基于预测器的方法已显著增强了神经架构搜索（NAS）优化。这些预测器的有效性在很大程度上受到神经网络架构编码方式的影响。传统编码使用邻接矩阵描述神经网络的图结构，而新型编码则涵盖从潜在表示的无监督预训练到零成本代理向量等多种方法。本文将神经编码分为三大类并加以研究：结构化、学习型和基于评分的编码。此外，我们扩展了这些编码，并提出了统一编码，将NAS预测器扩展到多个搜索空间。我们的分析基于在NASBench-101（NB101）、NB201、NB301、Network Design Spaces（NDS）和TransNASBench-101等NAS空间中对超过150万个神经网络架构进行的实验。在研究基础上，我们提出了预测器FLAN：用于NAS的流注意力（Flow Attention for NAS）。FLAN整合了关于预测器设计、迁移学习和统一编码的关键洞见，使NAS精度预测器的训练成本降低超过一个数量级。我们的实现以及所有神经网络的编码已在https://github.com/abdelfattah-lab/flan_nas开源。
英文摘要：
Predictor-based methods have substantially enhanced Neural Architecture Search (NAS) optimization. The efficacy of these predictors is largely influenced by the method of encoding neural network architectures. While traditional encodings used an adjacency matrix describing the graph structure of a neural network, novel encodings embrace a variety of approaches from unsupervised pretraining of latent representations to vectors of zero-cost proxies. In this paper, we categorize and investigate neural encodings from three main types: structural, learned, and score-based. Furthermore, we extend these encodings and introduce \textit{unified encodings}, that extend NAS predictors to multiple search spaces. Our analysis draws from experiments conducted on over 1.5 million neural network architectures on NAS spaces such as NASBench-101 (NB101), NB201, NB301, Network Design Spaces (NDS), and TransNASBench-101. Building on our study, we present our predictor \textbf{FLAN}: \textbf{Fl}ow \textbf{A}ttention for \textbf{N}AS. FLAN integrates critical insights on predictor design, transfer learning, and \textit{unified encodings} to enable more than an order of magnitude cost reduction for training NAS accuracy predictors. Our implementation and encodings for all neural networks are open-sourced at \href{https://github.com/abdelfattah-lab/flan_nas}{https://github.com/abdelfattah-lab/flan\_nas}.
Neural architecture search (NAS) has been extensively studied in the past few years. A popular approach is to represent each neural architecture in the search space as a directed acyclic graph (DAG), and then search over all DAGs by encoding the adjacency matrix and list of operations as a set of hyperparameters. Recent work has demonstrated that even small changes to the way each architecture is encoded can have a significant effect on the performance of NAS algorithms. In this work, we present the first formal study on the effect of architecture encodings for NAS, including a theoretical gro…
Michigan State University（密歇根州立大学）；University of Central Florida（中佛罗里达大学）；Tencent AI Lab（腾讯人工智能实验室）
Recent works (White et al., 2020a; Yan et al., 2020) demonstrate the importance of architecture encodings in Neural Architecture Search (NAS). These encodings encode either structure or computation information of the neural architectures. Compared to structure-aware encodings, computation-aware encodings map architectures with similar accuracies to the same region, which improves the downstream architecture search performance (Zhang et al., 2019; White et al., 2020a). In this work, we introduce a Computation-Aware Transformer-based Encoding method called CATE. Different from existing computati…
The renaissance of neural architecture search (NAS) has seen classical methods such as genetic algorithms (GA) and genetic programming (GP) being exploited for convolutional neural network (CNN) architectures. While recent work have achieved promising performance on visual perception tasks, the direct encoding scheme of both GA and GP has functional complexity deficiency and does not scale well on large architectures like CNN. To address this, we present a new generative encoding scheme -- $symbolic\ linear\ generative\ encoding$ (SLGE) -- simple, yet powerful scheme which embeds local graph t…
This work proposes a novel Graph-based neural ArchiTecture Encoding Scheme, a.k.a. GATES, to improve the predictor-based neural architecture search. Specifically, different from existing graph-based schemes, GATES models the operations as the transformation of the propagating information, which mimics the actual data processing of neural architecture. GATES is a more reasonable modeling of the neural architectures, and can encode architectures from both the "operation on node" and "operation on edge" cell search spaces consistently. Experimental results on various search spaces confirm GATES's…
Inspired by the recent success of deep learning in multiscale information encoding, we introduce a variational autoencoder (VAE) based semi-supervised method for detection of faulty traffic data, which is cast as a classification problem. Continuous wavelet transform (CWT) is applied to the time series of traffic volume data to obtain rich features embodied in time-frequency representation, followed by a twin of VAE models to separately encode normal data and faulty data. The resulting multiscale dual encodings are concatenated and fed to an attention-based classifier, consisting of a self-att…
