Learning Representations of Sets through Optimized Permutations

12/10/2018
by   Yan Zhang, et al.
0

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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 13

page 14

page 15

page 22

page 23

page 24

page 25

page 26

11/05/2021

Grounded Graph Decoding Improves Compositional Generalization in Question Answering

Question answering models struggle to generalize to novel compositions o...
09/10/2017

Classifying Unordered Feature Sets with Convolutional Deep Averaging Networks

Unordered feature sets are a nonstandard data structure that traditional...
11/19/2019

Representation Learning with Multisets

We study the problem of learning permutation invariant representations t...
01/23/2020

Sorting Permutations with Fixed Pinnacle Set

We give a positive answer to a question raised by Davis et al. ( Discret...
04/10/2017

DeepPermNet: Visual Permutation Learning

We present a principled approach to uncover the structure of visual data...
01/30/2020

Learn to Predict Sets Using Feed-Forward Neural Networks

This paper addresses the task of set prediction using deep feed-forward ...
03/14/2022

Permutation Invariant Representations with Applications to Graph Deep Learning

This paper presents primarily two Euclidean embeddings of the quotient s...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.