Neural Architecture Search

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

26 leaderboard tables shown for this task, 26 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted. 10 shown of 26 until expanded.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

27 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

1 subtask in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 859 papers with code (1,915 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Proximal Policy Optimization Algorithms
  20 Jul 2017 188 repositories listed Syntology ran 99 of 176 samples · 77 unverified · 94 pointer-only (licence)
  We propose a new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using…
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
  28 May 2019 144 repositories listed Syntology ran 171 of 302 samples · 131 unverified · 112 pointer-only (licence)
  Convolutional Neural Networks (ConvNets) are commonly developed at a fixed resource budget, and then scaled up for better accuracy if more resources are available.
• Searching for MobileNetV3
  6 May 2019 67 repositories listed Syntology ran 58 of 105 samples · 47 unverified · 46 pointer-only (licence)
  We achieve new state of the art results for mobile classification, detection and segmentation.
• DARTS: Differentiable Architecture Search
  24 Jun 2018 59 repositories listed Syntology ran 66 of 156 samples · 90 unverified · 48 pointer-only (licence)
  This paper addresses the scalability challenge of architecture search by formulating the task in a differentiable manner.
• MnasNet: Platform-Aware Neural Architecture Search for Mobile
  31 Jul 2018 29 repositories listed Syntology ran 2 of 6 samples · 4 unverified · 2 pointer-only (licence)
  In this paper, we propose an automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good…
• Efficient Neural Architecture Search via Parameter Sharing
  9 Feb 2018 28 repositories listed Syntology ran 18 of 38 samples · 20 unverified · 25 pointer-only (licence)
  The controller is trained with policy gradient to select a subgraph that maximizes the expected reward on the validation set.
• EfficientNetV2: Smaller Models and Faster Training
  1 Apr 2021 26 repositories listed Syntology ran 41 of 79 samples · 38 unverified · 10 pointer-only (licence)
  By pretraining on the same ImageNet21k, our EfficientNetV2 achieves 87.
• ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
  2 Dec 2018 23 repositories listed Syntology ran 5 of 27 samples · 22 unverified
  We address the high memory consumption issue of differentiable NAS and reduce the computational cost (GPU hours and GPU memory) to the same level of regular training while still allowing a large candidate set.
• Progressive Neural Architecture Search
  2 Dec 2017 18 repositories listed Syntology ran 3 of 3 samples · 0 unverified · 2 pointer-only (licence)
  We propose a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms.
• Learning Transferable Architectures for Scalable Image Recognition
  21 Jul 2017 17 repositories listed Syntology ran 0 of 1 samples · 1 unverified · 1 pointer-only (licence)
  In our experiments, we search for the best convolutional layer (or "cell") on the CIFAR-10 dataset and then apply this cell to the ImageNet dataset by stacking together more copies of this cell, each with their own…
• SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
  10 Dec 2019 13 repositories listed
  We propose SpineNet, a backbone with scale-permuted intermediate features and cross-scale connections that is learned on an object detection task by Neural Architecture Search.
• Auto-Keras: An Efficient Neural Architecture Search System
  27 Jun 2018 13 repositories listed Syntology ran 3 of 6 samples · 3 unverified
  In this paper, we propose a novel framework enabling Bayesian optimization to guide the network morphism for efficient neural architecture search.
• Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
  10 Jan 2019 12 repositories listed Syntology ran 1 of 4 samples · 3 unverified · 1 pointer-only (licence)
  Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space.
• AMC: AutoML for Model Compression and Acceleration on Mobile Devices
  10 Feb 2018 12 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 1 pointer-only (licence)
  Model compression is a critical technique to efficiently deploy neural network models on mobile devices which have limited computation resources and tight power budgets.
• Learning Efficient Convolutional Networks through Network Slimming
  22 Aug 2017 12 repositories listed
  For VGGNet, a multi-pass version of network slimming gives a 20x reduction in model size and a 5x reduction in computing operations.
• Neural Architecture Search with Reinforcement Learning
  5 Nov 2016 12 repositories listed Syntology ran 5 of 5 samples · 0 unverified · 3 pointer-only (licence)
  Our cell achieves a test set perplexity of 62.
• Once-for-All: Train One Network and Specialize it for Efficient Deployment
  26 Aug 2019 10 repositories listed Syntology ran 4 of 34 samples · 30 unverified
  On diverse edge devices, OFA consistently outperforms state-of-the-art (SOTA) NAS methods (up to 4.
• AutoSlim: Towards One-Shot Architecture Search for Channel Numbers
  27 Mar 2019 10 repositories listed
  Notably, by setting optimized channel numbers, our AutoSlim-MobileNet-v2 at 305M FLOPs achieves 74.
• BAM: Bottleneck Attention Module
  17 Jul 2018 10 repositories listed
  In this work, we focus on the effect of attention in general deep neural networks.
• ISyNet: Convolutional Neural Networks design for AI accelerator
  4 Sep 2021 9 repositories listed
  To address this problem we propose a measure of hardware efficiency of neural architecture search space - matrix efficiency measure (MEM); a search space comprising of hardware-efficient operations; a latency-aware…
• Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours
  5 Apr 2019 9 repositories listed Syntology ran 1 of 16 samples · 15 unverified
  Can we automatically design a Convolutional Network (ConvNet) with the highest image classification accuracy under the runtime constraint of a mobile device?
• Exploring Randomly Wired Neural Networks for Image Recognition
  2 Apr 2019 9 repositories listed Syntology ran 0 of 31 samples · 31 unverified
  In this paper, we explore a more diverse set of connectivity patterns through the lens of randomly wired neural networks.
• PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search
  12 Jul 2019 8 repositories listed Syntology ran 1 of 11 samples · 10 unverified · 1 pointer-only (licence)
  Differentiable architecture search (DARTS) provided a fast solution in finding effective network architectures, but suffered from large memory and computing overheads in jointly training a super-network and searching…
• NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
  16 Apr 2019 8 repositories listed
  Here we aim to learn a better architecture of feature pyramid network for object detection.
• MobileNetV4 -- Universal Models for the Mobile Ecosystem
  16 Apr 2024 7 repositories listed Syntology ran 6 of 13 samples · 7 unverified · 1 pointer-only (licence)
  We present the latest generation of MobileNets, known as MobileNetV4 (MNv4), featuring universally efficient architecture designs for mobile devices.
• ReNAS: Relativistic Evaluation of Neural Architecture Search
  19 Jun 2021 7 repositories listed
  An effective and efficient architecture performance evaluation scheme is essential for the success of Neural Architecture Search (NAS).
• AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data
  13 Mar 2020 7 repositories listed Syntology ran 0 of 11 samples · 11 unverified
  We introduce AutoGluon-Tabular, an open-source AutoML framework that requires only a single line of Python to train highly accurate machine learning models on an unprocessed tabular dataset such as a CSV file.
• Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
  31 Jul 2020 6 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely.
• SP-NAS: Serial-to-Parallel Backbone Search for Object Detection
  1 Jun 2020 6 repositories listed
  Advanced object detectors usually adopt a backbone network designed and pretrained by ImageNet classification.
• HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass Lens
  29 May 2020 6 repositories listed
  To achieve an extremely fast NAS while preserving the high accuracy, we propose to identify the vital blocks and make them the priority in the architecture search.

Syntology lines on 21 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.