Evolutionary Transfer Neural Architecture Search Across Spaces via Representation Learning

ETNAS: An energy consumption task-driven neural architecture search

Neural architecture search (NAS) can automatically discover well-performing architectures in a large search space and has been shown to bring improvements to various applications. However, the computational burden of NAS is huge, since exploring a large search space can need evaluating more than thousands of architecture samples. To improve the sample efficiency of search space exploration, predictor-based NAS methods learn a performance predictor of architectures, and utilize the predictor to sample worth-evaluating architectures. The encoding scheme of NN architectures is crucial to the predictor's generalization ability, and thus crucial to the efficacy of the NAS process. To this end, we have designed a generic Graph-based neural ArchiTecture Encoding Scheme (GATES), a more reasonable modeling of NN architectures that mimics their data processing. Nevertheless, GATES is unaware of the concrete computing semantic of NN operations or architectures. Thus, the learning of operation embeddings and weights in GATES can only exploit the information in architectures-performance pairs. We propose GATES++, which incorporates multifaceted information about NN's operation-level and architecture-level computing semantics into its construction and training, respectively. Experiments on benchmark search spaces show that both the operation-level and architecture-level information can bring improvements alone, and GATES++ can discover better architectures after evaluating the same number of architectures.

The Neural Architecture Search (NAS) enables Deep Learning engineers to automatically explore the wide variety of all possible neural architectures to design the solution for a given problem. Though the NAS methods automatically generate the best possible architecture, it is time-consuming, and resource constraint since the search space consists of the best architectures(good accuracy) and includes non performing architectures as well. Researchers have proposed various NAS methods especially based on evolutionary algorithms which consists of diverse search space due to the presence of genetic operations leading to expensive search time cost. These NAS methods also deal with multiple objectives like FLOPS, latency and power usage, and model accuracy, for image classification tasks. Though the generated architectures from NAS have multi-objective, they require significant computing resources and are not suitable for running on edge devices with limited computational resources. The proposed method includes a novel model optimization method designed for the neural architecture generated from NAS methods to make it smaller in size, memory efficient, and faster at inference with minimal loss of accuracy. We optimized the models designed for standard datasets and decreased the parameters by 7.82% for CIFAR-10, 2.95% for CIFAR-100, 6.36% for STL-10, and 3.57% for Food-101 datasets. The resulting models have achieved an accuracy of 97.4% for CIFAR-10, 86% for CIFAR-100, 96.7% for STL-10, and 87.4% for Food-101 datasets.

Deep learning has made substantial breakthroughs in many fields due to its powerful automatic representation capabilities. It has been proven that neural architecture design is crucial to the feature representation of data and the final performance. However, the design of the neural architecture heavily relies on the researchers’ prior knowledge and experience. And due to the limitations of humans’ inherent knowledge, it is difficult for people to jump out of their original thinking paradigm and design an optimal model. Therefore, an intuitive idea would be to reduce human intervention as much as possible and let the algorithm automatically design the neural architecture.Neural Architecture Search(NAS) is just such a revolutionary algorithm, and the related research work is complicated and rich. Therefore, a comprehensive and systematic survey on the NAS is essential. Previously related surveys have begun to classify existing work mainly based on the key components of NAS: search space, search strategy, and evaluation strategy. While this classification method is more intuitive, it is difficult for readers to grasp the challenges and the landmark work involved. Therefore, in this survey, we provide a new perspective: beginning with an overview of the characteristics of the earliest NAS algorithms, summarizing the problems in these early NAS algorithms, and then providing solutions for subsequent related research work. In addition, we conduct a detailed and comprehensive analysis, comparison, and summary of these works. Finally, we provide some possible future research directions.

