Yejining/Survey

Survey on AutoML

Survey

This repository is for organizing papers on AutoML

Survey on NAS

0. Unknown

• 2015 An Empirical Exploration of Recurrent Network Architectures
• 2015 Efficient and Robust Automated Machine Learning
• 2017 Convolutional Neural Fabrics
• 2017 LSTM A Search Space Odyssey
• 2018 Hyperband A Novel Bandit-Based Approach to Hyperparameter Optimization
• 2018 Relational Autoencoder for Feature Extraction
• 2019 MnasNet Platform-Aware Neural Architecture Search for Mobile

1. Survey

• 2019 Neural Architecture Search A Survey
• 2019 Towards Automated Machine Learning Evaluation and Comparison of AutoML Approaches and Tools
• 2020 AutoML A Survey of the State-of-the-Art

2. Well-Designed Operations

• 2016 Deep Residual Learning for Image Recognition
• 2016 Multi-Scale Context Aggregation by Dilated Convolutions
• 2017 Xception Deep Learning with Depthwise Separable Convolutions
• 2019 Squeeze-and-Excitation Networks

3. Cell-Based Structure

• 2015 BinaryConnect Training Deep Neural Networks with Binary Weights during Propagations
• 2017 Large-Scale Evolution of Image Classifiers
• 2018 Efficient Neural Architecture Search via Parameter Sharing
• 2019 ProxylessNAS Direct Neural Architecture Search on Target Task and Hardware

4. Progressive Structure

• 2018 Progressive Neural Architecture Searchpdf
• 2019 Progressive Differentiable Architecture Search Bridging the Depth Gap between Search and Evaluation

5. Morphism-Based Structure

• 2016 Net2Net Accelerating Learning via Knowledge Transfer
• 2016 Network Morphism
• 2017 Modularized Morphing of Neural Networks
• 2019 Auto-Keras An Efficient Neural Architecture Search System
• 2019 Deep Neural Network Architecture Search Using Network Morphism
• 2019 Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution
• 2019 EfficientNet Rethinking Model Scaling for Convolutional Neural Networks

6. Reinforcement Learning

• 2017 Designing Neural Network Architectures using Reinforcement Learning
• 2017 Efficient Architecture Search by Network Transformation
• 2017 Neural Architecture Search with Reinforcement Learning
• 2018 Learning Transferable Architectures for Scalable Image Recognition
• 2018 Practical Block-wise Neural Network Architecture Generation

7. Evolution Method

• 2017 Genetic CNN
• 2018 Hierarchical Representations for Efficient Architecture Search
• 2019 Regularized Evolution for Image Classifier Architecture Search

8. Gradient Based

• 2018 Differentiable Neural Network Architecture Search
• 2019 DARTS Differentiable Architecture Search

9. Random Search

• 2017 Google Vizier A Service for Black-Box Optimization

10. Semantic Segmentation

• 2015 U-Net Convolutional Networks for Biomedical Image Segmentation
• 2018 Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
• 2019 Auto-DeepLab Hierarchical Neural Architecture Search for Semantic Image Segmentation
• 2019 NAS-Unet Neural Architecture Search for Medical Image Segmentation

Survey for Spatiotemporal dataset for AutoML

Recently I am trying to read

• AUTOML: METHODS, SYSTEMS, CHALLENGES (NEW BOOK)

0. Unknown

• 2011 Follow-the-Regularized-Leader and Mirror Descent: Equivalence Theorems and L1 Regularization
• 2016 Architectural Style Classification of Mexican Buildings using Deep Convolutional Neural Networks and Sparse Features

1. Spatiotemporal - in dataset perspective

• 2015 Cultural Event Recognition with Visual Convnets and Temporal Models
• 2017 Gated Spatio and Temporal Convolutional Neural Network for Activity Recognition: Towards Gated Multimodal Deep Learning
• 2018 Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction
• 2018 TICNN: A Hierarchical Deep Learning Framework for Still Image Action Recognition using Temporal Image Prediction
• 2020 Predicting Clustered Weather Patterns: A Test Case for Applications of Convolutional Neural Networks to Spatio-Temporal Climate Data

2. Spatiotemporal - former studies

• 2015 Detecting the Influence of Spreading in Social Networks with Excitable Sensor Networks
• 2016 Dnn-based prediction model for spatio-temporal data
• 2018 Diffusion Convolutional Recurrent Neural Network: Data-Driven Traffic Forecasting
• 2018 DeepCrime: Attentive Hierarchical Recurrent Networks for Crime Prediction
• 2018 Hetero-ConvLSTM: A Deep Learning Approach to Traffic Accident Prediction on Heterogeneous Spatio-Temporal Data
• 2019 Deep Leaning for Spatio-Temporal Data Mining: A Survey
• 2019 Deep Learning Resolves Representative Movement Patterns in a Marine Predator Species
• 2020 Deep Learning Approach on Information Diffusion in Heterogeneous Networks
• 2017 Deep Learning for Real Time Crime Forecasting

3. AutoML Projects on Image Classification or Object Detection

• MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
• Progressive Neural Architecture Search

4. Feature Engineering / Survey on Feature

• 2014 A Survey on Feature Selection Methods
• 2019 Feature Selection and Feature Extraction in Pattern Analysis: A Literature Review
• 2019 Feature Selection and Extraction in Spatiotemporal Traffic Forecasting: A Systematic Literature Riview

5. HPO

• 2015 Deep Feature Synthesis: Towards Automating Data Science Endeavors
• 2017 Google Vizier: A Service for Black-Box Optimization
• 2018 Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
• 2018 BOHB: Robust and Efficient Hyperparameter Optimization at Scale
• 2018 DeepHyper: Asynchronous Hyperparameter Search for Deep Neural Networks
• 2018 Towards Automated Deep Learning: Efficient Joint Neural Architecture and Hyperparameter Search

6. AutoML

• AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data