paper-with-me

홈 › Papers

Active Learning on a Budget: Opposite Strategies Suit High and Low Budgets

2022-02-06 · Guy Hacohen, Avihu Dekel, Daphna Weinshall

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.

📄 PDF Abstract BibTeX arXiv:2202.02794

Code (1)

avihu111/typiclust 공식 구현 pytorch

Tasks

Active Learning

Similar Papers 제목 키워드 기반

How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budget

2023-06-06 · NeurIPS 2023 11

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 Learning

Understanding LLM Reasoning for Abstractive Summarization

2025-12-03 · Haohan Yuan, Haopeng Zhang arxiv

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 Generation

Active Learning Through a Covering Lens

2022-05-23 · Ofer Yehuda, Avihu Dekel, Guy Hacohen, Daphna Weinshall

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 Learning

Cost-Based Budget Active Learning for Deep Learning

2020-12-09 · Patrick K. Gikunda, Nicolas Jouandeau

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 Classification

Active-Learning-as-a-Service: An Automatic and Efficient MLOps System for Data-Centric AI

2022-07-19 · Yizheng Huang, Huaizheng Zhang, Yuanming Li, Chiew Tong Lau 외

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