Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets
Investigating active learning, we focus on the relation between the number of labeled examples (budget size), and suitable querying strategies. Our theoretical analysis shows a behavior reminiscent of phase transition: typical examples are best queried when the budget is low, while unrepresentative examples are best queried when the budget is large. Combined evidence shows that a similar phenomenon occurs in common classification models. Accordingly, we propose TypiClust -- a deep active learning strategy suited for low budgets. In a comparative empirical investigation of supervised learning, using a variety of architectures and image datasets, TypiClust outperforms all other active learning strategies in the low-budget regime. Using TypiClust in the semi-supervised framework, performance gets an even more significant boost. In particular, state-of-the-art semi-supervised methods trained on CIFAR-10 with 10 labeled examples selected by TypiClust, reach 93.2% accuracy -- an improvement of 39.4% over random selection. Code is available at https://github.com/avihu111/TypiClust.
Code (1)
Tasks
Active LearningSimilar Papers 제목 키워드 기반
How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budget
In the domain of Active Learning (AL), a learner actively selects which unlabeled examples to seek labels from an oracle, while operating within predefined budget constraints. Importantly, it has been recently shown that…
Active LearningUnderstanding LLM Reasoning for Abstractive Summarization
Reasoning has substantially improved Large Language Models (LLMs) on analytical tasks such as mathematics and code generation, but its value for abstractive summarization remains unclear. To address this gap, we adapt ge…
Code GenerationActive Learning Through a Covering Lens
Deep active learning aims to reduce the annotation cost for the training of deep models, which is notoriously data-hungry. Until recently, deep active learning methods were ineffectual in the low-budget regime, where onl…
Active LearningRepresentation LearningSelf-Supervised LearningCost-Based Budget Active Learning for Deep Learning
Majorly classical Active Learning (AL) approach usually uses statistical theory such as entropy and margin to measure instance utility, however it fails to capture the data distribution information contained in the unlab…
Active LearningDeep LearningDiversityGeneral ClassificationActive-Learning-as-a-Service: An Automatic and Efficient MLOps System for Data-Centric AI
The success of today's AI applications requires not only model training (Model-centric) but also data engineering (Data-centric). In data-centric AI, active learning (AL) plays a vital role, but current AL tools 1) requi…
Active LearningAutoMLPhilosophy