Deep learning methods, especially deep convolutional neural networks (DCNNs), have been widely used in high-resolution remote sensing image (HRSI) semantic segmentation. In literature, most successful DCNNs are artificially designed through a large number of experiments, which often consume lots of time and depend on rich domain knowledge. Recently, neural architecture search (NAS), as a direction for automatically designing network architectures, has achieved great success in different kinds of computer vision tasks. For HRSI semantic segmentation, NAS faces two major challenges: (1) The task’s high complexity degree, which is caused by the pixel-by-pixel prediction demand in semantic segmentation, leads to a rapid expansion of the search space; (2) HRSI semantic segmentation often needs to exploit long-range dependency (i.e., a large spatial context), which means the NAS technique requires a lot of display memory in the optimization process and can be tough to converge. With the aforementioned considerations in mind, we propose a new decoupling NAS (DNAS) framework to automatically design the network architecture for HRSI semantic segmentation. In DNAS, a hierarchical search space with three levels is recommended: path-level, connection-level, and cell-level. To adapt to this hierarchical search space, we devised a new decoupling search optimization strategy to decrease the memory occupation. More specifically, the search optimization strategy consists of three stages: (1) a light super-net (i.e., the specific search space) in the path-level space is trained to get the optimal path coding; (2) we endowed the optimal path with various cross-layer connections and it is trained to obtain the connection coding; (3) the super-net, which is initialized by path coding and connection coding, is populated with kinds of concrete cell operators and the optimal cell operators are finally determined. It is worth noting that the well-designed search space can cover various network candidates and the optimization process can be done efficiently. Extensive experiments on the publicly open GID and FU datasets showed that our DNAS outperformed the state-of-the-art methods, including artificial networks and NAS methods.

One-shot neural architecture search (NAS) has recently become mainstream in the NAS community because it significantly improves computational efficiency through weight sharing. However, the supernet training paradigm in one-shot NAS introduces catastrophic forgetting, where each step of the training can deteriorate the performance of other architectures that contain partially-shared weights with current architecture. To overcome this problem of catastrophic forgetting, we formulate supernet training for one-shot NAS as a constrained continual learning optimization problem such that learning the current architecture does not degrade the validation accuracy of previous architectures. The key to solving this constrained optimization problem is a novelty search based architecture selection (NSAS) loss function that regularizes the supernet training by using a greedy novelty search method to find the most representative subset. We applied the NSAS loss function to two one-shot NAS baselines and extensively tested them on both a common search space and a NAS benchmark dataset. We further derive three variants based on the NSAS loss function, the NSAS with depth constrain (NSAS-C) to improve the transferability, and NSAS-G and NSAS-LG to handle the situation with a limited number of constraints. The experiments on the common NAS search space demonstrate that NSAS and it variants improve the predictive ability of supernet training in one-shot NAS with remarkable and efficient performance on the CIFAR-10, CIFAR-100, and ImageNet datasets. The results with the NAS benchmark dataset also confirm the significant improvements these one-shot NAS baselines can make.

Defect recognition is an important task in intelligent manufacturing. Due to the subjectivity of human annotation, the collected defect data usually contains a lot of noise and unpredictable uncertainties, which have a great negative influence on defect recognition. It is a significant challenge to discover an effective defect recognition model with satisfactory uncertainty processing ability. A natural way is to automatically search for an efficient deep model, which can be realized by neural architecture search (NAS). To achieve this, we propose an efficient fuzzy NAS framework for defect recognition, where the searched architecture can effectively handle uncertain information from the given datasets. Specifically, we first design a fuzzy search space and the related encoding strategy for fuzzy NAS. Then, we propose a comparator-based evolutionary search approach, where an online end-to-end comparator is learned to directly determine the selection of candidate architectures from the evolutionary population. The comparator works in an end-to-end way and it transforms the complex ranking problem of evaluating architectures into a simple classification task, which overcomes the rank disorder issue suffered from traditional performance predictors. A series of experimental results demonstrate that the architecture with fewer #Params (1.22 M) search by fuzzy neural architecture search framework for defect recognition method achieves higher accuracy (92.26%) compared to the state-of-the-art results (i.e., DARTS-PV) on the ELPV dataset, as well as competitive results (accuracy = 76.4%, #Params = 1.04 M) on the CODEBRIM dataset. Experimental results show the effectiveness and efficiency of our proposed method in handling uncertain problems.

