English

Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data

Computer Vision and Pattern Recognition 2021-08-10 v1 Machine Learning

Abstract

Multi-attribute classification generalizes classification, presenting new challenges for making accurate predictions and quantifying uncertainty. We build upon recent work and show that architectures for multi-attribute prediction can be reinterpreted as energy-based models (EBMs). While existing EBM approaches achieve strong discriminative performance, they are unable to generate samples conditioned on novel attribute combinations. We propose a simple extension which expands the capabilities of EBMs to generating accurate conditional samples. Our approach, combined with newly developed techniques in energy-based model training, allows us to directly maximize the likelihood of data and labels under the unnormalized joint distribution. We evaluate our proposed approach on high-dimensional image data with high-dimensional binary attribute labels. We find our models are capable of both accurate, calibrated predictions and high-quality conditional synthesis of novel attribute combinations.

Keywords

Cite

@article{arxiv.2108.04227,
  title  = {Directly Training Joint Energy-Based Models for Conditional Synthesis and Calibrated Prediction of Multi-Attribute Data},
  author = {Jacob Kelly and Richard Zemel and Will Grathwohl},
  journal= {arXiv preprint arXiv:2108.04227},
  year   = {2021}
}
R2 v1 2026-06-24T04:57:44.655Z