mlsanityData to 14 Oct 2026

SGAS: Sequential Greedy Architecture Search

arXiv 1912.00195 ↗First posted 30 Nov 2019cs.LG cs.CV stat.MLcited by 69

Not on the map. Why?

Abstract (arXiv)

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 operations in a greedy fashion. We apply SGAS to search architectures for Convolutional Neural Networks (CNN) and Graph Convolutional Networks (GCN). Extensive experiments show that SGAS is able to find state-of-the-art architectures for tasks such as image classification, point cloud classification and node classification in protein-protein interaction graphs with minimal computational cost. Please visit https://www.deepgcns.org/auto/sgas for more information about SGAS.

Key facts. Cited by 69 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Nov 2019.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 25; 2022: 22; 2023: 14; 2024: 3; 2025: 5.

69 papers.

Sort:

By area:

  1. 2021Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspectivecited by 169
  2. 2023Neural Architecture Search: Insights from 1000 Paperscited by 139
  3. 2023A Comprehensive Survey of Dataset Distillationcited by 115
  4. 2021Rethinking Architecture Selection in Differentiable NAScited by 92
  5. 2021Parameter Prediction for Unseen Deep Architecturescited by 89
  6. 2021Automated Machine Learning on Graphs: A Surveycited by 39
  7. 2021MAAS: Multi-modal Assignation for Active Speaker Detectioncited by 36
  8. 2023Visual Tuningcited by 34
  9. 2021KNAS: Green Neural Architecture Searchcited by 33
  10. 2021Prioritized Architecture Sampling with Monto-Carlo Tree Searchcited by 32
  11. 2022Enable Deep Learning on Mobile Devices: Methods, Systems, and Applicationscited by 32
  12. 2023Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Modelscited by 31
38 more
  1. 2021Rethinking Graph Neural Architecture Search from Message-passingcited by 26
  2. 2022End-to-End Active Speaker Detectioncited by 25
  3. 2022Generalizing Few-Shot NAS with Gradient Matchingcited by 25
  4. 2022Shapley-NAS: Discovering Operation Contribution for Neural Architecture Searchcited by 23
  5. 2021Meta Navigator: Search for a Good Adaptation Policy for Few-shot Learningcited by 19
  6. 2021Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspectivecited by 19
  7. 2021ZARTS: On Zero-order Optimization for Neural Architecture Searchcited by 18
  8. 2022Demystifying the Neural Tangent Kernel from a Practical Perspective: Can it be trusted for Neural Architecture Search without training?cited by 18
  9. 2022Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networkscited by 18
  10. 2022PVNAS: 3D Neural Architecture Search with Point-Voxel Convolutioncited by 16
  11. 2021Accelerating Neural Architecture Search via Proxy Datacited by 14
  12. 2021Reconsidering CO2 emissions from Computer Visioncited by 9
  13. 2021Zero-Cost Operation Scoring in Differentiable Architecture Searchcited by 9
  14. 2022Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directionscited by 9
  15. 2022MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixingcited by 9
  16. 2022Efficient Joint-Dimensional Search with Solution Space Regularization for Real-Time Semantic Segmentationcited by 9
  17. 2021Understanding and Accelerating Neural Architecture Search with Training-Free and Theory-Grounded Metricscited by 7
  18. 2021On the Security Risks of AutoMLcited by 7
  19. 2021Effective and Fast: A Novel Sequential Single Path Search for Mixed-Precision Quantizationcited by 6
  20. 2022Automatic Relation-aware Graph Network Proliferationcited by 6
  21. 2023Improving Differentiable Architecture Search via Self-Distillationcited by 6
  22. 2023Robust Neural Architecture Searchcited by 5
  23. 2023IS-DARTS: Stabilizing DARTS through Precise Measurement on Candidate Importancecited by 5
  24. 2021Differentiable Architecture Search for Reinforcement Learningcited by 4
  25. 2022Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysiscited by 4
  26. 2022LidarNAS: Unifying and Searching Neural Architectures for 3D Point Cloudscited by 4
  27. 2022Pareto-aware Neural Architecture Generation for Diverse Computational Budgetscited by 4
  28. 2023Neural Fine-Tuning Search for Few-Shot Learningcited by 4
  29. 2021Coarse-to-Fine Searching for Efficient Generative Adversarial Networkscited by 3
  30. 2021Differentiable Convolution Search for Point Cloud Processingcited by 3
  31. 2022When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Searchcited by 3
  32. 2022FEATHERS: Federated Architecture and Hyperparameter Searchcited by 3
  33. 2023Operation-level Progressive Differentiable Architecture Searchcited by 3
  34. 2023Search-time Efficient Device Constraints-Aware Neural Architecture Searchcited by 3
  35. 2021CONet: Channel Optimization for Convolutional Neural Networkscited by 2
  36. 2021Edge-featured Graph Neural Architecture Searchcited by 2
  37. 2021Full-attention based Neural Architecture Search using Context Auto-regressioncited by 2
  38. 2022A Survey of Supernet Optimization and its Applications: Spatial and Temporal Optimization for Neural Architecture Searchcited by 2

50 most cited of 69 All 69 (JSON)