中文
相关论文

相关论文: OpenAL: Evaluation and Interpretation of Active Le…

200 篇论文

Active learning aims to alleviate the amount of labor involved in data labeling by automating the selection of unlabeled samples via an acquisition function. For example, variational adversarial active learning (VAAL) leverages an…

机器学习 · 计算机科学 2024-08-26 Zongyao Lyu , William J. Beksi

Medical image analysis requires substantial labeled data for model training, yet expert annotation is expensive and time-consuming. Active learning (AL) addresses this challenge by strategically selecting the most informative samples for…

图像与视频处理 · 电气工程与系统科学 2026-03-06 Ifrat Ikhtear Uddin , Longwei Wang , Xiao Qin , Yang Zhou , KC Santosh

In the world of big data, large but costly to label datasets dominate many fields. Active learning, a semi-supervised alternative to the standard PAC-learning model, was introduced to explore whether adaptive labeling could learn concepts…

机器学习 · 计算机科学 2020-06-02 Max Hopkins , Daniel M. Kane , Shachar Lovett

Often, labeling large amount of data is challenging due to high labeling cost limiting the application domain of deep learning techniques. Active learning (AL) tackles this by querying the most informative samples to be annotated among…

机器学习 · 计算机科学 2020-12-09 Kwanyoung Kim , Dongwon Park , Kwang In Kim , Se Young Chun

The acquisition of labels for supervised learning can be expensive. To improve the sample efficiency of neural network regression, we study active learning methods that adaptively select batches of unlabeled data for labeling. We present a…

机器学习 · 统计学 2023-08-02 David Holzmüller , Viktor Zaverkin , Johannes Kästner , Ingo Steinwart

Active learning aims to select samples to be annotated that yield the largest performance improvement for the learning algorithm. Many methods approach this problem by measuring the informativeness of samples and do this based on the…

机器学习 · 计算机科学 2021-08-02 Javad Zolfaghari Bengar , Bogdan Raducanu , Joost van de Weijer

In recent years, an active field of research has developed around automated machine learning (AutoML). Unfortunately, comparing different AutoML systems is hard and often done incorrectly. We introduce an open, ongoing, and extensible…

机器学习 · 计算机科学 2019-07-02 Pieter Gijsbers , Erin LeDell , Janek Thomas , Sébastien Poirier , Bernd Bischl , Joaquin Vanschoren

Deep learning models for natural language processing rely heavily on high-quality labeled datasets. However, existing labeling approaches often struggle to balance label quality with labeling cost. To address this challenge, we propose…

人机交互 · 计算机科学 2026-02-17 Guozheng Li , Ao Wang , Shaoxiang Wang , Yu Zhang , Pengcheng Cao , Yang Bai , Chi Harold Liu

In this work, we introduce the concept of Active Representation Learning, a novel class of problems that intertwines exploration and representation learning within partially observable environments. We extend ideas from Active Simultaneous…

机器学习 · 计算机科学 2024-11-07 Nikola Milosevic , Gesine Müller , Jan Huisken , Nico Scherf

Active learning (AL) is a machine learning (ML) approach that strategically selects the most informative samples for annotation during training, aiming to minimize annotation costs. This strategy not only reduces labeling expenses but also…

机器学习 · 计算机科学 2026-03-25 Cédric Jung , Shirin Salehi , Anke Schmeink

Self-Supervised Learning (SSL) has emerged as the solution of choice to learn transferable representations from unlabeled data. However, SSL requires to build samples that are known to be semantically akin, i.e. positive views. Requiring…

机器学习 · 计算机科学 2023-10-02 Vivien Cabannes , Leon Bottou , Yann Lecun , Randall Balestriero

We introduce a new framework for sample-efficient model evaluation that we call active testing. While approaches like active learning reduce the number of labels needed for model training, existing literature largely ignores the cost of…

机器学习 · 统计学 2021-06-15 Jannik Kossen , Sebastian Farquhar , Yarin Gal , Tom Rainforth

Aligning large language models (LLMs) depends on high-quality datasets of human preference labels, which are costly to collect. Although active learning has been studied to improve sample efficiency relative to passive collection, many…

机器学习 · 计算机科学 2026-02-03 Yao Zhao , Kwang-Sung Jun

Active learning is to design label-efficient algorithms by sampling the most representative samples to be labeled by an oracle. In this paper, we propose a state relabeling adversarial active learning model (SRAAL), that leverages both the…

计算机视觉与模式识别 · 计算机科学 2020-04-13 Beichen Zhang , Liang Li , Shijie Yang , Shuhui Wang , Zheng-Jun Zha , Qingming Huang

Multi-agent deep reinforcement learning (MARL) suffers from a lack of commonly-used evaluation tasks and criteria, making comparisons between approaches difficult. In this work, we provide a systematic evaluation and comparison of three…

机器学习 · 计算机科学 2021-11-10 Georgios Papoudakis , Filippos Christianos , Lukas Schäfer , Stefano V. Albrecht

We focus on the online-based active learning (OAL) setting where an agent operates over a stream of observations and trades-off between the costly acquisition of information (labelled observations) and the cost of prediction errors. We…

机器学习 · 计算机科学 2024-05-16 Maxime Heuillet , Ola Ahmad , Audrey Durand

The remarkable advancements in large language models (LLMs) have significantly enhanced the performance in few-shot learning settings. By using only a small number of labeled examples, referred to as demonstrations, LLMs can effectively…

计算与语言 · 计算机科学 2023-11-23 Katerina Margatina , Timo Schick , Nikolaos Aletras , Jane Dwivedi-Yu

Online Active Learning (OAL) aims to manage unlabeled datastream by selectively querying the label of data. OAL is applicable to many real-world problems, such as anomaly detection in health-care and finance. In these problems, there are…

机器学习 · 计算机科学 2019-11-19 Yifan Zhang , Peilin Zhao , Shuaicheng Niu , Qingyao Wu , Jiezhang Cao , Junzhou Huang , Mingkui Tan

Pathology image classification plays a crucial role in accurate medical diagnosis and treatment planning. Training high-performance models for this task typically requires large-scale annotated datasets, which are both expensive and…

计算机视觉与模式识别 · 计算机科学 2025-07-01 Lanfeng Zhong , Xin Liao , Shichuan Zhang , Shaoting Zhang , Guotai Wang

In this work, we provide a survey of active learning (AL) for its applications in natural language processing (NLP). In addition to a fine-grained categorization of query strategies, we also investigate several other important aspects of…

计算与语言 · 计算机科学 2023-02-06 Zhisong Zhang , Emma Strubell , Eduard Hovy