Networks found with Neural Architecture Search (NAS) achieve state-of-the-art performance in a variety of tasks, out-performing human-designed networks. However, most NAS methods heavily rely on human-defined assumptions that constrain the search: architecture's outer-skeletons, number of layers, parameter heuristics and search spaces. Additionally, common search spaces consist of repeatable modules (cells) instead of fully exploring the architecture's search space by designing entire architectures (macro-search). Imposing such constraints requires deep human expertise and restricts the search…
Duke University（杜克大学）；Facebook, Inc（脸书公司）；Tsinghua University（清华大学）；University of Nevada, Reno（内华达大学雷诺分校）
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 scalable and flexible search. However, existing estimator-based methods encode the architecture into a latent space without considering graph similarity. Ignoring graph similarity in node-based search space may induce a large inconsistency between similar graphs and their distance in the continuous encoding space, leading to inaccurate encoding representation and/or reduced represent…
Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding
Kim Jaechul Graduate School of AI（金 Jaechul人工智能研究生院）；School of Electrical Engineering（电气工程学院）；Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）
Tabular Learning: Encoding for Entity and Context Embeddings
Institute for Data Applications and Security（数据应用与安全研究院）；School of Engineering and Computer Science（工程与计算机科学学院）；Bern University of Applied Sciences（伯尔尼应用科学大学）
A Continuous Encoding-Based Representation for Efficient Multi-Fidelity Multi-Objective Neural Architecture Search
Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局高性能计算研究院）；Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局前沿人工智能研究中心）；College of Computing and Data Science (CCDS), Nanyang Technological University (NTU)（南洋理工大学计算与数据科学学院）
Alternative positional encoding functions for neural transformers
Department of Computer Languages and Computer Science University of Málaga（计算机语言与计算机科学系马拉加大学）；Department of Systems Engineering and Automation University of Málaga（系统工程与自动化系马拉加大学）；ITIS Software. Universidad de Málaga（ITIS软件. 马拉加大学）
National Technical University of Athens（雅典国家技术大学）；École Polytechnique（巴黎综合理工学院）
Neural Architecture Search (NAS) has recently gained increased attention, as a class of approaches that automatically searches in an input space of network architectures. A crucial part of the NAS pipeline is the encoding of the architecture that consists of the applied computational blocks, namely the operations and the links between them. Most of the existing approaches either fail to capture the structural properties of the architectures or use hand-engineered vector to encode the operator information. In this paper, we propose the replacement of fixed operator encoding with learnable repre…
Over the past half-decade, many methods have been considered for neural architecture search (NAS). Bayesian optimization (BO), which has long had success in hyperparameter optimization, has recently emerged as a very promising strategy for NAS when it is coupled with a neural predictor. Recent work has proposed different instantiations of this framework, for example, using Bayesian neural networks or graph convolutional networks as the predictive model within BO. However, the analyses in these papers often focus on the full-fledged NAS algorithm, so it is difficult to tell which individual com…
Existing Neural Architecture Search (NAS) methods either encode neural architectures using discrete encodings that do not scale well, or adopt supervised learning-based methods to jointly learn architecture representations and optimize architecture search on such representations which incurs search bias. Despite the widespread use, architecture representations learned in NAS are still poorly understood. We observe that the structural properties of neural architectures are hard to preserve in the latent space if architecture representation learning and search are coupled, resulting in less effe…
How to discover and evaluate the true strength of models quickly and accurately is one of the key challenges in Neural Architecture Search (NAS). To cope with this problem, we propose an Architecture-Driven Weight Prediction (ADWP) approach for neural architecture search (NAS). In our approach, we first design an architecture-intensive search space and then train a HyperNetwork by inputting stochastic encoding architecture parameters. In the trained HyperNetwork, weights of convolution kernels can be well predicted for neural architectures in the search space. Consequently, the target architec…
Transformer models have advanced the state of the art in many Natural Language Processing (NLP) tasks. In this paper, we present a new Transformer architecture, Extended Transformer Construction (ETC), that addresses two key challenges of standard Transformer architectures, namely scaling input length and encoding structured inputs. To scale attention to longer inputs, we introduce a novel global-local attention mechanism between global tokens and regular input tokens. We also show that combining global-local attention with relative position encodings and a Contrastive Predictive Coding (CPC) …
