Name
Abstract | ||
|---|---|---|
Stochastic relational models (SRMs) (15) provide a rich family of choices for learning and predicting dyadic data between two sets of entities. The models gen- eralize matrix factorization to a supervised learning problem that utilizes attributes of entities in a hierarchical Bayesian framework. Previously variational Bayes in- ference was applied for SRMs, which is, however, not scalable when the size of either entity set grows to tens of thousands. In this paper, we introduce a Markov chain Monte Carlo (MCMC) algorithm for equivalent models of SRMs in order to scale the computation to very large dyadic data sets. Both superior scalability and predictive accuracy are demonstrated on a collaborative filtering problem, which involves tens of thousands users and half million items. |
Year | Venue | Keywords |
|---|---|---|
2008 | NIPS | matrix factorization,collaborative filtering,supervised learning,relational model,markov chain monte carlo |
Field | DocType | Citations |
Collaborative filtering,Markov chain Monte Carlo,Inference,Computer science,Matrix decomposition,Supervised learning,Artificial intelligence,Machine learning,Bayes' theorem,Bayesian probability,Scalability | Conference | 9 |
PageRank | References | Authors |
1.25 | 10 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zhu, Shenghuo | 1 | 2996 | 167.68 |
| Yu, Kai | 2 | 4799 | 255.21 |
| yihong gong | 3 | 7300 | 470.57 |