The University of Southampton
University of Southampton Institutional Repository

Learning representations of sets through optimized permutations

Learning representations of sets through optimized permutations
Learning representations of sets through optimized permutations
Representations of sets are challenging to learn because operations on sets should be permutation-invariant. To this end, we propose a Permutation-Optimisation module that learns how to permute a set end-to-end. The permuted set can be further processed to learn a permutation-invariant representation of that set, avoiding a bottleneck in traditional set models. We demonstrate our model's ability to learn permutations and set representations with either explicit or implicit supervision on four datasets, on which we achieve state-of-the-art results: number sorting, image mosaics, classification from image mosaics, and visual question answering.
Zhang, Yan
0edf84ab-1e32-4239-bef6-7fe80d6bc7a7
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e
Zhang, Yan
0edf84ab-1e32-4239-bef6-7fe80d6bc7a7
Hare, Jonathon
65ba2cda-eaaf-4767-a325-cd845504e5a9
Prugel-Bennett, Adam
b107a151-1751-4d8b-b8db-2c395ac4e14e

Zhang, Yan, Hare, Jonathon and Prugel-Bennett, Adam (2019) Learning representations of sets through optimized permutations. International Conference on Learning Representations, New Orleans, United States. 06 - 09 May 2019. 26 pp .

Record type: Conference or Workshop Item (Paper)

Abstract

Representations of sets are challenging to learn because operations on sets should be permutation-invariant. To this end, we propose a Permutation-Optimisation module that learns how to permute a set end-to-end. The permuted set can be further processed to learn a permutation-invariant representation of that set, avoiding a bottleneck in traditional set models. We demonstrate our model's ability to learn permutations and set representations with either explicit or implicit supervision on four datasets, on which we achieve state-of-the-art results: number sorting, image mosaics, classification from image mosaics, and visual question answering.

Full text not available from this repository.

More information

Accepted/In Press date: 21 December 2018
Published date: 6 May 2019
Venue - Dates: International Conference on Learning Representations, New Orleans, United States, 2019-05-06 - 2019-05-09

Identifiers

Local EPrints ID: 427851
URI: https://eprints.soton.ac.uk/id/eprint/427851
PURE UUID: e9257ae1-dec9-4225-a178-bed649feb1e7
ORCID for Yan Zhang: ORCID iD orcid.org/0000-0003-3470-3663
ORCID for Jonathon Hare: ORCID iD orcid.org/0000-0003-2921-4283

Catalogue record

Date deposited: 30 Jan 2019 17:30
Last modified: 29 Nov 2019 01:35

Export record

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.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of https://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×