资源分类
》 资源 》论文》FSP OOL :L EARNING SET REPRESENTATIONS WITHF EATUREWISE SORT POOLING

FSP OOL :L EARNING SET REPRESENTATIONS WITHF EATUREWISE SORT POOLING

2020-01-02 | |  57 |   48 |   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.

上一篇：DEEP DOUBLE DESCENT:W HERE BIGGER MODELS AND MORE DATA HURT

下一篇：PROGRAM GUIDED AGENT

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...