paper-with-me

Papers

Interpretable Neural Architecture Search via Bayesian Optimisation with Weisfeiler-Lehman Kernels

2020-06-13 · ICLR 2021 1 · Binxin Ru, Xingchen Wan, Xiaowen Dong, Michael Osborne

Current neural architecture search (NAS) strategies focus only on finding a single, good, architecture. They offer little insight into why a specific network is performing well, or how we should modify the architecture if we want further improvements. We propose a Bayesian optimisation (BO) approach for NAS that combines the Weisfeiler-Lehman graph kernel with a Gaussian process surrogate. Our method optimises the architecture in a highly data-efficient manner: it is capable of capturing the topological structures of the architectures and is scalable to large graphs, thus making the high-dimensional and graph-like search spaces amenable to BO. More importantly, our method affords interpretability by discovering useful network features and their corresponding impact on the network performance. Indeed, we demonstrate empirically that our surrogate model is capable of identifying useful motifs which can guide the generation of new architectures. We finally show that our method outperforms existing NAS approaches to achieve the state of the art on both closed- and open-domain search spaces.

📄 PDF Abstract BibTeX arXiv:2006.07556

Code (1)

xingchenwan/nasbowl pytorch

Tasks

Bayesian OptimisationNeural Architecture Search

Methods 이 논문이 사용한 방법론

Sigmoid 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 $x$…
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Gaussian Process Gaussian Processes are non-parametric models for approximating functions. They rely upon a measure of similarity between points (the kernel function) to predict the value for…

Similar Papers 제목 키워드 기반

BOP-Elites, a Bayesian Optimisation algorithm for Quality-Diversity search

2020-05-08 · Paul Kent, Juergen Branke

Quality Diversity (QD) algorithms such as MAP-Elites are a class of optimisation techniques that attempt to find a set of high-performing points from an objective function while enforcing behavioural diversity of the poi…

Bayesian OptimisationDiversityGaussian Processes

Sub-linear Regret Bounds for Bayesian Optimisation in Unknown Search Spaces

2020-09-05 · NeurIPS 2020 12 · Hung Tran-The, Sunil Gupta, Santu Rana, Huong Ha 외

Bayesian optimisation is a popular method for efficient optimisation of expensive black-box functions. Traditionally, BO assumes that the search space is known. However, in many problems, this assumption does not hold. T…

Bayesian Optimisation

Neural Architecture Search with Bayesian Optimisation and Optimal Transport

2018-02-11 · NeurIPS 2018 12 · Kirthevasan Kandasamy, Willie Neiswanger, Jeff Schneider, Barnabas Poczos 외

Bayesian Optimisation (BO) refers to a class of methods for global optimisation of a function $f$ which is only accessible via point evaluations. It is typically used in settings where $f$ is expensive to evaluate. A com…

Bayesian OptimisationBIG-bench Machine LearningModel SelectionNeural Architecture Search

Tuning Hyperparameters without Grad Students: Scalable and Robust Bayesian Optimisation with Dragonfly

2019-03-15 · Kirthevasan Kandasamy, Karun Raju Vysyaraju, Willie Neiswanger, Biswajit Paria 외

Bayesian Optimisation (BO) refers to a suite of techniques for global optimisation of expensive black box functions, which use introspective Bayesian models of the function to efficiently search for the optimum. While BO…

Bayesian Optimisation

Cost-aware Multi-objective Bayesian optimisation

2019-09-09 · Majid Abdolshah, Alistair Shilton, Santu Rana, Sunil Gupta 외

The notion of expense in Bayesian optimisation generally refers to the uniformly expensive cost of function evaluations over the whole search space. However, in some scenarios, the cost of evaluation for black-box object…

Bayesian Optimisation