Learning with Pseudo-Ensembles

Abstract

We formalize the notion of a pseudo-ensemble, a (possibly infinite) collection of child models spawned from a parent model by perturbing it according to some noise process. E.g., dropout (Hinton et. al, 2012) in a deep neural network trains a pseudo-ensemble of child subnetworks generated by randomly masking nodes in the parent network. We present a novel regularizer based on making the behavior of a pseudo-ensemble robust with respect to the noise process generating it. In the fully-supervised setting, our regularizer matches the performance of dropout. But, unlike dropout, our regularizer naturally extends to the semi-supervised setting, where it produces state-of-the-art results. We provide a case study in which we transform the Recursive Neural Tensor Network of (Socher et. al, 2013) into a pseudo-ensemble, which significantly improves its performance on a real-world sentiment analysis benchmark.

To appear in Advances in Neural Information Processing Systems 27 (NIPS 2014), Advances in Neural Information Processing Systems 27, Dec. 2014

References in corpus (4)

• Improving neural networks by preventing co-adaptation of feature detectors
• Distributed Representations of Sentences and Documents
• On the difficulty of training Recurrent Neural Networks
• Large-Scale Feature Learning With Spike-and-Slab Sparse Coding

Cited by in corpus (2)

• Data Distillation: Towards Omni-Supervised Learning
• Infinite Variational Autoencoder for Semi-Supervised Learning