DATA: Differentiable ArchiTecture Approximation
Neural architecture search (NAS) is inherently subject to the gap of architectures during searching and validating. To bridge this gap, we develop Differentiable ArchiTecture Approximation (DATA) with an Ensemble Gumbel-Softmax (EGS) estimator to automatically approximate architectures during searching and validating in a differentiable manner. Technically, the EGS estimator consists of a group of Gumbel-Softmax estimators, which is capable of converting probability vectors to binary codes and passing gradients from binary codes to probability vectors. Benefiting from such modeling, in searching, architecture parameters and network weights in the NAS model can be jointly optimized with the standard back-propagation, yielding an end-to-end learning mechanism for searching deep models in a large enough search space. Conclusively, during validating, a high-performance architecture that approaches to the learned one during searching is readily built. Extensive experiments on a variety of popular datasets strongly evidence that our method is capable of discovering high-performance architectures for image classification, language modeling and semantic segmentation, while guaranteeing the requisite efficiency during searching.
Code (1)
Tasks
image-classificationImage ClassificationLanguage ModelingLanguage ModellingNeural Architecture SearchSemantic SegmentationSimilar Papers 제목 키워드 기반
UNAS: Differentiable Architecture Search Meets Reinforcement Learning
Neural architecture search (NAS) aims to discover network architectures with desired properties such as high accuracy or low latency. Recently, differentiable NAS (DNAS) has demonstrated promising results while maintaini…
Neural Architecture Searchreinforcement-learningReinforcement LearningReinforcement Learning (RL)EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture Search
In hardware-aware Differentiable Neural Architecture Search (DNAS), it is challenging to compute gradients of hardware metrics to perform architecture search. Existing works rely on linear approximations with limited sup…
BenchmarkingNeural Architecture SearchDifferentiable Histogram with Hard-Binning
The simplicity and expressiveness of a histogram render it a useful feature in different contexts including deep learning. Although the process of computing a histogram is non-differentiable, researchers have proposed di…
Going Beyond Approximation: Encoding Constraints for Explainable Multi-hop Inference via Differentiable Combinatorial Solvers
Integer Linear Programming (ILP) provides a viable mechanism to encode explicit and controllable assumptions about explainable multi-hop inference with natural language. However, an ILP formulation is non-differentiable …
iDARTS: Differentiable Architecture Search with Stochastic Implicit Gradients
\textit{Differentiable ARchiTecture Search} (DARTS) has recently become the mainstream of neural architecture search (NAS) due to its efficiency and simplicity. With a gradient-based bi-level optimization, DARTS alternat…
Neural Architecture Search