Papers Active Learning
“Active Learning” 태그가 달린 논문 3,569편 · 필터 해제
Scientific Discovery under Validation Congestion via Multi-Fidelity Pairwise Rankings
Modern computational methods can now propose candidate molecules, materials, and other scientific designs at an unprecedented scale, creating a validation congestion where candidates are abundant, but experimental capaci…
Active LearningDrug DiscoveryCalibration as a First-Class Criterion in LLM Evaluation
Calibration of language models -- the alignment between expressed or implicit confidence and empirical correctness -- is a well-studied subfield within NLP. Methods to measure it already exist. The problem is adoption: o…
Synthetic Data GenerationActive LearningOne Loop, Two Gains: Can Active Learning win the Lottery for Free?
The lottery ticket hypothesis posits the existence of winning tickets: sparse subnetworks that, when trained in isolation from their original initialization, match the accuracy of the full dense network. The predominant …
Image ClassificationActive LearningTrain Smarter, Not Harder: Switching Signal-Guided Training in Active Learning
Training strategy, namely whether to retrain from scratch or fine-tune from the previous checkpoint, is an overlooked decision variable in active learning. We show that this choice has exploitable structure: retraining i…
Active LearningCost-efficient Active Learning for Referring Image Segmentation and Grounding
Collecting natural-language referring expressions along with region annotations, such as masks or boxes, is a major bottleneck in visual grounding (VG), as annotators must write descriptions that distinguish target regio…
Image SegmentationVisual GroundingActive LearningLoss-Based Active Learning for Neural Abstractive Summarization
Fine-tuning abstractive summarization models requires high-quality annotated data. However, obtaining such corpora is expensive and time-consuming, as it requires human annotators to read and comprehend long documents to…
Active LearningConfAL-WM: Confidence-Guided Active Learning for Action-Conditioned World Models
Action-conditioned world models have become an important foundation for embodied prediction, planning, and synthetic data generation, but their errors under new task and scene distributions are often concentrated in loca…
Synthetic Data GenerationActive LearningDiversity-Based Active Learning: An Evaluation of Metric Spaces for Active Learning Selection
With rapid advancement over the last few years, many different methods are now widely used for classification. However, training these models requires substantial labeled data. Active Learning is a potential solution to …
Active LearningLLMs as Acquisition Policies for Finite-Pool Materials Optimization: A Controlled Study
Discovering materials with desirable properties often requires searching large candidate spaces while experimental or computational evaluations remain costly. Active learning addresses this challenge by using previous ob…
Active LearningLearning Canonical Register Automata over Ordered Data Domains
Register automata are finite automata equipped with memory that recognize data languages over infinite alphabets. In this work, we investigate active learning algorithms for deterministic register automata (DRAs) over or…
Active LearningCoordination on a Budget: Federated Active Learning with Few Labels
Federated Active Learning (FAL) addresses the dual challenges of data privacy and label scarcity, where the absence of a global data view introduces additional hurdles for coordinated query selection. We study cross-silo…
Representation LearningFederated LearningActive LearningProbing Association Instability with Track-State Perturbations for Clip-Level Active Learning in Query-Propagation Multi-Object Tracking
Training query-propagation end-to-end multi-object tracking (MOT) models requires dense bounding-box and identity annotations across video sequences, making dataset construction expensive. Clip-level active learning redu…
Multi-Object TrackingActive LearningQ-based Variational Inverse Reinforcement Learning
The development of safe and beneficial AI requires that systems can learn and act in accordance with human preferences. However, explicitly specifying these preferences by hand is often infeasible. Inverse reinforcement …
Reinforcement LearningActive LearningAtari GamesSUGFW+: An Uncertainty-guided Feature Weighting Framework for Cold Start Active Adaptation of SAM in Medical Image Segmentation
Cold Start Active Learning (CSAL) is important in improving the performance of a medical image segmentation model with low annotation budget by querying a small subset for annotation from an unlabeled training set. Exist…
Medical Image SegmentationSelf-Supervised LearningActive LearningOvercoming Shortcut Learning in Graph Neural Networks through Active Explanation Guidance
Graph Neural Networks (GNNs) can solve prediction tasks by unintentionally exploiting shortcuts---that is, edges, nodes, and features that correlate with but are not causal for the prediction---which compromise their rel…
Active LearningBuy the Rumor, Sell the News: When Is News Priced In?
Two old market sayings hold that news is already priced in by the time it is published, and that the rumor is bought while the news is sold. Both place the price move associated with a piece of news before and at publica…
Active LearningA Remote Approach to Cashew Orchard Detection: Leveraging Active Learning with Satellite Imagery in Guinea-Bissau
Cashew production is a widespread economic activity in Guinea-Bissau, as well as other countries in West Africa. However, unregulated cashew production can be directly associated with increasing regionwide deforestation …
Active LearningHow Many Labels Are Enough? ALDA: Active Learning Deployment Advisor for Medical Image Classification
Active learning (AL) promises to reduce the cost of medical imaging projects by lowering the number of clinical labels required. However, practical deployment requires committing to a sampling strategy before the full an…
Medical Image ClassificationActive LearningOne Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learning
Cold-Start Active Learning (CSAL) aims to select a valuable subset from an unlabeled pool without any prior knowledge or human assistance. Existing methods take diverse routes based on typicality, coverage, or diversity.…
Active LearningUncertainty-guided active learning for surrogate prediction of stream-finishing wear fields
In stream finishing, the wear experienced by a workpiece depends strongly on its orientation within the rotating abrasive media. Determining suitable orientations to achieve uniform wear requires evaluating the wear-rate…
Active Learning