English

Graph Structured Prediction Energy Networks

Machine Learning 2020-01-07 v2 Machine Learning

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.

Keywords

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

R2 v1 2026-06-23T12:01:23.918Z