FSPool: Learning Set Representations with Featurewise Sort Pooling

Code

• github.com/Cyanogenoid/fspool
  OfficialIn paperpytorch★ 0
• github.com/LukeBolly/tf-tspn/blob/master/models/fspool.py
  tf★ 0

Abstract

Traditional set prediction models can struggle with simple datasets due to an issue we call the responsibility problem. We introduce a pooling method for sets of feature vectors based on sorting features across elements of the set. This can be used to construct a permutation-equivariant auto-encoder that avoids this responsibility problem. On a toy dataset of polygons and a set version of MNIST, we show that such an auto-encoder produces considerably better reconstructions and representations. Replacing the pooling function in existing set encoders with FSPool improves accuracy and convergence speed on a variety of datasets.

Tasks

Reproductions