Inferring Generative Model Structure with Static Analysis

09/07/2017
by   Paroma Varma, et al.
0

Obtaining enough labeled data to robustly train complex discriminative models is a major bottleneck in the machine learning pipeline. A popular solution is combining multiple sources of weak supervision using generative models. The structure of these models affects training label quality, but is difficult to learn without any ground truth labels. We instead rely on these weak supervision sources having some structure by virtue of being encoded programmatically. We present Coral, a paradigm that infers generative model structure by statically analyzing the code for these heuristics, thus reducing the data required to learn structure significantly. We prove that Coral's sample complexity scales quasilinearly with the number of heuristics and number of relations found, improving over the standard sample complexity, which is exponential in n for identifying n^th degree relations. Experimentally, Coral matches or outperforms traditional structure learning approaches by up to 3.81 F1 points. Using Coral to model dependencies instead of assuming independence results in better performance than a fully supervised model by 3.07 accuracy points when heuristics are used to label radiology data without ground truth labels.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/25/2016

Socratic Learning: Augmenting Generative Models to Incorporate Latent Subsets in Training Data

A challenge in training discriminative models like neural networks is ob...
research
03/02/2017

Learning the Structure of Generative Models without Labeled Data

Curating labeled training data has become the primary bottleneck in mach...
research
03/14/2019

Learning Dependency Structures for Weak Supervision Models

Labeling training data is a key bottleneck in the modern machine learnin...
research
07/27/2022

Learning Hyper Label Model for Programmatic Weak Supervision

To reduce the human annotation efforts, the programmatic weak supervisio...
research
01/09/2022

Weak Supervision for Affordable Modeling of Electrocardiogram Data

Analysing electrocardiograms (ECGs) is an inexpensive and non-invasive, ...
research
02/28/2022

Resolving label uncertainty with implicit posterior models

We propose a method for jointly inferring labels across a collection of ...
research
10/21/2019

Multi-Resolution Weak Supervision for Sequential Data

Since manually labeling training data is slow and expensive, recent indu...

Please sign up or login with your details

Forgot password? Click here to reset