Hyperspectral image classification (HSIC) is a key task in the field of remote sensing, but the complex nature of hyperspectral data poses a serious challenge to traditional methods. Although deep learning significantly improves classification performance through automatic feature extraction, manually designed network architectures suffer from issues such as dependence on expert experience and lack of flexibility. Neural architecture search (NAS) provides new ideas for HSIC through automated network structure optimization. This article systematically reviews the application progress of NAS in HSIC: firstly, the core components of NAS are analyzed, and the characteristics of various methods are compared from three aspects: search space, search strategy, and performance evaluation. Furthermore, the focus is on exploring NAS technology based on convolutional neural networks, covering 1D, 2D, and 3D convolutional architectures and their innovative integration with various technologies, revealing the advantages of NAS in HSIC. However, NAS still faces challenges such as high computing resource requirements and insufficient interpretability. This article systematically reviews the application of NAS in the field of HSIC for the first time, facilitating readers to quickly understand the development process of NAS in HSIC and the advantages and disadvantages of various technologies, proposing possible future research directions.

By labelling high spatial resolution (HSR) images with specific semantic classes according to geographical properties, scene classification has been proven to be an effective method for HSR remote sensing image semantic interpretation. Deep learning is widely applied in HSR remote sensing scene classification. Most of the scene classification methods based on deep learning assume that the training datasets and the test datasets come from the same datasets or obey similar feature distributions. However, in practical application scenarios, it is difficult to guarantee this assumption. For new datasets, it is time-consuming and labor-intensive to repeat data annotation and network design. The neural architecture search (NAS) can automate the process of redesigning the baseline network. However, traditional NAS lacks the generalization ability to different settings and tasks. In this paper, a novel neural network search architecture framework—the spatial generalization neural architecture search (SGNAS) framework—is proposed. This model applies the NAS of spatial generalization to cross-domain scene classification of HSR images to bridge the domain gap. The proposed SGNAS can automatically search the architecture suitable for HSR image scene classification and possesses network design principles similar to the manually designed networks. To obtain a simple and low-dimensional search space, the traditional NAS search space was optimized and the human-the-loop method was used. To extend the optimized search space to different tasks, the search space was generalized. The experimental results demonstrate that the network searched by the SGNAS framework with good generalization ability displays its effectiveness for cross-domain scene classification of HSR images, both in accuracy and time efficiency.

Evolutionary algorithms (EA) based neural architecture search (NAS) involves evaluating each architecture by training it from scratch, which is extremely time-consuming. This can be reduced by using a supernet for estimating the fitness of an architecture due to weight sharing among all architectures in the search space. However, the estimated fitness is very noisy due to the co-adaptation of the operations in the supernet which results in NAS methods getting trapped in local optimum. In this paper, we propose a method called NEvoNAS wherein the NAS problem is posed as a multi-objective problem with 2 objectives: (i) maximize architecture novelty, (ii) maximize architecture fitness/accuracy. The novelty search is used for maintaining a diverse set of solutions at each generation which helps avoiding local optimum traps while the architecture fitness is calculated using supernet. NSGA-II is used for finding the pareto optimal front for the NAS problem and the best architecture in the pareto front is returned as the searched architecture. Exerimentally, NEvoNAS gives better results on 2 different search spaces while using significantly less computational resources as compared to previous EA-based methods. The code for our paper can be found here.

Recent breakthroughs of Neural Architecture Search (NAS) extend the field’s research scope towards a broader range of vision tasks and more diversified search spaces. While existing NAS methods mostly design architectures on a single task, algorithms that look beyond single-task search are surging to pursue a more efficient and universal solution across various tasks. Many of them leverage transfer learning and seek to preserve, reuse, and refine network design knowledge to achieve higher efficiency in future tasks. However, the enormous computational cost and experiment complexity of cross-task NAS are imposing barriers for valuable research in this direction. Existing NAS benchmarks all focus on one type of vision task, i.e., classification. In this work, we propose TransNAS-Bench-101, a benchmark dataset containing network performance across seven tasks, covering classification, regression, pixel-level prediction, and self-supervised tasks. This diversity provides opportunities to transfer NAS methods among tasks and allows for more complex transfer schemes to evolve. We explore two fundamentally different types of search space: cell-level search space and macro-level search space. With 7,352 backbones evaluated on seven tasks, 51,464 trained models with detailed training information are provided. With TransNAS-Bench-101, we hope to encourage the advent of exceptional NAS algorithms that raise cross-task search efficiency and generalizability to the next level. Our dataset and code will be available at Mindspore <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> and VEGA <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> .

