Loading...
Diversified Bayesian nonnegative matrix factorization
Qiao, Maoying Jun,Yu Tongliang, Liu Xinchao, Wang Dacheng, Tao
Qiao, Maoying
Jun,Yu
Tongliang, Liu
Xinchao, Wang
Dacheng, Tao
Abstract
Nonnegative matrix factorization (NMF) has been widely employed in a variety of scenarios due to its capability of inducing semantic part-based representation. However, because of the non-convexity of its objective, the factorization is generally not unique and may inaccurately discover intrinsic “parts” from the data. In this paper, we approach this issue using a Bayesian framework. We propose to assign a diversity prior to the parts of the factorization to induce correctness based on the assumption that useful parts should be distinct and thus well-spread. A Bayesian framework including this diversity prior is then established. This framework aims at inducing factorizations embracing both good data fitness from maximizing likelihood and large separability from the diversity prior. Specifically, the diversity prior is formulated with determinantal point processes (DPP) and is seamlessly embedded into a Bayesian NMF framework. To carry out the inference, a Monte Carlo Markov Chain (MCMC) based procedure is derived. Experiments conducted on a synthetic dataset and a real-world MULAN dataset for multi-label learning (MLL) task demonstrate the superiority of the proposed method.
Keywords
Date
2020
Type
Conference paper
Journal
Proceedings of the AAAI Conference on Artificial Intelligence
Book
Volume
34
Issue
4
Page Range
5420-5427
Article Number
ACU Department
Peter Faber Business School
Faculty of Law and Business
Faculty of Law and Business
Collections
Relation URI
Source URL
Event URL
Open Access Status
License
All rights reserved
File Access
Controlled