Set Aggregation Network as a Trainable Pooling Layer

Abstract

Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data. Based on the recent DeepSets architecture proposed by Zaheer et al. (NIPS 2017), we introduce a Set Aggregation Network (SAN) as an alternative global pooling layer. In contrast to typical pooling operators, SAN allows to embed a given set of features to a vector representation of arbitrary size. We show that by adjusting the size of embedding, SAN is capable of preserving the whole information from the input. In experiments, we demonstrate that replacing global pooling layer by SAN leads to the improvement of classification accuracy. Moreover, it is less prone to overfitting and can be used as a regularizer.

arXiv commentICONIP 2019

References in corpus (7)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Semi-Supervised Classification with Graph Convolutional Networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
• Seeing stars: Exploiting class relationships for sentiment categorization with respect to rating scales
• Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs
• Universal approximations of permutation invariant/equivariant functions by deep neural networks