Auto-Ensemble: An Adaptive Learning Rate Scheduling based Deep Learning Model Ensembling

Abstract

Ensembling deep learning models is a shortcut to promote its implementation in new scenarios, which can avoid tuning neural networks, losses and training algorithms from scratch. However, it is difficult to collect sufficient accurate and diverse models through once training. This paper proposes Auto-Ensemble (AE) to collect checkpoints of deep learning model and ensemble them automatically by adaptive learning rate scheduling algorithm. The advantage of this method is to make the model converge to various local optima by scheduling the learning rate in once training. When the number of lo-cal optimal solutions tends to be saturated, all the collected checkpoints are used for ensemble. Our method is universal, it can be applied to various scenarios. Experiment results on multiple datasets and neural networks demonstrate it is effective and competitive, especially on few-shot learning. Besides, we proposed a method to measure the distance among models. Then we can ensure the accuracy and diversity of collected models.

arXiv comment14 pages, 8 figures, in IEEE Access

References in corpus (12)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Neural Architecture Search with Reinforcement Learning
• Wide Residual Networks
• Neural Architecture Search: A Survey
• Matching Networks for One Shot Learning
• Visualizing the Loss Landscape of Neural Nets
• Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNs
• Qualitatively characterizing neural network optimization problems
• Snapshot Ensembles: Train 1, get M for free
• Checkpoint Ensembles: Ensemble Methods from a Single Training Process
• AdaNet: A Scalable and Flexible Framework for Automatically Learning Ensembles
• Adaptive Ensemble Prediction for Deep Neural Networks based on Confidence Level