Recently, differentiable search methods have made major progress in reducing the computational costs of neural architecture search. However, these approaches often report lower accuracy in evaluating the searched architecture or transferring it to another dataset. This is arguably due to the large gap between the architecture depths in search and evaluation scenarios. In this paper, we present an efficient algorithm which allows the depth of searched architectures to grow gradually during the training procedure. This brings two issues, namely, heavier computational overheads and weaker search …
Existing neural architecture search (NAS) methods often return an architecture with good search performance but generalizes poorly to the test setting. To achieve better generalization, we propose a novel neighborhood-aware NAS formulation to identify flat-minima architectures in the search space, with the assumption that flat minima generalize better than sharp minima. The phrase ``flat-minima architecture'' refers to architectures whose performance is stable under small perturbations in the architecture (e.g., replacing a convolution with a skip connection). Our formulation takes the ``flatn…
Differentiable ARchiTecture Search (DARTS) is one of the most trending Neural Architecture Search (NAS) methods. It drastically reduces search cost by resorting to weight-sharing. However, it also dramatically reduces the search space, thus excluding potential promising architectures. In this article, we propose D-DARTS, a solution that addresses this problem by nesting neural networks at the cell level instead of using weight-sharing to produce more diversified and specialized architectures. Moreover, we introduce a novel algorithm that can derive deeper architectures from a few trained cells…
Neural architecture search has shown its great potential in various areas recently. However, existing methods rely heavily on a black-box controller to search architectures, which suffers from the serious problem of lacking interpretability. In this paper, we propose disentangled neural architecture search (DNAS) which disentangles the hidden representation of the controller into semantically meaningful concepts, making the neural architecture search process interpretable. Based on systematical study, we discover the correlation between network architecture and its performance, and propose a d…
School of Computing（计算学院）；National University of Singapore（新加坡国立大学）
Neural architecture search (NAS) searches architectures automatically for given tasks, e.g., image classification and language modeling. Improving the search efficiency and effectiveness have attracted increasing attention in recent years. However, few efforts have been devoted to understanding the generated architectures. In this paper, we first reveal that existing NAS algorithms (e.g., DARTS, ENAS) tend to favor architectures with wide and shallow cell structures. These favorable architectures consistently achieve fast convergence and are consequently selected by NAS algorithms. Our empiric…
In neural architecture search, the structure of the neural network to best model a given dataset is determined by an automated search process. Efficient Neural Architecture Search (ENAS), proposed by Pham et al. (2018), has recently received considerable attention due to its ability to find excellent architectures within a comparably short search time. In this work, which is motivated by the quest to further improve the learning speed of architecture search, we evaluate the learning progress of the controller which generates the architectures in ENAS. We measure the progress by comparing the a…
Rensselaer Polytechnic Institute（伦斯勒理工学院）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）
Neural architecture search enables automation of architecture design. Despite its success, it is computationally costly and does not provide an insight on how to design a desirable architecture. Here we propose a new way of searching neural network where we search neural architecture by rewiring the corresponding graph and predict the architecture performance by graph properties. Because we do not perform machine learning over the entire graph space and use predicted architecture performance to search architecture, the searching process is remarkably efficient. We find graph based search can g…
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学（KAUST））；Intel Labs（英特尔研究院）
Architecture design has become a crucial component of successful deep learning. Recent progress in automatic neural architecture search (NAS) shows a lot of promise. However, discovered architectures often fail to generalize in the final evaluation. Architectures with a higher validation accuracy during the search phase may perform worse in the evaluation. Aiming to alleviate this common issue, we introduce sequential greedy architecture search (SGAS), an efficient method for neural architecture search. By dividing the search procedure into sub-problems, SGAS chooses and prunes candidate opera…
Korea University（高丽大学）；Hallym University（翰林大学）；Kyung Hee University（庆熙大学）
As deep neural networks achieve unprecedented performance in various tasks, neural architecture search (NAS), a research field for designing neural network architectures with automated processes, is actively underway. More recently, differentiable NAS has a great impact by reducing the search cost to the level of training a single network. Besides, the search space that defines candidate architectures to be searched directly affects the performance of the final architecture. In this paper, we propose an adaptation scheme of the search space by introducing a search scope. The effectiveness of p…
