Active Learning

Active learning is a machine learning paradigm focused on optimizing data labeling efficiency by strategically selecting the most informative samples for annotation from a larger unlabeled pool. Current research emphasizes developing novel acquisition functions and data pruning strategies to reduce computational costs associated with large datasets, exploring the integration of active learning with various model architectures (including deep neural networks, Gaussian processes, and language models), and addressing challenges like privacy preservation and handling open-set noise. This approach holds significant promise for reducing the substantial cost and effort of data labeling in diverse fields, ranging from image classification and natural language processing to materials science and healthcare.

Papers

May 26, 2023

D-CALM: A Dynamic Clustering-based Active Learning Approach for Mitigating Bias
Sabit Hassan, Malihe Alikhani
Active Learning Bias Mitigation NLP Model Mitigating Bias Annotation System Clustering Based Active Learning

May 24, 2023

Active Learning for Natural Language Generation
Yotam Perlitz, Ariel Gera, Michal Shmueli-Scheuer, Dafna Sheinwald, Noam Slonim, Liat Ein-Dor
Active Learning Language Generation Text Classification Natural Language Generation Efficient Annotation

May 23, 2023

May 22, 2023

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

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 17, 2023

Active Learning in Symbolic Regression with Physical Constraints
Jorge Medina, Andrew D. White
Active Learning Symbolic Regression Diverse Equation Physical Constraint

May 16, 2023

On Dataset Transferability in Active Learning for Transformers
Fran Jelenić, Josip Jukić, Nina Drobac, Jan Šnajder
Transformer Megatron Decepticons Active Learning Text Classification Model Learning Transformer Based Pre Trained Language Model Transfer

May 13, 2023

May 11, 2023

May 10, 2023

Accelerating Batch Active Learning Using Continual Learning Techniques
Arnav Das, Gantavya Bhatt, Megh Bhalerao, Vianne Gao, Rui Yang, Jeff Bilmes
Active Learning Catastrophic Forgetting Continual Learning Replay Based Continual Learning Batch Active Learning Continual Learning Paradigm

May 7, 2023

Disentangled Multi-Fidelity Deep Bayesian Active Learning
Dongxia Wu, Ruijia Niu, Matteo Chinazzi, Yian Ma, Rose Yu
Active Learning Multi Fidelity Deep Active Learning Deep Surrogate Low Precision Representation Multi Fidelity Active Learning

May 6, 2023

Active Continual Learning: On Balancing Knowledge Retention and Learnability
Thuy-Trang Vu, Shahram Khadivi, Mahsa Ghorbanali, Dinh Phung, Gholamreza Haffari
Continual LEArning Active Learning Incremental Learning Anti Forgetting Knowledge Retention

Active Learning

Papers

D-CALM: A Dynamic Clustering-based Active Learning Approach for Mitigating Bias

Active Learning for Natural Language Generation

Parameter-Efficient Language Model Tuning with Active Learning in Low-Resource Settings

Active Learning Principles for In-Context Learning with Large Language Models

EASE: An Easily-Customized Annotation System Powered by Efficiency Enhancement Mechanisms

Error-Tolerant Exact Query Learning of Finite Set Partitions with Same-Cluster Oracle

The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning

Beyond Labels: Empowering Human Annotators with Natural Language Explanations through a Novel Active-Learning Architecture

Data-efficient Active Learning for Structured Prediction with Partial Annotation and Self-Training

On the Limitations of Simulating Active Learning

STREAMLINE: Streaming Active Learning for Realistic Multi-Distributional Settings

Active Learning in Symbolic Regression with Physical Constraints

On Dataset Transferability in Active Learning for Transformers

Learning to Learn Unlearned Feature for Brain Tumor Segmentation

An Active Learning-based Approach for Hosting Capacity Analysis in Distribution Systems

Sequential Experimental Design for Spectral Measurement: Active Learning Using a Parametric Model

Active Learning in the Predict-then-Optimize Framework: A Margin-Based Approach

Accelerating Batch Active Learning Using Continual Learning Techniques

Disentangled Multi-Fidelity Deep Bayesian Active Learning

Active Continual Learning: On Balancing Knowledge Retention and Learnability