latent factor model via the Bernoulli-Poisson link, and uses the gamma process to support a potentially infinite number of latent communities. Expand

Generalized Latent Factor Models for Social Network Analysis

- Computer Science
- IJCAI
- 2011

This paper proposes a novel model, called generalized latent factor model (GLFM), for social network analysis by enhancing homophily modeling in MLFM, and devise a minorization-maximization (MM) algorithm with linear-time complexity and convergence guarantee to learn the model parameters. Expand

A Latent Space Model for Multilayer Network Data

- Computer Science, Mathematics
- ArXiv
- 2021

A Bayesian statistical model to simultaneously characterize two or more social networks defined over a common set of actors with a hierarchical prior distribution is proposed, achieving a compromise between dependent and independent networks. Expand

A Review of Latent Space Models for Social Networks

- Computer Science, Mathematics
- ArXiv
- 2020

This paper discusses in detail several latent space models provided in literature, providing special attention to distance, class, and eigen models in the context of undirected, binary networks. Expand

Exploration of Large Networks with Covariates via Fast and Universal Latent Space Model Fitting

- Mathematics, Computer Science
- 2017

Two universal fitting algorithms for networks with edge covariates are presented: one based on nuclear norm penalization and the other based on projected gradient descent, which are fast and scalable to large networks. Expand

Regression of binary network data with exchangeable latent errors

- Computer Science, Mathematics
- 2019

The Probit Exchangeable (PX) Model for undirected binary network data is proposed, based on an assumption of exchangeability, which is common to many of the latent variable network models in the literature, and an algorithm for obtaining the maximum likelihood estimator of the PX model is presented. Expand

Marginally Specified Hierarchical Models for Relational Data

- 2009

We present a unified approach to modelling dyadic relational data, namely that seen in social, biological and technological networks, without restriction to the binary format. The approach involves… Expand

Advancements in latent space network modelling

- Computer Science
- 2020

A latent space model for network data in which the interactions occur between sets of the population and, as a motivating example, a coauthorship network in which it is typical for more than two authors to contribute to an article is considered. Expand

#### References

SHOWING 1-10 OF 19 REFERENCES

A latent mixed membership model for relational data

- Computer Science
- LinkKDD '05
- 2005

This paper proposes a Bayesian model that uses a hierarchy of probabilistic assumptions about the way objects interact with one another in order to learn latent groups, their typical interaction patterns, and the degree of membership of objects to groups. Expand

Latent Space Approaches to Social Network Analysis

- Mathematics
- 2002

Network models are widely used to represent relational information among interacting units. In studies of social networks, recent emphasis has been placed on random graph models where the nodes… Expand

Discovering Latent Classes in Relational Data

- Computer Science
- 2004

A domain-general framework for learning abstract relational knowledge, which goes beyond previous category-learning models in psychology and applies in two specific domains: learning the structure of kinship systems and learning causal theories. Expand

Bilinear Mixed-Effects Models for Dyadic Data

- Mathematics
- 2005

This article discusses the use of a symmetric multiplicative interaction effect to capture certain types of third-order dependence patterns often present in social networks and other dyadic datasets.… Expand

Estimation and Prediction for Stochastic Blockstructures

- Mathematics
- 2001

A statistical approach to a posteriori blockmodeling for digraphs and valued digraphs is proposed. The probability model assumes that the vertices of the digraph are partitioned into several… Expand

Social network analysis - methods and applications

- Mathematics, Computer Science
- Structural analysis in the social sciences
- 2007

This work characterizes networked structures in terms of nodes (individual actors, people, or things within the network) and the ties, edges, or links that connect them. Expand

Interaction network containing conserved and essential protein complexes in Escherichia coli

- Biology, Medicine
- Nature
- 2005

Insight is provided into the function of previously uncharacterized bacterial proteins and the overall topology of a microbial interaction network, the core components of which are broadly conserved across Prokaryota. Expand

Handcock . Latent space approaches to social network analysis

- J . Amer . Statist . Assoc .
- 2002

J. Amer. Statist. Assoc

- J. Amer. Statist. Assoc
- 2001