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
6 May 2019
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, Ernest N. Morial Convention Center, 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.
Text
learning_representations_of_sets_through_optimized_permutations
- Version of Record
Restricted to Repository staff only
Request a copy
More information
Accepted/In Press date: 21 December 2018
Published date: 6 May 2019
Venue - Dates:
International Conference on Learning Representations, Ernest N. Morial Convention Center, New Orleans, United States, 2019-05-06 - 2019-05-09
Identifiers
Local EPrints ID: 427851
URI: http://eprints.soton.ac.uk/id/eprint/427851
PURE UUID: e9257ae1-dec9-4225-a178-bed649feb1e7
Catalogue record
Date deposited: 30 Jan 2019 17:30
Last modified: 16 Mar 2024 03:50
Export record
Contributors
Author:
Yan Zhang
Author:
Jonathon Hare
Author:
Adam Prugel-Bennett
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