Generative Prior Knowledge for Discriminative Classification

09/27/2011
by   G. DeJong, et al.
0

We present a novel framework for integrating prior knowledge into discriminative classifiers. Our framework allows discriminative classifiers such as Support Vector Machines (SVMs) to utilize prior knowledge specified in the generative setting. The dual objective of fitting the data and respecting prior knowledge is formulated as a bilevel program, which is solved (approximately) via iterative application of second-order cone programming. To test our approach, we consider the problem of using WordNet (a semantic database of English language) to improve low-sample classification accuracy of newsgroup categorization. WordNet is viewed as an approximate, but readily available source of background knowledge, and our framework is capable of utilizing it in a flexible way.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/04/2012

Learning Bayesian Network Parameters with Prior Knowledge about Context-Specific Qualitative Influences

We present a method for learning the parameters of a Bayesian network wi...
research
03/13/2020

Dynamic transformation of prior knowledge intoBayesian models for data streams

We consider how to effectively use prior knowledge when learning a Bayes...
research
11/02/2018

Prior Knowledge Integration for Neural Machine Translation using Posterior Regularization

Although neural machine translation has made significant progress recent...
research
03/13/2020

Dynamic transformation of prior knowledge into Bayesian models for data streams

We consider how to effectively use prior knowledge when learning a Bayes...
research
03/02/2021

Factoring out prior knowledge from low-dimensional embeddings

Low-dimensional embedding techniques such as tSNE and UMAP allow visuali...
research
11/19/2020

Classification by Attention: Scene Graph Classification with Prior Knowledge

A main challenge in scene graph classification is that the appearance of...
research
11/12/2018

Markov Property in Generative Classifiers

We show that, for generative classifiers, conditional independence corre...

Please sign up or login with your details

Forgot password? Click here to reset