Learning from Dyadic Data
Lists
Only you see this
Abstract
Dyadzc data refers to a domain with two finite sets of objects in which observations are made for dyads , i.e., pairs with one element from either set. This type of data arises naturally in many ap(cid:173) plication ranging from computational linguistics and information retrieval to preference analysis and computer vision. In this paper, we present a systematic, domain-independent framework of learn(cid:173) ing from dyadic data by statistical mixture models. Our approach covers different models with fiat and hierarchical latent class struc(cid:173) tures. We propose an annealed version of the standard EM algo(cid:173) rithm for model fitting which is empirically evaluated on a variety of data sets from different domains.
BibTeX
@inproceedings{hofmann1998learning,
author = {Thomas Hofmann and Jan Puzicha and Michael I. Jordan},
title = {{Learning from Dyadic Data}},
booktitle = {Advances in Neural Information Processing Systems},
year = {1998},
}| Infinite Hidden Relational Models | arXiv · 2012 |
| Infinite mixtures for multi-relational categorical data | MLG @ ICML · 2008 |
| Modeling Relational Data via Latent Factor Blockmodel | arXiv · 2012 |
| Inferring Latent Structure From Mixed Real and Categorical Relational Data | ICML · 2012 |
| Unsupervised Learning by Probabilistic Latent Semantic Analysis | Machine Learning · 2001 |
| Subset Infinite Relational Models | AISTATS · 2012 |