Everything about Active Learning

Everything you need about Active Learning (AL).

Not only a curated list, but also a well-structured library.

关于主动学习你需要的一切.

不仅仅包含文献列表，更是一个结构化的资料库.

(The majority of contents are presented in English.)

Papers • Introduction • Tutorials • Survey • Problem Settings • Theory

Dissertations • Code & Library • Scholars • Applications

Contributing - 加入本项目

If you find any valuable researches, please feel free to pull request or contact ruihe.cs@gmail.com to update this repository. Comments and suggestions are also very welcome!

0. Papers - 当前论文

By Origin - 按出处分类

By conference - 按会议分类：ICML / NeurIPS / ICLR / AAAI / IJCAI / ACL / CVPR / ICCV

By journal - 按期刊分类：AI / TPAMI / IJCV / JMLR

By degree - 按学位论文分类：Master / PhD

By Content - 按内容分类

Constructed in a problem-orientated approach, which is easy for users to locate and track the problem. 基于以问题为导向的分类方式，以方便读者准确定位以及跟踪相关问题。

• Taxonomy of Strategies - 主动学习技术分类
• AL Problem Settings - 问题场景
• AL in other AI Fields - 其他人工智能领域中的主动学习
• Deep AL - 深度主动学习
• Practical Considerations - 运用主动学习时的实际考虑
• AL Applications (Scientific & Industrial) - 主动学习在科学及工业界的应用

By Hot Discussions - 按热门讨论分类

• Intrinsic Issues in AL - 主动学习的内在问题
• Criticism / Discovery on Deep AL - 深度主动学习的批判和探索

1. Introduction to AL - 主动学习简介

Problem - 面向的问题: High labeling cost is common in machine learning community. Acquiring a heavy number of annotations hindering the application of machine learning methods.

Essence / Assumption - 本质 / 基础假设: Not all the instances are equally important to the desired task, so only labeling the more important instances might bring cost reduction.

When we talk about active learning, we talk about - 当我们在谈论主动学习时，我们指的是:

• an approach to reduce the annotation cost in machine learning.
• the ways to select the most important instances for the corresponding tasks.
• (in most cases) an interactive labeling manner between algorithms and oracles.
• a machine learning setting where human experts could be involved.

2. Reviews & Tutorials - 相关综述及教程

There have been several reviews / surveys / benchmarks for this topic.

Reviews / Surveys - 综述:

• Active learning: theory and applications [2001]
• Active Learning Literature Survey (Recommend to read) [2009]
• A survey on instance selection for active learning [2012]
• Active Learning: A Survey [2014]
• Active Learning Query Strategies for Classification, Regression, and Clustering: A Survey [2020, Journal of Computer Science and Technology]
• A Survey of Active Learning for Text Classification using Deep Neural Networks [2020]
• A Survey of Deep Active Learning [2020]
• Active Learning: Problem Settings and Recent Developments [2020]
• From Model-driven to Data-driven: A Survey on Active Deep Learning [2021]
• Understanding the Relationship between Interactions and Outcomes in Human-in-the-Loop Machine Learning [2021]: HIL, a wider framework.
• A Survey on Cost Types, Interaction Schemes, and Annotator Performance Models in Selection Algorithms for Active Learning in Classification [2021]
• A Comparative Survey of Deep Active Learning [2022]
• A survey on online active learning [2023]
• Human‐in‐the‐loop machine learning: a state of the art [2023, Artificial Intelligence Review]

Benchmarks - 基线:

• A Comparative Survey: Benchmarking for Pool-based Active Learning [2021, IJCAI]
• A Framework and Benchmark for Deep Batch Active Learning for Regression [2022]
• Re-Benchmarking Pool-Based Active Learning for Binary Classification [2023]
• LabelBench: A Comprehensive Framework for Benchmarking Label-Efficient Learning [2023]

Tutorials - 教程

Lecture Topic	Year	Lecturer	Occasion
Active learning and transfer learning at scale with R and Python	2018	-	KDD
Active Learning from Theory to Practice	2019	Robert Nowak & Steve Hanneke	ICML
Overview of Active Learning for Deep Learning	2021	Jacob Gildenblat	Personal Blog

3. Problem Settings - 问题场景

3.1 Basic Scenarios - 基础问题场景

Almost all the AL studies are based on the following scenarios. The difference lies in the different sources of the quired samples. The details of these scenarios could see here.

