ActIve Learning algORithm

Active learning algorithms aim to improve the efficiency of machine learning by strategically selecting the most informative data points for labeling, minimizing the need for extensive manual annotation. Current research focuses on developing scalable algorithms for large datasets, exploring their application in diverse fields like solving partial differential equations and 6G network optimization, and improving the robustness of these methods to noisy or imbalanced data through techniques like uncertainty-based sampling and pseudo-labeling. These advancements are significant because they promise to reduce the cost and time associated with training machine learning models, leading to more efficient and effective applications across various scientific and engineering domains.

Papers

November 16, 2024

Targeting Negative Flips in Active Learning using Validation Sets
Ryan Benkert, Mohit Prabhushankar, Ghassan AlRegib
Active Learning Active Learning Algorithm ActIve Learning algORithm Negative Flip

September 11, 2024

A Scalable Algorithm for Active Learning
Youguang Chen, Zheyu Wen, George Biros
Active Learning Supervised ImageNet Synthetic Dataset Multiclass Classification Scalable Algorithm ActIve Learning algORithm

August 2, 2024

Active Learning for Neural PDE Solvers
Daniel Musekamp, Marimuthu Kalimuthu, David Holzmüller, Makoto Takamoto, Mathias Niepert
Active Learning Neural PDE Solver ActIve Learning algORithm

June 6, 2024

Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
Dake Bu, Wei Huang, Taiji Suzuki, Ji Cheng, Qingfu Zhang, Zhiqiang Xu, Hau-San Wong
Active Learning ActIve Learning algORithm Passive Learning Neural Active Learning

June 5, 2024

Active ML for 6G: Towards Efficient Data Generation, Acquisition, and Annotation
Omar Alhussein, Ning Zhang, Sami Muhaidat, Weihua Zhuang
Active Learning Data Generation Annotation Rather Channel Acquisition ActIve Learning algORithm Active Machine Learning

May 23, 2024

Smooth Pseudo-Labeling
Nikolaos Karaliolios, Hervé Le Borgne, Florian Chabot
Semi Supervised Learning Pseudo Label Limited Label ActIve Learning algORithm

December 7, 2023

Transferable Candidate Proposal with Bounded Uncertainty
Kyeongryeol Go, Kye-Hyeon Kim
Active Learning Task Transferability ActIve Learning algORithm Informative Subset

November 9, 2023

Dirichlet Active Learning
Kevin Miller, Ryan Murray
Active Learning Bayesian Approach ActIve Learning algORithm

July 25, 2023

Robust Assignment of Labels for Active Learning with Sparse and Noisy Annotations
Daniel Kałuża, Andrzej Janusz, Dominik Ślęzak
Active Learning Many Sparse Label Information Noisy Annotation Annotation System Annotation Error High Quality Annotation ActIve Learning algORithm Robust Assignment

June 7, 2023

NTKCPL: Active Learning on Top of Self-Supervised Model by Estimating True Coverage
Ziting Wen, Oscar Pizarro, Stefan Williams
Self Supervised Active Learning Estimation Task Neural Tangent Kernel Self Supervised Model Higher Coverage Rate ActIve Learning algORithm Novel Active Learning

May 21, 2023

On the Limitations of Simulating Active Learning
Katerina Margatina, Nikolaos Aletras
Active Learning Fundamental Limitation Human Annotation Human in the Loop ActIve Learning algORithm

February 14, 2023

Algorithm Selection for Deep Active Learning with Imbalanced Datasets
Jifan Zhang, Shuai Shao, Saurabh Verma, Robert Nowak
Active Learning Imbalanced Datasets Deep Active Learning Algorithm Selection ActIve Learning algORithm

November 2, 2022

Neural Active Learning on Heteroskedastic Distributions
Savya Khosla, Chew Kin Whye, Jordan T. Ash, Cyril Zhang, Kenji Kawaguchi, Alex Lamb
Active Learning ActIve Learning algORithm Efficient Machine Learning Neural Active Learning

October 2, 2022

Improved Algorithms for Neural Active Learning
Yikun Ban, Yuheng Zhang, Hanghang Tong, Arindam Banerjee, Jingrui He
Active Learning Multi Class Classification Instance Dependent Regret Improved Algorithm ActIve Learning algORithm Static Regret Neural Active Learning

January 26, 2022

Competition over data: how does data purchase affect users?
Yongchan Kwon, Antonio Ginart, James Zou
Machine Learning Raw Data User Base Competition Platform Prediction Performance ActIve Learning algORithm Data Pricing

January 19, 2022

Batch versus Sequential Active Learning for Recommender Systems
Toon De Pessemier, Sander Vanhove, Luc Martens
Active Learning Recommender System Sequential Learning ActIve Learning algORithm Batch Greenkhorn Active Learner

December 27, 2021

Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing
Renyu Zhang, Aly A. Khan, Robert L. Grossman, Yuxin Chen
Active Learning Deep Active Learning Latent Class ActIve Learning algORithm Mini Batch Consistency Batch Active Learning Decision Aware