# Improving Joint Training of Inference Networks and Structured Prediction Energy Networks

arXiv: https://arxiv.org/abs/1911.02891 · HTML: https://mlsanity.com/paper/1911.02891/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2019.

## Built on by (most cited first, 6 of 6)

- [Text Generation by Learning from Demonstrations](https://mlsanity.com/paper/2009.07839/) (2020)
- [Token Dropping for Efficient BERT Pretraining](https://mlsanity.com/paper/2203.13240/) (2022)
- [Introducing Verification Task of Set Consistency with Set-Consistency Energy Networks](https://mlsanity.com/paper/2503.10695/) (2025)
- [Modeling Structure with Undirected Neural Networks](https://mlsanity.com/paper/2202.03760/) (2022)
- [Implicit Training of Energy Model for Structure Prediction](https://mlsanity.com/paper/2211.11649/) (2022)
- [Interval Type-2 Fuzzy Neural Networks for Multi-Label Classification](https://mlsanity.com/paper/2302.10430/) (2023)

## Abstract (arXiv)

Deep energy-based models are powerful, but pose challenges for learning and inference (Belanger and McCallum, 2016). Tu and Gimpel (2018) developed an efficient framework for energy-based models by training "inference networks" to approximate structured inference instead of using gradient descent. However, their alternating optimization approach suffers from instabilities during training, requiring additional loss terms and careful hyperparameter tuning. In this paper, we contribute several strategies to stabilize and improve this joint training of energy functions and inference networks for structured prediction. We design a compound objective to jointly train both cost-augmented and test-time inference networks along with the energy function. We propose joint parameterizations for the inference networks that encourage them to capture complementary functionality during learning. We empirically validate our strategies on two sequence labeling tasks, showing easier paths to strong performance than prior work, as well as further improvements with global energy terms.