paper-with-me

Papers

Cold-start Active Learning through Self-supervised Language Modeling

2020-10-19 · EMNLP 2020 11 · Michelle Yuan, Hsuan-Tien Lin, Jordan Boyd-Graber

Active learning strives to reduce annotation costs by choosing the most critical examples to label. Typically, the active learning strategy is contingent on the classification model. For instance, uncertainty sampling depends on poorly calibrated model confidence scores. In the cold-start setting, active learning is impractical because of model instability and data scarcity. Fortunately, modern NLP provides an additional source of information: pre-trained language models. The pre-training loss can find examples that surprise the model and should be labeled for efficient fine-tuning. Therefore, we treat the language modeling loss as a proxy for classification uncertainty. With BERT, we develop a simple strategy based on the masked language modeling loss that minimizes labeling costs for text classification. Compared to other baselines, our approach reaches higher accuracy within less sampling iterations and computation time.

📄 PDF Abstract BibTeX arXiv:2010.09535

Code (1)

forest-snow/alps 공식 구현 pytorch

Tasks

Active LearningClassificationGeneral ClassificationLanguage ModelingLanguage ModellingMasked Language Modelingtext-classificationText Classification

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
WordPiece 설명 없음
Adam 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Multi-Head Attention 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

Similar Papers 제목 키워드 기반

Cold-Start Active Preference Learning in Socio-Economic Domains

2025-08-07 · Mojtaba Fayaz-Bakhsh, Danial Ataee, MohammadAmin Fazli arxiv

Active preference learning offers an efficient approach to modeling preferences, but it is hindered by the cold-start problem, which leads to a marked decline in performance when no initial labeled data are available. Wh…

Active Learning

Foundation Model Makes Clustering A Better Initialization For Cold-Start Active Learning

2024-02-04 · Han Yuan, Chuan Hong

Active learning selects the most informative samples from the unlabelled dataset to annotate in the context of a limited annotation budget. While numerous methods have been proposed for subsequent sample selection based …

Active LearningClusteringimage-classificationImage Classification

Dataset-Aware Cold-Start Active Learning for Annotation-Efficient 3D Medical Image Segmentation

2026-06-18 · Rémi Hattat, Marine Beaumont, Charline Bertholdt, Gabriela Hossu 외 arxiv

Deep learning for 3D medical image segmentation requires extensive manual annotations, a major bottleneck in volumetric medical imaging. Active learning aims to reduce this burden by selecting informative samples for ann…

Medical Image SegmentationActive Learning

Self-supervised Assisted Active Learning for Skin Lesion Segmentation

2022-05-14 · Ziyuan Zhao, Wenjing Lu, Zeng Zeng, Kaixin Xu 외

Label scarcity has been a long-standing issue for biomedical image segmentation, due to high annotation costs and professional requirements. Recently, active learning (AL) strategies strive to reduce annotation costs by …

Active LearningDiversityImage SegmentationLesion Segmentation+4

Cold-Start Active Correlation Clustering

2025-09-29 · Linus Aronsson, Han Wu, Morteza Haghir Chehreghani arxiv

We study active correlation clustering where pairwise similarities are not provided upfront and must be queried in a cost-efficient manner through active learning. Specifically, we focus on the cold-start scenario, where…

Active Learning