FSPool: Learning Set Representations with Featurewise Sort Pooling
Abstract
Traditional set prediction models can struggle with simple datasets due to an issue we call the responsibility problem. We introduce a pooling method for sets of feature vectors based on sorting features across elements of the set. This can be used to construct a permutation-equivariant auto-encoder that avoids this responsibility problem. On a toy dataset of polygons and a set version of MNIST, we show that such an auto-encoder produces considerably better reconstructions and representations. Replacing the pooling function in existing set encoders with FSPool improves accuracy and convergence speed on a variety of datasets.
Cite
Text
Zhang et al. "FSPool: Learning Set Representations with Featurewise Sort Pooling." International Conference on Learning Representations, 2020.Markdown
[Zhang et al. "FSPool: Learning Set Representations with Featurewise Sort Pooling." International Conference on Learning Representations, 2020.](https://mlanthology.org/iclr/2020/zhang2020iclr-fspool/)BibTeX
@inproceedings{zhang2020iclr-fspool,
title = {{FSPool: Learning Set Representations with Featurewise Sort Pooling}},
author = {Zhang, Yan and Hare, Jonathon and Prügel-Bennett, Adam},
booktitle = {International Conference on Learning Representations},
year = {2020},
url = {https://mlanthology.org/iclr/2020/zhang2020iclr-fspool/}
}