Deep Learning with Sets and Point Clouds
Abstract
We introduce a simple permutation equivariant layer for deep learning with set structure. This type of layer, obtained by parameter-sharing, has a simple implementation and linear-time complexity in the size of each set. We use deep permutation-invariant networks to perform point-could classification and MNIST-digit summation, where in both cases the output is invariant to permutations of the input. In a semi-supervised setting, where the goal is make predictions for each instance within a set, we demonstrate the usefulness of this type of layer in set-outlier detection as well as semi-supervised learning with clustering side-information.
Cite
Text
Ravanbakhsh et al. "Deep Learning with Sets and Point Clouds." International Conference on Learning Representations, 2017.Markdown
[Ravanbakhsh et al. "Deep Learning with Sets and Point Clouds." International Conference on Learning Representations, 2017.](https://mlanthology.org/iclr/2017/ravanbakhsh2017iclr-deep/)BibTeX
@inproceedings{ravanbakhsh2017iclr-deep,
title = {{Deep Learning with Sets and Point Clouds}},
author = {Ravanbakhsh, Siamak and Schneider, Jeff G. and Póczos, Barnabás},
booktitle = {International Conference on Learning Representations},
year = {2017},
url = {https://mlanthology.org/iclr/2017/ravanbakhsh2017iclr-deep/}
}