Paper Info
Title
Cooperative neural networks (CoNN) - Exploiting prior independence structure for improved classification.
Abstract
We propose a new approach, called cooperative neural networks (CoNN), which uses a set of cooperatively trained neural networks to capture latent representations that exploit prior given independence structure. The model is more flexible than traditional graphical models based on exponential family distributions, but incorporates more domain specific prior structure than traditional deep networks or variational autoencoders. The framework is very general and can be used to exploit the independence structure of any graphical model. We illustrate the technique by showing that we can transfer the independence structure of the popular Latent Dirichlet Allocation (LDA) model to a cooperative neural network, CoNN-sLDA. Empirical evaluation of CoNN-sLDA on supervised text classification tasks demonstrates that the theoretical advantages of prior independence structure can be realized in practice - we demonstrate a 23% reduction in error on the challenging MultiSent data set compared to state-of-the-art.
Year
Venue
Keywords
2018
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 31 (NIPS 2018)
neural networks,a set,neural network,data set,graphical models,graphical model,latent dirichlet allocation
Field
DocType
Volume
Latent Dirichlet allocation,Computer science,Exponential family,Exploit,Artificial intelligence,Graphical model,Artificial neural network,Machine learning
Conference
31
ISSN
Citations 
PageRank 
1049-5258
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Shrivastava, Harsh100.34
Eugene Bart2292.43
Bob Price348131.72
Hanjun Dai432325.71
Bo Dai523034.71
Aluru, Srinivas61166122.83