This paper addresses the scalability challenge of architecture search by formulating the task in a differentiable manner. Unlike conventional approaches of applying evolution or reinforcement learning over a discrete and non-differentiable search space, our method is based on the continuous relaxation of the architecture representation, allowing efficient search of the architecture using gradient descent. Extensive experiments on CIFAR-10, ImageNet, Penn Treebank and WikiText-2 show that our algorithm excels in discovering high-performance convolutional architectures for image classification a…
Differentiable architecture search (DAS) has made great progress in searching for high-performance architectures with reduced computational cost. However, DAS-based methods mainly focus on searching for a repeatable cell structure, which is then stacked sequentially in multiple stages to form the networks. This configuration significantly reduces the search space, and ignores the importance of connections between the cells. To overcome this limitation, in this paper, we propose a Hierarchical Differentiable Architecture Search (H-DAS) that performs architecture search both at the cell level an…
TALP Research Center（TALP研究中心）；Universitat Politecnica de Catalunya（加泰罗尼亚理工大学）
The computing power of mobile devices limits the end-user applications in terms of storage size, processing, memory and energy consumption. These limitations motivate researchers for the design of more efficient deep models. On the other hand, self-attention networks based on Transformer architecture have attracted remarkable interests due to their high parallelization capabilities and strong performance on a variety of Natural Language Processing (NLP) applications. Inspired by the Transformer, we propose a tandem Self-Attention Encoding and Pooling (SAEP) mechanism to obtain a discriminative…
In this paper, we point out that differential architecture search (DARTS) makes gradient of architecture parameters biased for network weights and architecture parameters are updated in different datasets alternatively in the bi-level optimization framework. The bias causes the architecture parameters of non-learnable operations to surpass that of learnable operations. Moreover, using softmax as architecture parameters' activation function and inappropriate learning rate would exacerbate the bias. As a result, it's frequently observed that non-learnable operations are dominated in the search p…
Neural architecture search (NAS) is a recent methodology for automating the design of neural network architectures. Differentiable neural architecture search (DARTS) is a promising NAS approach that dramatically increases search efficiency. However, it has been shown to suffer from performance collapse, where the search often leads to detrimental architectures. Many recent works try to address this issue of DARTS by identifying indicators for early stopping, regularising the search objective to reduce the dominance of some operations, or changing the parameterisation of the search problem. In …
Neural Architecture Search (NAS) enabled the discovery of state-of-the-art architectures in many domains. However, the success of NAS depends on the definition of the search space. Current search spaces are defined as a static sequence of decisions and a set of available actions for each decision. Each possible sequence of actions defines an architecture. We propose a more expressive class of search space: directed graphs. In our formalism, each decision is a vertex and each action is an edge. This allows us to model iterative and branching architecture design decisions. We demonstrate in simu…
National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所模式识别国家重点实验室）；School of EIC, Huazhong University of Science and Technology（华中科技大学电子信息与通信学院）；Horizon Robotics（地平线机器人）
Neural architecture search (NAS) methods have been proposed to release human experts from tedious architecture engineering. However, most current methods are constrained in small-scale search due to the issue of computational resources. Meanwhile, directly applying architectures searched on small datasets to large datasets often bears no performance guarantee. This limitation impedes the wide use of NAS on large-scale tasks. To overcome this obstacle, we propose an elastic architecture transfer mechanism for accelerating large-scale neural architecture search (EAT-NAS). In our implementations,…
Hong Kong Applied Science and Technology Research Institute Company Limited（香港应用科技研究院有限公司）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））
The Transformer based neural networks have been showing significant advantages on most evaluations of various natural language processing and other sequence-to-sequence tasks due to its inherent architecture based superiorities. Although the main architecture of the Transformer has been continuously being explored, little attention was paid to the positional encoding module. In this paper, we enhance the sinusoidal positional encoding algorithm by maximizing the variances between encoded consecutive positions to obtain additional promotion. Furthermore, we propose an augmented Transformer arch…
