Conference proceeding
Adversarial Localized Energy Network for Structured Prediction
Proceedings of the ... AAAI Conference on Artificial Intelligence, Vol.34(4), pp.5347-5354
04/03/2020
DOI: 10.1609/aaai.v34i04.5982
Abstract
This paper focuses on energy model based structured output prediction. Though inheriting the benefits from energy-based models to handle the sophisticated cases, previous deep energy-based methods suffered from the substantial computation cost introduced by the enormous amounts of gradient steps in the inference process. To boost the efficiency and accuracy of the energy-based models on structured output prediction, we propose a novel method analogous to the adversarial learning framework. Specifically, in our proposed framework, the generator consists of an inference network while the discriminator is comprised of an energy network. The two sub-modules, i.e., the inference network and the energy network, can benefit each other mutually during the whole computation process. On the one hand, our modified inference network can boost the efficiency by predicting good initializations and reducing the searching space for the inference process; On the other hand, inheriting the benefits of the energy network, the energy module in our network can evaluate the quality of the generated output from the inference network and correspondingly provides a resourceful guide to the training of the inference network. In the ideal case, the adversarial learning strategy makes sure the two sub-modules can achieve an equilibrium state after steps. We conduct extensive experiments to verify the effectiveness and efficiency of our proposed method.
Details
- Title: Subtitle
- Adversarial Localized Energy Network for Structured Prediction
- Creators
- Pingbo Pan - University of Technology SydneyPing Liu - University of Technology SydneyYan Yan - University of IowaTianbao Yang - University of IowaYi Yang - University of Technology Sydney
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of the ... AAAI Conference on Artificial Intelligence, Vol.34(4), pp.5347-5354
- DOI
- 10.1609/aaai.v34i04.5982
- ISSN
- 2159-5399
- eISSN
- 2374-3468
- Language
- English
- Date published
- 04/03/2020
- Academic Unit
- Computer Science
- Record Identifier
- 9984259475902771
Metrics
3 Record Views