Active Learning Framework

Active learning frameworks aim to optimize the process of training machine learning models by strategically selecting the most informative data points for labeling, thereby minimizing annotation costs and maximizing model performance. Current research focuses on integrating active learning with various model architectures, including graph neural networks, large language models, and recurrent neural networks, and employing algorithms like Bayesian optimization and reinforcement learning to guide data selection. These frameworks are proving valuable across diverse applications, from text classification and image recognition to drug discovery and industrial fault detection, by significantly reducing the need for extensive labeled datasets. The resulting cost savings and improved efficiency are driving significant advancements in various fields.

Papers

October 17, 2024

An Active Learning Framework for Inclusive Generation by Large Language Models
Sabit Hassan, Anthony Sicilia, Malihe Alikhani
Knowledge Distillation Training Data Full Model Active Learning Large Language Active Learning Framework Learner Model

June 17, 2024

May 20, 2024

An Active Learning Framework with a Class Balancing Strategy for Time Series Classification
Shemonto Das
Active Learning Time Series Classification Industrial Anomaly Detection Active Learning Framework

February 15, 2024

Class-Balanced and Reinforced Active Learning on Graphs
Chengcheng Yu, Jiapeng Zhu, Xiang Li
Graph Drawing Active Learning Graph Classification Active Learning Framework

February 5, 2024

ActiveAnno3D -- An Active Learning Framework for Multi-Modal 3D Object Detection
Ahmed Ghita, Bjørk Antoniussen, Walter Zimmer, Ross Greer, Christian Creß, Andreas Møgelmose, Mohan M. Trivedi, Alois C. Knoll
Active Learning 3D Object Detection Active Learning Framework INtersection Dataset

January 30, 2024

ActDroid: An active learning framework for Android malware detection
Ali Muzaffar, Hani Ragab Hassen, Hind Zantout, Michael A Lones
Active Learning Concept Drift Malware Detection Active Learning Framework Malware Attack Android Malware

December 29, 2023

Quantifying Policy Administration Cost in an Active Learning Framework
Si Zhang, Philip W. L. Fong
Based Policy Active Learning Framework Policy Search Access Control Heuristic Policy

December 18, 2023

Generalized Category Discovery with Large Language Models in the Loop
Wenbin An, Wenkai Shi, Feng Tian, Haonan Lin, QianYing Wang, Yaqiang Wu, Mingxiang Cai, Luyan Wang, Yan Chen, Haiping Zhu, Ping Chen
Contrastive Learning Generalized Category Discovery Active Learning Framework Clustering Friendly Representation

December 13, 2023

Fair Active Learning in Low-Data Regimes
Romain Camilleri, Andrew Wagenmaker, Jamie Morgenstern, Lalit Jain, Kevin Jamieson
Active Learning Fairness Constraint Active Learning Framework Chaotic Regime FAir Classifier Fairness Verification

November 30, 2023

Towards Comparable Active Learning
Thorben Werner, Johannes Burchert, Lars Schmidt-Thieme
Active Learning Active Learning Framework Comparative Learning

November 18, 2023

Active Prompt Learning in Vision Language Models
Jihwan Bang, Sumyeong Ahn, Jae-Gil Lee
Vision Language Model Active Learning Prompt Learning Active Learning Framework

October 23, 2023

October 16, 2023

Active Learning Framework for Cost-Effective TCR-Epitope Binding Affinity Prediction
Pengfei Zhang, Seojin Bang, Heewook Lee
Active Learning Framework Affinity Prediction

August 17, 2023

Mitigating Semantic Confusion from Hostile Neighborhood for Graph Active Learning
Tianmeng Yang, Min Zhou, Yujing Wang, Zhengjie Lin, Lujia Pan, Bin Cui, Yunhai Tong
Graph Neural Network Node Classification Semantic Feature Active Learning Framework Graph Based Active Learning

July 10, 2023

Active Learning for Video Classification with Frame Level Queries
Debanjan Goswami, Shayok Chakraborty
Computer Vision Active Learning Video Classification Active Learning Framework Active Learning Algorithm Frame Wise

May 18, 2023

STREAMLINE: Streaming Active Learning for Realistic Multi-Distributional Settings
Nathan Beck, Suraj Kothawade, Pradeep Shenoy, Rishabh Iyer
Active Learning Link Stream Active Learning Framework Multi Distribution Streamlined Approach

May 4, 2023

Optimizing Drug Design by Merging Generative AI With Active Learning Frameworks
Isaac Filella-Merce, Alexis Molina, Marek Orzechowski, Lucía Díaz, Yang Ming Zhu, Julia Vilalta Mor, Laura Malo, Ajay S Yekkirala, Soumya Ray, Victor Guallar
Generative AI Drug Discovery Chemical Space Active Learning Framework Drug Design Chemical Property Prediction

April 13, 2023

Optimizing Multi-Domain Performance with Active Learning-based Improvement Strategies
Anand Gokul Mahalingam, Aayush Shah, Akshay Gulati, Royston Mascarenhas, Rakshitha Panduranga
Active Learning Image Classification Multi Domain Active Learning Framework