# Learning Representations of Sets through Optimized Permutations

Source: [Learning Representations of Sets through Optimized Permutations](<https://www.sota2.com/research/paper/68fa654e1e209131cea097be>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:23:52.793Z

Authors: Yan Zhang, Jonathon Hare, Adam Pr\\"ugel-Bennett

Published: 2018-12-10T17:26:25.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1812.03928>)

[PDF](<https://arxiv.org/pdf/1812.03928.pdf>)
