AdaNet: A Scalable and Flexible Framework for Automatically Learning Ensembles

Abstract

AdaNet is a lightweight TensorFlow-based (Abadi et al., 2015) framework for automatically learning high-quality ensembles with minimal expert intervention. Our framework is inspired by the AdaNet algorithm (Cortes et al., 2017) which learns the structure of a neural network as an ensemble of subnetworks. We designed it to: (1) integrate with the existing TensorFlow ecosystem, (2) offer sensible default search spaces to perform well on novel datasets, (3) present a flexible API to utilize expert information when available, and (4) efficiently accelerate training with distributed CPU, GPU, and TPU hardware. The code is open-source and available at: https://github.com/tensorflow/adanet.

References in corpus (3)

• Distilling the Knowledge in a Neural Network
• Born Again Neural Networks
• Sensitivity and Generalization in Neural Networks: an Empirical Study

Cited by in corpus (5)

• Grid Search, Random Search, Genetic Algorithm: A Big Comparison for NAS
• Review: Deep Learning in Electron Microscopy
• Auto-Ensemble: An Adaptive Learning Rate Scheduling based Deep Learning Model Ensembling
• Improving the performance of bagging ensembles for data streams through mini-batching
• Techniques for Automated Machine Learning