Gamma Process Poisson Factorization for Joint Modeling of Network and Documents
Abstract
Developing models to discover, analyze, and predict clusters within networked entities is an area of active and diverse research. However, many of the existing approaches do not take into consideration pertinent auxiliary information. This paper introduces Joint Gamma Process Poisson Factorization (J-GPPF) to jointly model network and side-information. J-GPPF naturally fits sparse networks, accommodates separately-clustered side information in a principled way, and effectively addresses the computational challenges of analyzing large networks. Evaluated with hold-out link prediction performance on sparse networks (both synthetic and real-world) with side information, J-GPPF is shown to clearly outperform algorithms that only model the network adjacency matrix.
Cite
Text
Acharya et al. "Gamma Process Poisson Factorization for Joint Modeling of Network and Documents." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2015. doi:10.1007/978-3-319-23528-8_18Markdown
[Acharya et al. "Gamma Process Poisson Factorization for Joint Modeling of Network and Documents." European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2015.](https://mlanthology.org/ecmlpkdd/2015/acharya2015ecmlpkdd-gamma/) doi:10.1007/978-3-319-23528-8_18BibTeX
@inproceedings{acharya2015ecmlpkdd-gamma,
title = {{Gamma Process Poisson Factorization for Joint Modeling of Network and Documents}},
author = {Acharya, Ayan and Teffer, Dean and Henderson, Jette and Tyler, Marcus and Zhou, Mingyuan and Ghosh, Joydeep},
booktitle = {European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},
year = {2015},
pages = {283-299},
doi = {10.1007/978-3-319-23528-8_18},
url = {https://mlanthology.org/ecmlpkdd/2015/acharya2015ecmlpkdd-gamma/}
}