Learning Representations of Sets through Optimized Permutations

Code

• github.com/iclr2019-anon123456/perm-optim
  OfficialIn paperpytorch★ 0
• github.com/Cyanogenoid/perm-optim
  OfficialIn paperpytorch★ 0

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.

Tasks

Reproductions