Predictor-based Neural Architecture Search (NAS) employs an architecture performance predictor to improve the sample efficiency. However, predictor-based NAS suffers from the severe ``cold-start'' problem, since a large amount of architecture-performance data is required to get a working predictor. In this paper, we focus on exploiting information in cheaper-to-obtain performance estimations (i.e., low-fidelity information) to mitigate the large data requirements of predictor training. Despite the intuitiveness of this idea, we observe that using inappropriate low-fidelity information even damages the prediction ability and different search spaces have different preferences for low-fidelity information types. To solve the problem and better fuse beneficial information provided by different types of low-fidelity information, we propose a novel dynamic ensemble predictor framework that comprises two steps. In the first step, we train different sub-predictors on different types of available low-fidelity information to extract beneficial knowledge as low-fidelity experts. In the second step, we learn a gating network to dynamically output a set of weighting coefficients conditioned on each input neural architecture, which will be used to combine the predictions of different low-fidelity experts in a weighted sum. The overall predictor is optimized on a small set of actual architecture-performance data to fuse the knowledge from different low-fidelity experts to make the final prediction. We conduct extensive experiments across five search spaces with different architecture encoders under various experimental settings. For example, our methods can improve the Kendall's Tau correlation coefficient between actual performance and predicted scores from 0.2549 to 0.7064 with only 25 actual architecture-performance data on NDS-ResNet. Our method can easily be incorporated into existing predictor-based NAS frameworks to discover better architectures. Our method will be implemented in Mindspore (Huawei 2020), and the example code is published at https://github.com/A-LinCui/DELE.

High-resolution representations (HR) are essential for dense prediction tasks such as segmentation, detection, and pose estimation. Learning HR representations is typically ignored in previous Neural Architecture Search (NAS) methods that focus on image classification. This work proposes a novel NAS method, called HR-NAS, which is able to find efficient and accurate networks for different tasks, by effectively encoding multiscale contextual information while maintaining high-resolution representations. In HR-NAS, we renovate the NAS search space as well as its searching strategy. To better encode multiscale image contexts in the search space of HR-NAS, we first carefully design a lightweight transformer, whose computational complexity can be dynamically changed with respect to different objective functions and computation budgets. To maintain high-resolution representations of the learned networks, HR-NAS adopts a multi-branch architecture that provides convolutional encoding of multiple feature resolutions, inspired by HRNet [73]. Last, we proposed an efficient fine-grained search strategy to train HR-NAS, which effectively explores the search space, and finds optimal architectures given various tasks and computation resources. As shown in Fig. 1 (a), HR-NAS is capable of achieving state-of-the-art trade-offs between performance and FLOPs for three dense prediction tasks and an image classification task, given only small computational budgets. For example, HR-NAS surpasses SqueezeNAS [63] that is specially designed for semantic segmentation while improving efficiency by 45.9%. Code is available at https://github.com/dingmyu/HR-NAS.

A multi-perspective revisit to the optimization methods of Neural Architecture Search and Hyper-parameter optimization for non-federated and federated learning environments

Deep Neural Networks are often vulnerable to adversarial attacks. Neural Architecture Search (NAS), one of the tools for developing novel deep neural architectures, demonstrates superior performance in prediction accuracy in various machine learning applications. However, the performance of a neural architecture discovered by NAS against adversarial attacks has not been sufficiently studied, especially under the regime of knowledge distillation. Given the presence of a robust teacher, we investigate if NAS would produce a robust neural architecture by inheriting robustness from the teacher. In this paper, we propose Robust Neural Architecture Search by Cross-Layer knowledge distillation (RNAS-CL), a novel NAS algorithm that improves the robustness of NAS by learning from a robust teacher through cross-layer knowledge distillation. Unlike previous knowledge distillation methods that encourage close student-teacher output only in the last layer, RNAS-CL automatically searches for the best teacher layer to supervise each student layer. Experimental results demonstrate the effectiveness of RNAS-CL and show that RNAS-CL produces compact and adversarially robust neural architectures. Our results point to new approaches for finding compact and robust neural architecture for many applications. The code of RNAS-CL is available at https://github.com/Statistical-Deep-Learning/RNAS-CL.