Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

methodology-4

AutoML

3260 papers • 126 benchmarks • 313 datasets

Automated Machine Learning (AutoML) is a general concept which covers diverse techniques for automated model learning including automatic data preprocessing, architecture search, and model selection. Source: Evaluating recommender systems for AI-driven data science (1905.09205) Source: CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in automl-4

Trend

Dataset

Best Model

Actions

Chalearn-AutoML-1

Chalearn-AutoML-1

OrdinalDataset

OrdinalDataset

Libraries

i

Use these libraries to find automl-4 models and implementations

jim-schwoebel/allie

14 papers 139

Datasets

NAS-Bench-101

MedMNIST

PMLB

NAS-Bench-1Shot1

NAS-Bench-1Shot1

CSS10

OrdinalDataset

Subtasks

Neural Architecture Search Hyperparameter Optimization Automated Feature Engineering

Most implemented papers

EfficientDet: Scalable and Efficient Object Detection

Quoc V. Le, Mingxing Tan, Ruoming Pang•Tue Nov 19 2019

This paper systematically study neural network architecture design choices for object detection and proposes a weighted bi-directional feature pyramid network (BiFPN) and a compound scaling method that uniformly scales the resolution, depth, and width for all backbone, feature network, and box/class prediction networks at the same time.

6070

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

awslabs/autogluon

5 papers 7,142

autogluon/autogluon

4 papers 7,146

rwightman/pytorch-image-models

3 papers 29,846

automl/auto-sklearn

3 papers 7,409

automl/Auto-PyTorch

3 papers 2,282

3 papers 495

PKU-DAIR/mindware

3 papers 47

mit-han-lab/once-for-all

2 papers 1,839

2 papers 1,009

DataCanvasIO/Hypernets

2 papers 261

thomas-young-2013/soln-ml

2 papers 55

thomas-young-2013/mindware

2 papers 55

Chalearn-AutoML-1

Chalearn-AutoML-1

0

EfficientNetV2: Smaller Models and Faster Training

Mingxing Tan, Quoc V. Le•Wed Mar 31 2021

This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models that were searched from the search space enriched with new ops such as Fused-MBConv.

3840 0

Auto-Keras: An Efficient Neural Architecture Search System

Haifeng Jin, Qingquan Song, Xia Hu•Tue Jun 26 2018

A novel framework enabling Bayesian optimization to guide the network morphism for efficient neural architecture search is proposed and an open-source AutoML system based on the developed framework is built, namely Auto-Keras.

888 0

MixConv: Mixed Depthwise Convolutional Kernels

Quoc V. Le, Mingxing Tan•Sun Jul 21 2019

This paper proposes a new mixed depthwise convolution (MixConv), which naturally mixes up multiple kernel sizes in a single convolution, and improves the accuracy and efficiency for existing MobileNets on both ImageNet classification and COCO object detection.

440 0

AMC: AutoML for Model Compression and Acceleration on Mobile Devices

Zhijian Liu, Song Han, Li-Jia Li, Ji Lin, Yihui He, Hanrui Wang•Fri Feb 09 2018

This paper proposes AutoML for Model Compression (AMC) which leverages reinforcement learning to efficiently sample the design space and can improve the model compression quality and achieves state-of-the-art model compression results in a fully automated way without any human efforts.

1448 0

The Machine Learning Bazaar: Harnessing the ML Ecosystem for Effective System Development

Micah J. Smith, K. Veeramachaneni, Carles Sala Cladellas, James Max Kanter•Tue May 21 2019

The Machine Learning Bazaar is introduced, a new framework for developing machine learning and automated machine learning software systems that provides solutions to a variety of data modalities and problem types and pair these pipelines with a hierarchy of AutoML strategies - Bayesian optimization and bandit learning.

53 0

AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data

Jonas W. Mueller, Alex Smola, Hang Zhang, Mu Li, Nick Erickson, Alexander Shirkov, Pedro Larroy•Thu Mar 12 2020

This work introduces 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.

832 0

TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second

Katharina Eggensperger, F. Hutter, Noah Hollmann, Samuel G. Müller•Mon Jul 04 2022

We present TabPFN, a trained Transformer that can do supervised classification for small tabular datasets in less than a second, needs no hyperparameter tuning and is competitive with state-of-the-art classification methods. TabPFN performs in-context learning (ICL), it learns to make predictions using sequences of labeled examples (x, f(x)) given in the input, without requiring further parameter updates. TabPFN is fully entailed in the weights of our network, which accepts training and test samples as a set-valued input and yields predictions for the entire test set in a single forward pass. TabPFN is a Prior-Data Fitted Network (PFN) and is trained offline once, to approximate Bayesian inference on synthetic datasets drawn from our prior. This prior incorporates ideas from causal reasoning: It entails a large space of structural causal models with a preference for simple structures. On the 18 datasets in the OpenML-CC18 suite that contain up to 1 000 training data points, up to 100 purely numerical features without missing values, and up to 10 classes, we show that our method clearly outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with up to 230$\times$ speedup. This increases to a 5 700$\times$ speedup when using a GPU. We also validate these results on an additional 67 small numerical datasets from OpenML. We provide all our code, the trained TabPFN, an interactive browser demo and a Colab notebook at https://github.com/automl/TabPFN.

548 0

MFES-HB: Efficient Hyperband with Multi-Fidelity Quality Measurements

Ce Zhang, Jinyang Gao, Yang Li, Yu Shen, Jiawei Jiang, B. Cui•Fri Dec 04 2020

Fidelity Ensemble Surrogate (MFES) is proposed, an efficient Hyperband method that is capable of utilizing both the high-fidelity and low-f fidelity measurements to accelerate the convergence of HPO tasks.

29 0

Adding a benchmark result helps the community track progress.

AutoML | State-of-the-Art