awesome-AutoML
Curating a list of AutoML-related research, tools, projects and other resources
https://github.com/windmaple/awesome-AutoML
Last synced: 27 days ago
JSON representation
Benchmarks
LLM
Blog posts
LLM
- Efficient Multi-Objective Neural Architecture Search with Ax
- AutoML Solutions: What I Like and Don’t Like About AutoML as a Data Scientist
- Neural Architecture Search
- How we use AutoML, Multi-task learning and Multi-tower models for Pinterest Ads
- A Conversation With Quoc Le: The AI Expert Behind Google AutoML
- fast.ai: An Opinionated Introduction to AutoML and Neural Architecture Search
- Improved On-Device ML on Pixel 6, with Neural Architecture Search
- Introducing AdaNet: Fast and Flexible AutoML with Learning Guarantees
- Using Evolutionary AutoML to Discover Neural Network Architectures
- Improving Deep Learning Performance with AutoAugment
- AutoML for large scale image classification and object detection
- Using Machine Learning to Discover Neural Network Optimizers
- Using Machine Learning to Explore Neural Network Architecture
- Using Machine Learning to Explore Neural Network Architecture
Books
LLM
- AUTOML: METHODS, SYSTEMS, CHALLENGES
- Hands-On Meta Learning with Python: Meta learning using one-shot learning, MAML, Reptile, and Meta-SGD with TensorFlow - repo
- Automated Machine Learning in Action - A book that introduces autoML with AutoKreas and Keras Tuner
Commercial products
LLM
Competitions, workshops and conferences
LLM
Courses
LLM
Other curated resources on AutoML
LLM
Presentations
LLM
Research papers
Activation function Search
AutoAugment
- MetaAugment: Sample-Aware Data Augmentation Policy Learning
- SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition
- RandAugment: Practical automated data augmentation with a reduced search space
- Learning Data Augmentation Strategies for Object Detection
- Fast AutoAugment
- AutoAugment: Learning Augmentation Policies from Data
AutoDistill
AutoDropout
Automatic feature selection
- Deep Feature Synthesis: Towards Automating Data Science Endeavors
- ExploreKit: Automatic Feature Generation and Selection
AutoML survey
- Neural architecture search: a survey 深度神经网络结构搜索综述
- AutoML to Date and Beyond: Challenges and Opportunities
- On Hyperparameter Optimization of Machine Learning Algorithms: Theory and Practice
- Benchmark and Survey of Automated Machine Learning Frameworks
- AutoML: A Survey of the State-of-the-Art
- A Survey on Neural Architecture Search
- Taking Human out of Learning Applications: A Survey on Automated Machine Learning
- Neural architecture search: a survey 深度神经网络结构搜索综述
- Neural architecture search: a survey 深度神经网络结构搜索综述
- Neural architecture search: a survey 深度神经网络结构搜索综述
- A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions
Bandits
Federated Neural Architecture Search
Graph neural network
Hyperparameter optimization
- Frugal Optimization for Cost-related Hyperparameters
- Economical Hyperparameter Optimization With Blended Search Strategy
- ChaCha for Online AutoML
- Using a thousand optimization tasks to learn hyperparameter search strategies
- AutoNE: Hyperparameter Optimization for Massive Network Embedding
- Google Vizier: A Service for Black-Box Optimization
- Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
- Practical Bayesian Optimization of Machine Learning Algorithms
- Random Search for Hyper-Parameter Optimization
- OptFormer: Towards Universal Hyperparameter Optimization with Transformers
- Population Based Training of Neural Networks
- Practical Bayesian Optimization of Machine Learning Algorithms
- Random Search for Hyper-Parameter Optimization
Learning to learn/Meta-learning
- ES-MAML: Simple Hessian-Free Meta Learning
- Learning to Learn with Gradients
- On First-Order Meta-Learning Algorithms
- Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
- A sample neural attentive meta-learner
- Learning to Learn without Gradient Descent by Gradient Descent
- Learning to learn by gradient descent by gradient descent
- Learning to reinforcement learn
- RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning
LLM
- LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models
- Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search
- Archon: An Architecture Search Framework for Inference-Time Techniques - Falcon et al. 2024)
Model compression
Neural Architecture Search
- Neural Architecture Search: A Survey
- LayerNAS: Neural Architecture Search in Polynomial Complexity
- EvoPrompting: Language Models for Code-Level Neural Architecture Search
- Neural Architecture Search using Property Guided Synthesis
- Data-Free Neural Architecture Search via Recursive Label Calibration
- Searching for Efficient Neural Architectures for On-Device ML on Edge TPUs
- Resource-Constrained Neural Architecture Search on Tabular Datasets
- Searching for Fast Model Families on Datacenter Accelerators
- Towards the co-design of neural networks and accelerators
- Neural Architecture Search for Energy Efficient Always-on Audio Models
- KNAS: Green Neural Architecture Search
- Primer: Searching for Efficient Transformers for Language Modeling
- NAS-BERT: Task-Agnostic and Adaptive-Size BERT Compression with Neural Architecture Search
- AlphaNet: Improved Training of Supernets with Alpha-Divergence
- AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling
- Speedy Performance Estimation for Neural Architecture Search
- AutoFormer: Searching Transformers for Visual Recognition
- NAAS: Neural Accelerator Architecture Search
- ModularNAS: Towards Modularized and Reusable Neural Architecture Search
- BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture Search
- AutoReCon: Neural Architecture Search-based Reconstruction for Data-free Compression
- AutoSpace: Neural Architecture Search with Less Human Interference
- ReNAS:Relativistic Evaluation of Neural Architecture Search
- Zen-NAS: A Zero-Shot NAS for High-Performance Deep Image Recognition
- PyGlove: Symbolic Programming for Automated Machine Learning
- DARTS-: Robustly Stepping out of Performance Collapse Without Indicators
- NAS-DIP: Learning Deep Image Prior with Neural Architecture Search
- AttentionNAS: Spatiotemporal Attention Cell Search for Video Classification
- CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending
- Few-shot Neural Architecture Search
- Efficient Neural Architecture Search via Proximal Iterations
- Cream of the Crop: Distilling Prioritized Paths For One-Shot Neural Architecture Search
- How Does Supernet Help in Neural Architecture Search?
