# Graph Structured Prediction Energy Networks

arXiv: https://arxiv.org/abs/1910.14670 · HTML: https://mlsanity.com/paper/1910.14670/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2019.

## Built on by (most cited first, 10 of 10)

- [Lifting Weak Supervision To Structured Prediction](https://mlsanity.com/paper/2211.13375/) (2022)
- [Total Variation Optimization Layers for Computer Vision](https://mlsanity.com/paper/2204.03643/) (2022)
- [Geometry-Aware Adaptation for Pretrained Models](https://mlsanity.com/paper/2307.12226/) (2023)
- [Flow-based Spatio-Temporal Structured Prediction of Motion Dynamics](https://mlsanity.com/paper/2104.04391/) (2021)
- [Constrained Structure Learning for Scene Graph Generation](https://mlsanity.com/paper/2201.11697/) (2022)
- [Diffusion Probabilistic Models for Structured Node Classification](https://mlsanity.com/paper/2302.10506/) (2023)
- [From Memories to Maps: Mechanisms of In-Context Reinforcement Learning in Transformers](https://mlsanity.com/paper/2506.19686/) (2025)
- [Heatmap Regression without Soft-Argmax for Facial Landmark Detection](https://mlsanity.com/paper/2508.14929/) (2025)
- [Learning Energy-Based Approximate Inference Networks for Structured Applications in NLP](https://mlsanity.com/paper/2108.12522/) (2021)
- [Structured Prediction in NLP -- A survey](https://mlsanity.com/paper/2110.02057/) (2021)

## Abstract (arXiv)

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.