FSPool: Learning Set Representations with Featurewise Sort Pooling
Yan Zhang, Jonathon Hare, Adam Prügel‐Bennett
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 to learn better set representations. This can be used to construct a permutation-equivariant auto-encoder, which avoids the 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. Used in set classification, FSPool significantly improves accuracy and convergence speed on the set versions of MNIST and CLEVR.
Topics & Concepts
PoolingMNIST databaseComputer sciencesortSet (abstract data type)AutoencoderEncoderEquivariant mapSortingArtificial intelligencePermutation (music)Feature (linguistics)Variety (cybernetics)Function (biology)Set functionConvergence (economics)Construct (python library)Simple (philosophy)Pattern recognition (psychology)Theoretical computer scienceAlgorithmDeep learningMathematicsInformation retrievalBiologyEconomic growthEpistemologyPhysicsPure mathematicsLinguisticsPhilosophyEvolutionary biologyProgramming languageAcousticsEconomicsOperating systemDomain Adaptation and Few-Shot LearningMachine Learning and Data ClassificationMachine Learning and Algorithms