UAI 2023poster2 citations

Exploiting Inferential Structure in Neural Processes

Dharmesh Tailor, Mohammad Emtiyaz Khan, Eric Nalisnick

Abstract

Neural Processes (NPs) are appealing due to their ability to perform fast adaptation based on a context set. This set is encoded by a latent variable, which is often assumed to follow a simple distribution. However, in real-word settings, the context set may be drawn from richer distributions having multiple modes, heavy tails, etc. In this work, we provide a framework that allows NPs’ latent variable to be given a rich prior defined by a graphical model. These distributional assumptions directly translate into an appropriate aggregation strategy for the context set. Moreover, we describe a message-passing procedure that still allows for end-to-end optimization with stochastic gradients. We demonstrate the generality of our framework by using mixture and Student-t assumptions that yield improvements in function modelling and test-time robustness.

BibTeX
@InProceedings{pmlr-v216-tailor23a,
  title = 	 {Exploiting Inferential Structure in Neural Processes},
  author =       {Tailor, Dharmesh and Khan, Mohammad Emtiyaz and Nalisnick, Eric},
  booktitle = 	 {Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence},
  pages = 	 {2089--2098},
  year = 	 {2023},
  editor = 	 {Evans, Robin J. and Shpitser, Ilya},
  volume = 	 {216},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {31 Jul--04 Aug},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v216/tailor23a/tailor23a.pdf},
  url = 	 {https://proceedings.mlr.press/v216/tailor23a.html},
  abstract = 	 {Neural Processes (NPs) are appealing due to their ability to perform fast adaptation based on a context set. This set is encoded by a latent variable, which is often assumed to follow a simple distribution. However, in real-word settings, the context set may be drawn from richer distributions having multiple modes, heavy tails, etc. In this work, we provide a framework that allows NPs’ latent variable to be given a rich prior defined by a graphical model. These distributional assumptions directly translate into an appropriate aggregation strategy for the context set. Moreover, we describe a message-passing procedure that still allows for end-to-end optimization with stochastic gradients. We demonstrate the generality of our framework by using mixture and Student-t assumptions that yield improvements in function modelling and test-time robustness.}
}