paper-with-me

Papers

Semi-supervised Batch Active Learning via Bilevel Optimization

2020-10-19 · Zalán Borsos, Marco Tagliasacchi, Andreas Krause

Active learning is an effective technique for reducing the labeling cost by improving data efficiency. In this work, we propose a novel batch acquisition strategy for active learning in the setting where the model training is performed in a semi-supervised manner. We formulate our approach as a data summarization problem via bilevel optimization, where the queried batch consists of the points that best summarize the unlabeled data pool. We show that our method is highly effective in keyword detection tasks in the regime when only few labeled samples are available.

📄 PDF Abstract BibTeX arXiv:2010.09654

Code (1)

zalanborsos/bilevel_coresets 공식 구현 pytorch

Tasks

Active LearningBilevel OptimizationData Summarization

Similar Papers 제목 키워드 기반

MetAL: Active Semi-Supervised Learning on Graphs via Meta Learning

2020-07-22 · Kaushalya Madhawa, Tsuyoshi Murata

The objective of active learning (AL) is to train classification models with less number of labeled instances by selecting only the most informative instances for labeling. The AL algorithms designed for other data types…

Active LearningBilevel OptimizationMeta-Learning

Learning to Rank for Active Learning via Multi-Task Bilevel Optimization

2023-10-25 · Zixin Ding, Si Chen, Ruoxi Jia, Yuxin Chen

Active learning is a promising paradigm to reduce the labeling cost by strategically requesting labels to improve model performance. However, existing active learning methods often rely on expensive acquisition function …

Active LearningBilevel OptimizationLearning-To-Rank

Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization

2022-11-14 · Quan Xiao, Han Shen, Wotao Yin, Tianyi Chen

Stochastic bilevel optimization, which captures the inherent nested structure of machine learning problems, is gaining popularity in many recent applications. Existing works on bilevel optimization mostly consider either…

Bilevel Optimization

Whiteness-based bilevel learning of regularization parameters in imaging

2024-03-10 · Carlo Santambrogio, Monica Pragliola, Alessandro Lanza, Marco Donatelli 외

We consider an unsupervised bilevel optimization strategy for learning regularization parameters in the context of imaging inverse problems in the presence of additive white Gaussian noise. Compared to supervised and sem…

Bilevel OptimizationImage Deconvolution

A Single-Timescale Method for Stochastic Bilevel Optimization

2021-02-09 · Tianyi Chen, Yuejiao Sun, Quan Xiao, Wotao Yin

Stochastic bilevel optimization generalizes the classic stochastic optimization from the minimization of a single objective to the minimization of an objective function that depends the solution of another optimization p…

Bilevel OptimizationMeta-LearningStochastic Optimization