Awesome Active Learning

A list of resources related to Active learning in machine learning.

Tutorials

• [Book] Active Learning. Burr Settles. (CMU, 2012)
• [Seminar] Active Learning from Theory to Practice. Steve Hanneke, Robert Nowak. (ICML, 2019)
• [Seminar] Bandits, Active Learning, Bayesian RL and Global Optimization.Marc Toussaint. (MLSS, 2013)
• [Lecture. 24] 36-708 Statistical Methods for Machine Learning. (CMU, 2015)

Papers

Pool-Based Sampling

Singleton

• Entropic Open-Set Active Learning. Bardia Safaei, Vibashan VS, Celso M. de Melo, Vishal M. Patel. (AAAI, 2024)

• Class-Balanced Active Learning for Image Classification. Javad Zolfaghari Bengar, Joost van de Weijer, Laura Lopez Fuentes, Bogdan Raducanu. (WACV, 2022)

• Influence Selection for Active Learning. Zhuoming Liu, Hao Ding, Huaping Zhong, Weijia Li, Jifeng Dai, Conghui He. (ICCV, 2021)

• A Variance Maximization Criterion for Active Learning. Yazhou Yang, Marco Loog. (Pattern Recognition, 2018)

• The power of ensembles for active learning in image classification. William H. Beluch, Tim Genewein, Andreas Nurnberger, Jan M. Kohler. (CVPR, 2018)

• Learning Algorithms for Active Learning. Philip Bachman, Alessandro Sordoni, Adam Trischler. (ICML, 2017)

• Beyond Disagreement-based Agnostic Active Learning. Chicheng Zhang, Kamalika Chaudhuri. (NIPS, 2014)

• Bayesian Optimal Active Search and Surveying. Roman Garnett, Yaumna Krishnamurthy, Xuehan Xiong, Jeff Schneider, Richard Mann. (ICML, 2012)

• Bayesian Active Learning for Classification and Prefernce Learning. Neil Houlsby, Ferenc Huszár, Zoubin Ghahramani, Máté Lengyel. (CoRR, 2011)

• Active Learning using On-line Algorithms. Chris Mesterharm, Michael J. Pazzani. (KDD, 2011)

• Active Learning from Crowds. Yan Yan, R ́omer Rosales, Glenn Fung, Jennifer G. Dy. (ICML, 2011)

• Hierarchical Sampling for Active Learning. Sanjoy Dasgupta, Daniel Hsu (ICML, 2008)

Batch/Batch-like

• Stochastic Batch Acquisition for Deep Active Learning. Andreas Kirsch, Sebastian Farquhar, Parmida Atighehchian, Andrew Jesson, Frederic Branchaud-Charron, Yarin Gal. (arXiv, 2021)
• LADA: Look-Ahead Data Acquisition via Augmentation for Deep Active Learning. Yooon-Yeong Kim, Kyungwoo Song, JoonHo Jang, Il-chul Moon. (NeurIPS, 2021)
• Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision. Denis Gudovskiy, Alec Hodgkinson, Takuya Yamaguchi, Sotaro Tsukizawa. (CVPR, 2020)
• Deep Batch Active Learning By Diverse, Uncertain Gradient Lower Bound. Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal. (ICLR, 2020)
• Bayesian Generative Active Deep Learning. Toan Tran, Thanh-Toan Do, Ian Reid, Gustavo Carneiro. (ICML, 2019)
• Learning Loss for Active Learning. Donggeun Yoo, In So Kweon. (CVPR, 2019)
• Variational Adversarial Active Learning. Samarth Sinha, Sayna Ebrahimi, Trevor Darrell. (arXiv, 2019)
• Integrating Bayesian and Discriminative Sparse Kernel Machines for Multi-class Active Learning. Weishi Shi, Qi Yu. (NeurIPS, 2019)
• Rapid Performance Gain through Active Model Reuse. Feng Shi, Yu-Feng Li. (IJCAI, 2019)
• Active Semi-Supervised Learning Using Sampling Theory for Graph Signals. Akshay Gadde, Aamir Anis, Antonio Ortega. (KDD, 2014)
• Active Learning for Multi-Objective Optimization. Marcela Zuluaga, Andreas Krause, Guillaume Sergent, Markus P{''u}schel (ICML, 2013)
• Querying Discriminative and Representative Samples forBatch Mode Active Learning. Zheng Wang, Jieping Ye. (KDD, 2013)
• Near-optimal Batch Mode Active Learning and Adaptive Submodular Optimization. Yuxin Chen, Andreas Krause. (ICML, 2013)
• Active Learning for Probabilistic Hypotheses Usingthe Maximum Gibbs Error Criterion, Nguyen Viet Cuong, Wee Sun Lee, Nan Ye, Kian Ming A. Chai, Hai Leong Chieu. (NIPS, 2013)
• Batch Active Learning via Coordinated Matching. Javad Azimi, Alan Fern, Xiaoli Z. Fern, Glencora Borradaile, Brent Heeringa. (ICML, 2012)
• Ask me better questions: active learning queries based on rule induction. Parisa Rashidi, Diane J. Cook. (KDD, 2011)
• Active Instance Sampling via Matrix Partition. Yuhong Guo. (NIPS 2010)
• Discriminative Batch Mode Active Learning. Charles X. Ling, Jun Du. (NIPS, 2007)