Automated Dominative Subspace Mining for Efficient Neural Architecture Search
School of Software Engineering, South China University of Technology（华南理工大学软件学院）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Changsha Hisense Intelligent System Research Institute Co., Ltd（长沙海信智能系统研究院有限公司）；Department of Computer Science and Engineering, the Hong Kong University of Science and Technology（香港科技大学计算机科学与工程学系）
University of Alberta（阿尔伯塔大学）；Alberta Machine Intelligence Institute (Amii)（阿尔伯塔机器智能研究所（Amii））
Architecture search optimizes the structure of a neural network for some task instead of relying on manual authoring. However, it is slow, as each potential architecture is typically trained from scratch. In this paper we present an approach called Conceptual Expansion Neural Architecture Search (CENAS) that combines a sample-efficient, computational creativity-inspired transfer learning approach with neural architecture search. This approach finds models faster than naive architecture search via transferring existing weights to approximate the parameters of the new model. It outperforms stand…
State-of-the-art deep networks are often too large to deploy on mobile devices and embedded systems. Mobile neural architecture search (NAS) methods automate the design of small models but state-of-the-art NAS methods are expensive to run. Differentiable neural architecture search (DNAS) methods reduce the search cost but explore a limited subspace of candidate architectures. In this paper, we introduce Fine-Grained Stochastic Architecture Search (FiGS), a differentiable search method that searches over a much larger set of candidate architectures. FiGS simultaneously selects and modifies oper…
University of California San Diego（加州大学圣地亚哥分校）；Rutgers University（罗格斯大学）
Neural architecture search, which aims to automatically search for architectures (e.g., convolution, max pooling) of neural networks that maximize validation performance, has achieved remarkable progress recently. In many application scenarios, several parties would like to collaboratively search for a shared neural architecture by leveraging data from all parties. However, due to privacy concerns, no party wants its data to be seen by other parties. To address this problem, we propose federated neural architecture search (FNAS), where different parties collectively search for a differentiable…
Neural Architecture Search (NAS) algorithms automate the task of finding optimal deep learning architectures given an initial search space of possible operations. Developing these search spaces is usually a manual affair with pre-optimized search spaces being more efficient, rather than searching from scratch. In this paper we present a new framework called Neural Architecture Type System (NeuralArTS) that categorizes the infinite set of network operations in a structured type system. We further demonstrate how NeuralArTS can be applied to convolutional layers and propose several future direct…
Revisiting Bi-Encoder Neural Search: An Encoding--Searching Separation Perspective
University of Information Technology（信息技术大学）；Vietnam National University（越南国家大学）；National Institute of Informatics（国家信息研究所）；The Graduate University for Advanced Studies, SOKENDAI（高级研究大学，SOKENDAI）；The University of Tokyo（东京大学）
Health-related data is noisy and stochastic in implying the true physiological states of patients, limiting information contained in single-moment observations for sequential clinical decision making. We model patient-clinician interactions as partially observable Markov decision processes (POMDPs) and optimize sequential treatment based on belief states inferred from history sequence. To facilitate inference, we build a variational generative model and boost state representation with a recurrent neural network (RNN), incorporating an auxiliary loss from sequence auto-encoding. Meanwhile, we o…
Recent works investigated the generalization properties in deep neural networks (DNNs) by studying the Information Bottleneck in DNNs. However, the mea- surement of the mutual information (MI) is often inaccurate due to the density estimation. To address this issue, we propose to measure the dependency instead of MI between layers in DNNs. Specifically, we propose to use Hilbert-Schmidt Independence Criterion (HSIC) as the dependency measure, which can measure the dependence of two random variables without estimating probability densities. Moreover, HSIC is a special case of the Squared-loss M…
There has been significant recent interest towards achieving highly efficient deep neural network architectures. A promising paradigm for achieving this is the concept of evolutionary deep intelligence, which attempts to mimic biological evolution processes to synthesize highly-efficient deep neural networks over successive generations. An important aspect of evolutionary deep intelligence is the genetic encoding scheme used to mimic heredity, which can have a significant impact on the quality of offspring deep neural networks. Motivated by the neurobiological phenomenon of synaptic clustering…