- CurveLane-NAS: Unifying Lane-Sensitive Architecture Search and Adaptive Point Blending
- APQ: Joint Search for Network Architecture, Pruning and Quantization Policy
- MCUNet: Tiny Deep Learning on IoT Devices
- FBNetV2: Differentiable Neural Architecture Search for Spatial and Channel Dimensions
- MobileDets: Searching for Object Detection Architectures for Mobile Accelerators
- Neural Architecture Transfer
- When NAS Meets Robustness: In Search of Robust Architectures against Adversarial Attacks
- Semi-Supervised Neural Architecture Search
- MixPath: A Unified Approach for One-shot Neural Architecture Search
- AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
- Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
- CARS: Continuous Evolution for Efficient Neural Architecture Search
- Meta-Learning of Neural Architectures for Few-Shot Learning
- Up to two billion times acceleration of scientific simulations with deep neural architecture search
- Efficient Forward Architecture Search
- Towards Oracle Knowledge Distillation with Neural Architecture Search
- Blockwisely Supervised Neural Architecture Search with Knowledge Distillation
- NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection
- Improving Keyword Spotting and Language Identification via Neural Architecture Search at Scale
- SpineNet: Learning Scale-Permuted Backbone for Recognition and Localization
- Efficient Neural Interaction Function Search for Collaborative Filtering
- Evaluating the Search Phase of Neural Architecture Search
- MixConv: Mixed Depthwise Convolutional Kernels
- Multinomial Distribution Learning for Effective Neural Architecture Search
- SNR: Sub-Network Routing for Flexible Parameter Sharing in Multi-task Learning
- PC-DARTS: Partial Channel Connections for Memory-Efficient Differentiable Architecture Search - code
- Single Path One-Shot Neural Architecture Search with Uniform Sampling
- AutoGAN: Neural Architecture Search for Generative Adversarial Networks
- MixConv: Mixed Depthwise Convolutional Kernels
- Tiny Video Networks
- AssembleNet: Searching for Multi-Stream Neural Connectivity in Video Architectures
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
- MoGA: Searching Beyond MobileNetV3 - code
- Searching for MobileNetV3
- Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
- DetNAS: Backbone Search for Object Detection
- Graph HyperNetworks for Neural Architecture Search
- Dynamic Distribution Pruning for Efficient Network Architecture Search
- FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search
- SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
- EENA: Efficient Evolution of Neural Architecture
- Single Path One-Shot Neural Architecture Search with Uniform Sampling
- InstaNAS: Instance-aware Neural Architecture Search
- ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware
- Evolutionary Neural AutoML for Deep Learning
- Fast, Accurate and Lightweight Super-Resolution with Neural Architecture Search
- The Evolved Transformer
- SNAS: Stochastic Neural Architecture Search
- NeuNetS: An Automated Synthesis Engine for Neural Network Design
- EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
- Understanding and Simplifying One-Shot Architecture Search
- Evolving Space-Time Neural Architectures for Videos
- IRLAS: Inverse Reinforcement Learning for Architecture Search
- Neural Architecture Search with Bayesian Optimisation and Optimal Transport
- Path-Level Network Transformation for Efficient Architecture Search
- BlockQNN: Efficient Block-wise Neural Network Architecture Generation
- Stochastic Adaptive Neural Architecture Search for Keyword Spotting
- Task-Driven Convolutional Recurrent Models of the Visual System
- Neural Architecture Optimization
- MnasNet: Platform-Aware Neural Architecture Search for Mobile
- MONAS: Multi-Objective Neural Architecture Search using Reinforcement Learning
- NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications
- Auto-Meta: Automated Gradient Based Meta Learner Search
- MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
- DPP-Net: Device-aware Progressive Search for Pareto-optimal Neural Architectures
- Searching Toward Pareto-Optimal Device-Aware Neural Architectures
- Differentiable Architecture Search
- Regularized Evolution for Image Classifier Architecture Search
- Efficient Architecture Search by Network Transformation