Three scenarios and corresponding tasks:

• pool-based - 基于数据池: select from a pre-collected data pool
  • pool-based classification
  • pool-based regression
• stream-based - 基于数据流: select from a steam of incoming data
  • stream-based classification
  • stream-based regression
• query synthesis - 基于数据生成: generate query instead of selecting data
  • query synthesis

3.2 Advanced Problem Settings - 复杂问题场景

There are many variants of machine learning problem settings with more advanced tasks. Under these problem settings, AL could be further applied.

Related AL Fields:

• Multi-class AL - 多分类主动学习
• Multi-label AL - 多标签主动学习
• Multi-task AL - 多任务主动学习
• Multi-domain AL - 多领域主动学习:
• Multi-view/modal AL - 多模态主动学习
• Multi-instance AL - 多样本主动学习

3.3 AL in AI Fields - 人工智能背景中的主动学习

Use AL to reduce the cost of annotation in many other AI research fields, where the tasks beyonds simple classification or regression. They either acquire different types of outputs or assume a unusual learning process. So AL algorithms should be revised/developed for these problem settings.

Utilize AL in the following fields (hot topics)：

• Computer Vision (CV)
• Natural Language Processing (NLP)
• Domain adaptation / Transfer learning
• One / Few / Zero-shot learning or Meta-Learning
• Graph Processing
• Metric learning / Pairwise comparison/Similarity learning
• Recommendation
• Reinforcement Learning
• Robotics
• Model Interpretability
• Clustering
• (Full list of fields could see here)

4. Theoretical Support - 理论支持

There have been many theoretical supports for AL. Most of them focus on finding a performance guarantee or the weakness of AL selection.

(This section has not been finished yet. 本章节当前还未完成.)

5. Practical Considerations - 运用 AL 时的考虑

Many researches of AL are built on very idealized experimental setting. When AL is used to real life scenarios, the practical situations usually do not perfectly match the assumptions in the experiments. These changes of assumptions lead issues which hinders the application of AL. In this section, the practical considerations are reviewed under different assumptions.

The considerations of: data / oracle / scale / workflow / model training cost / query & feedback types / performance metric / reliability / privacy / others

The details and the full list could see here.

6. Real-World Applications - 实际应用

AL has already been used in many real-world applications. For some reasons, the implementations in many companies are confidential. But we can still find many applications from several published papers and websites.

Basically, there are two types of applications: scientific applications & industrial applications.

7. Codes / Libraries - 代码与工具包

Name	Languages	Author	Notes
AL playground	Python(scikit-learn, keras)	Google	Abandoned
modAL	Python(scikit-learn)	Tivadar Danka	Keep updating
libact	Python(scikit-learn)	NTU(Hsuan-Tien Lin group)
ALiPy	Python(scikit-learn)	NUAA(Shengjun Huang)	Include MLAL
pytorch_active_learning	Python(pytorch)	Robert Monarch	Keep updating & include active transfer learning
DeepAL	Python(scikit-learn, pytorch)	Kuan-Hao Huang	Keep updating & deep neural networks
BaaL	Python(scikit-learn, pytorch)	ElementAI	Keep updating & bayesian active learning
lrtc	Python(scikit-learn, tensorflow)	IBM	Text classification
Small-text	Python(scikit-learn, pytorch)	Christopher Schröder	Text classification
DeepCore	Python(scikit-learn, pytorch)	Guo et al.	In the coreset selection formulation
PyRelationAL: A Library for Active Learning Research and Development	Python(scikit-learn, pytorch)	Scherer et al.
DeepAL+	Python(scikit-learn, pytorch)	Zhan	An extension for DeepAL
ALaaS	Python(scikit-learn)	A*STAR & NTU	Use the stage-level parallellism for AL.

8. Scholars / Groups - 著名学者及团队

We also list several scholars who are currently heavily contributing to this research direction.

1. Hsuan-Tien Lin
2. Shengjun Huang (NUAA)
3. Dongrui Wu (Active Learning for Regression)
4. Raymond Mooney
5. Yuchen Guo
6. Steve Hanneke

Several young researchers who provides valuable insights for AL:

• Jamshid Sourati [University of Chicago]: Deep neural networks.
• Stefano Teso [University of Trento]: Interactive learning & Human-in-the-loops.
• Xueyin Zhan [City University of Hong Kong]: Provide several invaluable comparative surveys.
• Katerina Margatina [University of Sheffield]: Provide several good insights, analysis and applications for AL.