English

Deep Polynomial Neural Networks

Machine Learning 2021-03-02 v2 Computer Vision and Pattern Recognition Machine Learning

Abstract

Deep Convolutional Neural Networks (DCNNs) are currently the method of choice both for generative, as well as for discriminative learning in computer vision and machine learning. The success of DCNNs can be attributed to the careful selection of their building blocks (e.g., residual blocks, rectifiers, sophisticated normalization schemes, to mention but a few). In this paper, we propose Π\Pi-Nets, a new class of function approximators based on polynomial expansions. Π\Pi-Nets are polynomial neural networks, i.e., the output is a high-order polynomial of the input. The unknown parameters, which are naturally represented by high-order tensors, are estimated through a collective tensor factorization with factors sharing. We introduce three tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks. We empirically demonstrate that Π\Pi-Nets are very expressive and they even produce good results without the use of non-linear activation functions in a large battery of tasks and signals, i.e., images, graphs, and audio. When used in conjunction with activation functions, Π\Pi-Nets produce state-of-the-art results in three challenging tasks, i.e. image generation, face verification and 3D mesh representation learning. The source code is available at \url{https://github.com/grigorisg9gr/polynomial_nets}.

Keywords

Cite

@article{arxiv.2006.13026,
  title  = {Deep Polynomial Neural Networks},
  author = {Grigorios Chrysos and Stylianos Moschoglou and Giorgos Bouritsas and Jiankang Deng and Yannis Panagakis and Stefanos Zafeiriou},
  journal= {arXiv preprint arXiv:2006.13026},
  year   = {2021}
}

Comments

Published in IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI). Code: https://github.com/grigorisg9gr/polynomial_nets. arXiv admin note: substantial text overlap with arXiv:2003.03828

R2 v1 2026-06-23T16:33:27.061Z