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 23, 2024

Actively Learning Combinatorial Optimization Using a Membership Oracle
Rosario Messana, Rui Chen, Andrea Lodi
Active Learning Convex Optimization Combinatorial Optimization Problem Test Oracle Online Combinatorial Linear Surrogate

May 22, 2024

Enhancing Active Learning for Sentinel 2 Imagery through Contrastive Learning and Uncertainty Estimation
David Pogorzelski, Peter Arlinghaus, Wenyan Zhang
Contrastive Learning Active Learning Semi Supervised Learning Uncertainty Estimation Satellite Image Visual Imagery Sentinel 1 Sentinel 2

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

May 18, 2024

A Unified Approach Towards Active Learning and Out-of-Distribution Detection
Sebastian Schmidt, Leonard Schenk, Leo Schwinn, Stephan Günnemann
Deep Learning Model Active Learning Distribution Detection Unified Framework Distance Metric

May 17, 2024

May 16, 2024

Active Learning with Fully Bayesian Neural Networks for Discontinuous and Nonstationary Data
Maxim Ziatdinov
Active Learning Gaussian Process Bayesian Neural Network Probabilistic Surrogate

May 15, 2024

May 14, 2024

Neural Active Learning Meets the Partial Monitoring Framework
Maxime Heuillet, Ola Ahmad, Audrey Durand
Active Learning Partial Monitoring Neural Active Learning

May 13, 2024

May 10, 2024

May 5, 2024

Active Preference Learning for Ordering Items In- and Out-of-sample
Herman Bergström, Emil Carlsson, Devdatt Dubhashi, Fredrik D. Johansson
Active Learning Order Matter Pairwise Comparison Document Ranking Active Preference

May 3, 2024

Combining X-Vectors and Bayesian Batch Active Learning: Two-Stage Active Learning Pipeline for Speech Recognition
Ognjen Kundacina, Vladimir Vincan, Dragisa Miskovic
Automatic Speech Recognition Active Learning Speech Recognition Speech Data X Vector Batch Active Learning Learning Pipeline

May 2, 2024

May 1, 2024

Predictive Accuracy-Based Active Learning for Medical Image Segmentation
Jun Shi, Shulan Ruan, Ziqi Zhu, Minfan Zhao, Hong An, Xudong Xue, Bing Yan
Active Learning Medical Image Segmentation Segmentation Task Segmentation Accuracy Efficient Active Learning

Active Learning

Papers

Actively Learning Combinatorial Optimization Using a Membership Oracle

Enhancing Active Learning for Sentinel 2 Imagery through Contrastive Learning and Uncertainty Estimation

An Active Learning Framework with a Class Balancing Strategy for Time Series Classification

A Unified Approach Towards Active Learning and Out-of-Distribution Detection

Frugal Algorithm Selection

ActiveLLM: Large Language Model-based Active Learning for Textual Few-Shot Scenarios

Future Aware Safe Active Learning of Time Varying Systems using Gaussian Processes

Active Learning with Fully Bayesian Neural Networks for Discontinuous and Nonstationary Data

Agnostic Active Learning of Single Index Models with Linear Sample Complexity

Perception Without Vision for Trajectory Prediction: Ego Vehicle Dynamics as Scene Representation for Efficient Active Learning in Autonomous Driving

Neural Active Learning Meets the Partial Monitoring Framework

Active Learning with Simple Questions

Maximizing Information Gain in Privacy-Aware Active Learning of Email Anomalies

Conformal Validity Guarantees Exist for Any Data Distribution (and How to Find Them)

Boolean matrix logic programming for active learning of gene functions in genome-scale metabolic network models

Active Preference Learning for Ordering Items In- and Out-of-sample

Combining X-Vectors and Bayesian Batch Active Learning: Two-Stage Active Learning Pipeline for Speech Recognition

Active Learning Enabled Low-cost Cell Image Segmentation Using Bounding Box Annotation

Uncertainty for Active Learning on Graphs

Predictive Accuracy-Based Active Learning for Medical Image Segmentation