Stream-Based Selective Sampling

• Online Active Learning of Reject Option Classifiers. Kulin Shah, Naresh Manwani. (AAAI, 2020)
• Active Learning from Peers. Keerthiram Murugesan, Jaime Carbonell. (NIPS, 2017)
• An Analysis of Active Learning Strategies for Sequence Labeling Tasks. Burr Settles, Mark Craven. (EMNLP, 2008)
• Improving Generalization with Active Learning, DAVID COHN, LES ATLAS, RICHARD LADNER. (Machine Learning, 1994)

Membership Query Synthesize

• Active Learning via Membership Query Synthesisfor Semi-supervised Sentence Classification. Raphael Schumann, Ines Rehbein. (CoNLL, 2019)
• Active Learning with Direct Query Construction, Yuhong Guo, Dale Schuurmans. (KDD, 2008)

Meta-Learning

• Meta-Learning for Batch Mode Active Learning. Sachin Ravi, Hugo Larochelle. (ICLR-WS, 2018)
• Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning. Kunkun Pang, Mingzhi Dong, Yang Wu, Timothy Hospedales. (ICML-WS, 2018)
• Learning Active Learning from Data. Ksenia Konyushkova, Sznitman Raphael. (NIPS, 2017)

Tasks

Object Detection

• Plug and Play Active Learning for Object Detection. Chenhongyi Yang, Lichao Huang and Elliot J. Crowley. (CVPR, 2024)
• Not All Labels Are Equal:Rationalizing The Labeling Costs for Training Object Detection. Ismail Elezi, Zhiding Yu, Anima Anandkumar, Laura Leal-Taixe, Jose M. Alvarez. (CVPR, 2022)
• Multiple Instance Active Learning for Object Detection. Tianning Yuan, Fang Wan, Mengying Fu, Jianzhuang Liu, Songcen Xu, Xiangyang Ji and Qixiang Ye. (CVPR, 2021)

Coreset

• Coresets for Robust Training of Neural Networks against Noisy Labels. Baharan Mirzasoleiman, Kaidi Cao, Jure Leskovec (NeurIPS, 2020)
• Coresets for Data-efficient Training of Machine Learning Models. Baharan Mirzasoleiman, Jeff Bilmes, Jure Leskovec (ICML, 2020)
• Active Learning for Convolutional Neural Networks: A Core-Set Approach Ozan Sener, Silvio Savarese (ICLR, 2018)

Theory

• On Statistical Bias In Active Learning: How and When To Fix It. Sebastian Farquhar, Yarin Gal, Tom Rainforth (ICLR, 2021 spotlight)
• Active Learning from Imperfect Labelers. Songbai Yan, Kamalika Chaudhuri, Tara Javidi (NIPS, 2016)

Critics

• Toward Realistic Evaluation of Deep Active Learning Algorithms in Image Classification. Carsten T. Lüth, Till J. Bungert, Lukas Klein, Paul F. Jaeger. (arXiv, 2023)
• Towards Robust and Reproducible Active Learning Using Neural Networks. Prateek Munjal, Nasir Hayaat, Nunawar Hayat, Jamshid Sourati, Shadab Khan. (arXiv, 2020)
• Parting with Illusions about Deep Active Learning. Sudhanshu Mittal, Maxim Tatarchenko. Ozgu ̈n Cicek, Thomas Brox. (arXiv, 2019)

Related

Data Valuation

• Dataset Condensation with Gradient Matching. Bo Zhao, Konda Reddy Mopuri, Hakan Bilen. (ICLR, 2021 Oral)
• Data Valuation Using Reinforcement Learning. Jinsung Yoon, Sercan O. Arik, Tomas Pfister. (ICML 2020)