mlsanityData to 7 Oct 2026

Auto-Keras: An Efficient Neural Architecture Search System

arXiv 1806.10282 ↗First posted 27 Jun 2018cs.LG cs.AI stat.MLcited by 169

Not on the map. Why?

Abstract (arXiv)

Neural architecture search (NAS) has been proposed to automatically tune deep neural networks, but existing search algorithms, e.g., NASNet, PNAS, usually suffer from expensive computational cost. Network morphism, which keeps the functionality of a neural network while changing its neural architecture, could be helpful for NAS by enabling more efficient training during the search. In this paper, we propose a novel framework enabling Bayesian optimization to guide the network morphism for efficient neural architecture search. The framework develops a neural network kernel and a tree-structured acquisition function optimization algorithm to efficiently explores the search space. Intensive experiments on real-world benchmark datasets have been done to demonstrate the superior performance of the developed framework over the state-of-the-art methods. Moreover, we build an open-source AutoML system based on our method, namely Auto-Keras. The system runs in parallel on CPU and GPU, with an adaptive search strategy for different GPU memory limits.

Key facts. Cited by 169 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Jun 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 44; 2022: 37; 2023: 29; 2024: 25; 2025: 23; 2026: 11.

169 papers.

Sort:

By area:

  1. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 682
  2. 2025AIDE: AI-Driven Exploration in the Space of Codecited by 206
  3. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 143
  4. 2022Minimizing the Accumulated Trajectory Error to Improve Dataset Distillationcited by 142
  5. 2023Neural Architecture Search: Insights from 1000 Paperscited by 136
  6. 2021Parameter Prediction for Unseen Deep Architecturescited by 89
  7. 2023MedViT: A Robust Vision Transformer for Generalized Medical Image Classificationcited by 89
  8. 2024AutoML-Agent: A Multi-Agent LLM Framework for Full-Pipeline AutoMLcited by 84
  9. 2021NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Searchcited by 55
  10. 2022AMLB: an AutoML Benchmarkcited by 55
  11. 2025MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinementcited by 52
  12. 2024Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language Modelscited by 43
38 more
  1. 2023Sequential Subset Matching for Dataset Distillationcited by 40
  2. 2021Automated Machine Learning on Graphs: A Surveycited by 38
  3. 2023AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Riskscited by 34
  4. 2021LightAutoML: AutoML Solution for a Large Financial Services Ecosystemcited by 32
  5. 2023Transfer Learning for Bayesian Optimization: A Surveycited by 27
  6. 2021Benchmarking Multimodal AutoML for Tabular Data with Text Fieldscited by 24
  7. 20213D Medical Point Transformer: Introducing Convolution to Attention Networks for Medical Point Cloud Analysiscited by 23
  8. 2024SELA: Tree-Search Enhanced LLM Agents for Automated Machine Learningcited by 23
  9. 2021Whither AutoML? Understanding the Role of Automation in Machine Learning Workflowscited by 22
  10. 2024Transformers and Large Language Models for Efficient Intrusion Detection Systems: A Comprehensive Surveycited by 21
  11. 2021PyGlove: Symbolic Programming for Automated Machine Learningcited by 19
  12. 2023Comparison of High-Dimensional Bayesian Optimization Algorithms on BBOBcited by 18
  13. 2024Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarioscited by 18
  14. 2025AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Paperscited by 18
  15. 2022IoT Data Analytics in Dynamic Environments: From An Automated Machine Learning Perspectivecited by 15
  16. 2023Out of Context: Investigating the Bias and Fairness Concerns of "Artificial Intelligence as a Service"cited by 15
  17. 2021AutoGL: A Library for Automated Graph Learningcited by 14
  18. 2022Efficient Automated Deep Learning for Time Series Forecastingcited by 14
  19. 2024AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision Taskscited by 14
  20. 2024Automated data processing and feature engineering for deep learning and big data applications: a surveycited by 14
  21. 2021Automated Evolutionary Approach for the Design of Composite Machine Learning Pipelinescited by 13
  22. 2021Automated Deep Learning: Neural Architecture Search Is Not the Endcited by 13
  23. 2024Multi-conditioned Graph Diffusion for Neural Architecture Searchcited by 13
  24. 2022A Survey on Computationally Efficient Neural Architecture Searchcited by 12
  25. 2021Accelerating Evolutionary Neural Architecture Search via Multi-Fidelity Evaluationcited by 9
  26. 2023Fix Fairness, Don't Ruin Accuracy: Performance Aware Fairness Repair using AutoMLcited by 9
  27. 2023Dataset Distillation via Adversarial Prediction Matchingcited by 9
  28. 2022Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and Directionscited by 8
  29. 2025MedKAN: An Advanced Kolmogorov-Arnold Network for Medical Image Classificationcited by 8
  30. 2025Agentic AI framework for End-to-End Medical Data Inferencecited by 8
  31. 2021Improving Neural Networks for Time Series Forecasting using Data Augmentation and AutoMLcited by 7
  32. 2025KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problemscited by 7
  33. 2021AutoVideo: An Automated Video Action Recognition Systemcited by 6
  34. 2022TabNAS: Rejection Sampling for Neural Architecture Search on Tabular Datasetscited by 6
  35. 2022Task Selection for AutoML System Evaluationcited by 6
  36. 2023TransNAS-TSAD: Harnessing Transformers for Multi-Objective Neural Architecture Search in Time Series Anomaly Detectioncited by 6
  37. 2023Towards On-device Learning on the Edge: Ways to Select Neurons to Update under a Budget Constraintcited by 6
  38. 2023AutoXPCR: Automated Multi-Objective Model Selection for Time Series Forecastingcited by 6

50 most cited of 169 All 169 (JSON)