Auto-Keras: Efficient Neural Architecture Search with Network Morphism

By Haifeng Jin, Qingquan Song, Xia Hu. 2018

63 citations recorded by the source corpus.

Subfields: Neural Architecture Search & AutoML

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Neural Architecture Search & AutoML

1. Colin White
2. Yash Savani
3. Sam Nolen
4. Xia Hu
5. Willie Neiswanger
6. Qingquan Song
7. Liam Li
8. Ameet Talwalkar

Citations in the corpus

• BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search (2019, methodology): “Initial BO approaches defined a distance function between architectures (Kandasamy et al. 2018b; Jin, Song, and Hu 2018).”
• Auto-GNN: Neural architecture search of graph neural networks (2019, methodology): “The action guider help controller search the potential networks along the direction with most uncertainty, which performs similar to the Bayesian optimization method [16].”
• AutoGAN: Neural Architecture Search for Generative Adversarial Networks (2019, methodology): “For the optimization algorithm, popular options include reinforcement learning [4, 71, 69, 72], evolutionary algorithm [60], Bayesian optimization [24], random search [7], and gradient-based optimization methods [38, 1].”
• Random Search and Reproducibility for Neural Architecture Search (2019, methodology): “Some works either compare to random search given a budget of just of few evaluations [39, 32] or Bayesian optimization methods without efficient architecture evaluation schemes [21].”
• A Study on Encodings for Neural Architecture Search (2020, methodology): “In the case of a Gaussian process model, the algorithm uses a distance metric defined on pairs of neural architectures, which is typically chosen as the edit distance between architecture encodings [6, 5].”
• Local Search is State of the Art for Neural Architecture Search Benchmarks (2020, methodology): “Popular techniques include Bayesian optimization [16, 13], reinforcement learning [40, 27, 20], gradient descent [21], neural prediction [36, 30], and evolution [28].”
• NAT: Neural Architecture Transformer for Accurate and Compact Architectures (2019, methodology): “propose a Bayesian optimization approach [19] to morph the deep architectures by inserting additional layers, adding more filters or introducing additional skip connections.”
• Optimal Transport Kernels for Sequential and Parallel Neural Architecture Search (2020, methodology): “Recently, Bayesian optimization has been used for searching the best neural architecture (Kandasamy et al., 2018; Jin et al., 2018; White et al., 2021).”