paper-with-me

Papers

Neural Architecture Search in Embedding Space

2019-09-09 · Chun-Ting Liu

The neural architecture search (NAS) algorithm with reinforcement learning can be a powerful and novel framework for the automatic discovering process of neural architectures. However, its application is restricted by noncontinuous and high-dimensional search spaces, which result in difficulty in optimization. To resolve these problems, we proposed NAS in embedding space (NASES), which is a novel framework. Unlike other NAS with reinforcement learning approaches that search over a discrete and high-dimensional architecture space, this approach enables reinforcement learning to search in an embedding space by using architecture encoders and decoders. The current experiment demonstrated that the performance of the final architecture network using the NASES procedure is comparable with that of other popular NAS approaches for the image classification task on CIFAR-10. The results of the experiment were efficient and indicated that NASES was highly efficient to discover final architecture only in $<$3.5 GPU hours. The beneficial-performance and effectiveness of NASES was impressive when the architecture-embedding searching and weight initialization were applied.

📄 PDF Abstract BibTeX arXiv:1909.03615

Code (0)

등록된 구현이 없습니다.

Tasks

GPUimage-classificationImage ClassificationNeural Architecture Searchreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Contrastive Embeddings for Neural Architectures

2021-02-08 · Daniel Hesslow, Iacopo Poli

The performance of algorithms for neural architecture search strongly depends on the parametrization of the search space. We use contrastive learning to identify networks across different initializations based on their d…

Contrastive LearningNeural Architecture SearchTransfer Learning

Learnable Embedding Space for Efficient Neural Architecture Compression

2019-02-01 · ICLR 2019 5 · Shengcao Cao, Xiaofang Wang, Kris M. Kitani

We propose a method to incrementally learn an embedding space over the domain of network architectures, to enable the careful selection of architectures for evaluation during compressed architecture search. Given a teach…

Bayesian OptimizationNeural Architecture SearchReinforcement Learning

Smooth Variational Graph Embeddings for Efficient Neural Architecture Search

2020-10-09 · Jovita Lukasik, David Friede, Arber Zela, Frank Hutter 외

Neural architecture search (NAS) has recently been addressed from various directions, including discrete, sampling-based methods and efficient differentiable approaches. While the former are notoriously expensive, the la…

AutoMLBayesian OptimizationGraph Neural NetworkNeural Architecture Search

Towards Code-Oriented LM Embeddings for Surrogate-Assisted Neural Architecture Search

2026-05-15 · Pranav Somu, Advay Balakrishnan, Stepan Kravtsov, Aaron McDaniel 외 arxiv

Developing effective surrogates (performance predictors) for Neural Architecture Search (NAS) typically requires expensive fine-tuning or the engineering of complex representations. We propose a low-cost embedding strate…

Neural Architecture Search

NASGEM: Neural Architecture Search via Graph Embedding Method

2020-07-08 · Hsin-Pai Cheng, Tunhou Zhang, Yixing Zhang, Shi-Yu Li 외

Neural Architecture Search (NAS) automates and prospers the design of neural networks. Estimator-based NAS has been proposed recently to model the relationship between architectures and their performance to enable scalab…

Graph EmbeddingGraph SimilarityNeural Architecture Searchobject-detection+1