Title
Multiset-equivariant set prediction with approximate implicit differentiation
Author
Zhang, Y.
Zhang, D.W.
Lacoste-Julien, S.
Burghouts, G.J.
Snoek, C.G.M.
Publication year
2022
Abstract
Most set prediction models in deep learning use set-equivariant operations, but they actually operate on multisets. We show that set-equivariant functions cannot represent certain functions on multisets, so we introduce the more appropriate notion of multiset-equivariance. We identify that the existing Deep Set Prediction Network (DSPN) can be multiset-equivariant without being hindered by set-equivariance and improve it with approximate implicit differentiation, allowing for better optimization while being faster and saving memory. In a range of toy experiments, we show that the perspective of multiset-equivariance is beneficial and that our changes to DSPN achieve better results in most cases. On CLEVR object property prediction, we substantially improve over the state-of-the-art Slot Attention from 8% to 77% in one of the strictest evaluation metrics because of the benefits made possible by implicit differentiation. (C) 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.
Subject
Deep learning
Toys
Equivariance
Evaluation metrics
Multi-sets
Object property
Optimisations
Prediction modelling
Property predictions
State of the art
Forecasting
To reference this document use:
http://resolver.tudelft.nl/uuid:ee3867c1-2efc-4656-8b2e-78d53922748b
TNO identifier
985095
Publisher
International Conference on Learning Representations, ICLR
Source
ICLR 2022 - 10th International Conference on Learning Representations
Document type
conference paper