Exploiting Inferential Structure in Neural Processes

This repository is the official implementation of the methods in the publication:

• D. Tailor, M.E. Khan, and E. Nalisnick (2023). Exploiting Inferential Structure in Neural Processes. In Uncertainty in Artificial Intelligence (UAI).

Install

Follow the instructions to set up the environment of Transformer Neural Processes

Then additionally install the following packages:

• pyro-ppl
• scikit-image

Citation

If you find this repo useful in your research, please consider citing our paper:

@inproceedings{tailor2023exploiting,
  title={Exploiting inferential structure in neural processes},
  author={Tailor, Dharmesh and Khan, Mohammad Emtiyaz and Nalisnick, Eric},
  booktitle={Uncertainty in Artificial Intelligence},
  pages={2089--2098},
  year={2023},
  organization={PMLR}
}

Acknowledgement

This implementation is a modified version of the official code base of Transformer Neural Processes.