Author
Lee, J
Lee, Y
Kim, J
Kosiorek, A
Choi, S
Teh, Y
Journal title
Proceedings of Machine Learning Research
Volume
97
Last updated
2020-09-11T00:32:47.78+01:00
Page
3744-3753
Abstract
Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of elements of the set, models used to address them should be permutation invariant. We present an attention-based neural network module, the Set Transformer, specifically designed to model interactions among elements in the input set. The model consists of an encoder and a decoder, both of which rely on attention mechanisms. In an effort to reduce computational complexity, we introduce an attention scheme inspired by inducing point methods from sparse Gaussian process literature. It reduces the computation time of self-attention from quadratic to linear in the number of elements in the set. We show that our model is theoretically attractive and we evaluate it on a range of tasks, demonstrating the state-of-the-art performance compared to recent methods for set-structured data.
Symplectic ID
1019532
Publication type
Conference Paper
Publication date
9 June 2019
Please contact us with feedback and comments about this page. Created on 20 Jun 2019 - 17:30.