Anytime Inference with Distilled Hierarchical Neural Ensembles

Authors

  • Adria Ruiz CSIC-UPC
  • Jakob Verbeek Facebook

Keywords:

(Deep) Neural Network Algorithms

Abstract

Inference in deep neural networks can be computationally expensive, and networks capable of anytime inference are important in scenarios where the amount of compute or input data varies over time. In such networks the inference process can interrupted to provide a result faster, or continued to obtain a more accurate result. We propose Hierarchical Neural Ensembles (HNE), a novel framework to embed an ensemble of multiple networks in a hierarchical tree structure, sharing intermediate layers. In HNE we control the complexity of inference on-the-fly by evaluating more or less models in the ensemble. Our second contribution is a novel hierarchical distillation method to boost the predictions of small ensembles. This approach leverages the nested structure of our ensembles, to optimally allocate accuracy and diversity across the individual models. Our experiments show that, compared to previous anytime inference models, HNE provides state-of-the-art accuracy-computation trade-offs on the CIFAR-10/100 and ImageNet datasets.

Downloads

Published

2021-05-18

How to Cite

Ruiz, A., & Verbeek, J. (2021). Anytime Inference with Distilled Hierarchical Neural Ensembles. Proceedings of the AAAI Conference on Artificial Intelligence, 35(11), 9463-9471. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/17140

Issue

Section

AAAI Technical Track on Machine Learning IV