Zhang, Yan, Hare, Jonathon and Prugel-Bennett, Adam (2020) FSPool: Learning set representations with featurewise sort pooling. International Conference on Learning Representations, Millennium Hall, Ethiopia. 26 - 30 Apr 2020.
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.
Full text not available from this repository.
More information
Identifiers
Catalogue record
Export record
Contributors
University divisions
- Current Faculties > Faculty of Engineering and Physical Sciences > School of Electronics and Computer Science > Vision, Learning and Control
School of Electronics and Computer Science > Vision, Learning and Control - Faculties (pre 2018 reorg) > Faculty of Engineering and the Environment (pre 2018 reorg) > Southampton Marine & Maritime Institute (pre 2018 reorg)
- Current Faculties > Faculty of Engineering and Physical Sciences > School of Electronics and Computer Science
School of Electronics and Computer Science
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.