Graph Structured Prediction Energy Networks
Abstract
For joint inference over multiple variables, a variety of structured prediction techniques have been developed to model correlations among variables and thereby improve predictions. However, many classical approaches suffer from one of two primary drawbacks: they either lack the ability to model high-order correlations among variables while maintaining computationally tractable inference, or they do not allow to explicitly model known correlations. To address this shortcoming, we introduce `Graph Structured Prediction Energy Networks,' for which we develop inference techniques that allow to both model explicit local and implicit higher-order correlations while maintaining tractability of inference. We apply the proposed method to tasks from the natural language processing and computer vision domain and demonstrate its general utility.
Cite
@article{arxiv.1910.14670,
title = {Graph Structured Prediction Energy Networks},
author = {Colin Graber and Alexander Schwing},
journal= {arXiv preprint arXiv:1910.14670},
year = {2020}
}
Comments
Appearing in NeurIPS 2019