Learning Representations of Sets through Optimized PermutationsDownload PDF

27 Sep 2018 (modified: 15 Jan 2019)ICLR 2019 Conference Blind SubmissionReaders: Everyone
  • 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.
  • Keywords: sets, representation learning, permutation invariance
  • TL;DR: Learn how to permute a set, then encode permuted set with RNN to obtain a set representation.
29 Replies