mlsanityData to 7 Oct 2026

Multi-Agent Automated Machine Learning

arXiv 2210.09084 ↗First posted 17 Oct 2022cs.LG cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

In this paper, we propose multi-agent automated machine learning (MA2ML) with the aim to effectively handle joint optimization of modules in automated machine learning (AutoML). MA2ML takes each machine learning module, such as data augmentation (AUG), neural architecture search (NAS), or hyper-parameters (HPO), as an agent and the final performance as the reward, to formulate a multi-agent reinforcement learning problem. MA2ML explicitly assigns credit to each agent according to its marginal contribution to enhance cooperation among modules, and incorporates off-policy learning to improve search efficiency. Theoretically, MA2ML guarantees monotonic improvement of joint optimization. Extensive experiments show that MA2ML yields the state-of-the-art top-1 accuracy on ImageNet under constraints of computational cost, e.g., 79.7%/80.5% with FLOPs fewer than 600M/800M. Extensive ablation studies verify the benefits of credit assignment and off-policy learning of MA2ML.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 43 of its 56 references that are in the map. First posted on arXiv 17 Oct 2022.

Builds on

43 of 56 references.

References · 43

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  3. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  7. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  8. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  9. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,097
  10. 2016Deep Networks with Stochastic Depthcited by 973
  11. 2020Designing Network Design Spacescited by 954
  12. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 937
31 more
  1. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  2. 2018Efficient Neural Architecture Search via Parameter Sharingcited by 831
  3. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  4. 2017Counterfactual Multi-Agent Policy Gradientscited by 733
  5. 2015Gradient-based Hyperparameter Optimization through Reversible Learningcited by 357
  6. 2017Large-Scale Evolution of Image Classifierscited by 348
  7. 2019Optimizing Millions of Hyperparameters by Implicit Differentiationcited by 303
  8. 2019PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Searchcited by 265
  9. 2019Fast AutoAugmentcited by 243
  10. 2016Hyperparameter optimization with approximate gradientcited by 231
  11. 2018Truncated Back-propagation for Bilevel Optimizationcited by 187
  12. 2019Population Based Augmentation: Efficient Learning of Augmentation Policy Schedulescited by 153
  13. 2017Multi-fidelity Bayesian Optimisation with Continuous Approximationscited by 120
  14. 2019Adversarial AutoAugmentcited by 111
  15. 2019Faster AutoAugment: Learning Augmentation Strategies using Backpropagationcited by 96
  16. 2019Practical Multi-fidelity Bayesian Optimization for Hyperparameter Tuningcited by 91
  17. 2020DARTS-: Robustly Stepping out of Performance Collapse Without Indicatorscited by 81
  18. 2019CARS: Continuous Evolution for Efficient Neural Architecture Searchcited by 79
  19. 2019Tabular Benchmarks for Joint Architecture and Hyperparameter Optimizationcited by 57
  20. 2020MiLeNAS: Efficient Neural Architecture Search via Mixed-Level Reformulationcited by 56
  21. 2018Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Searchcited by 38
  22. 2020ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Codingcited by 36
  23. 2020Improving Auto-Augment via Augmentation-Wise Weight Sharingcited by 28
  24. 2022Shapley-NAS: Discovering Operation Contribution for Neural Architecture Searchcited by 23
  25. 2021Divergence-Regularized Multi-Agent Actor-Criticcited by 15
  26. 2018Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networkscited by 10
  27. 2021DHA: End-to-End Joint Optimization of Data Augmentation Policy, Hyper-parameter and Architecturecited by 6
  28. 2021L2NAS: Learning to Optimize Neural Architectures via Continuous-Action Reinforcement Learningcited by 6
  29. 2021BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rulecited by 5
  30. 2020Joint Search of Data Augmentation Policies and Network Architecturescited by 4
  31. 2021DAAS: Differentiable Architecture and Augmentation Policy Searchcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 1.

3 papers.

  1. 2025Optimas: Optimizing Compound AI Systems with Globally Aligned Local Rewardscited by 23
  2. 2024FlickerFusion: Intra-trajectory Domain Generalizing Multi-Agent RLcited by 0
  3. 2026A Framework for Assessing AI Agent Decisions and Outcomes in AutoML Pipelinescited by 0