English(EN) Should Pseudo-Labels Share Mini-Batches with Labeled Examples? Semi-Supervised Continual Active Learning with Limited Training Cost

新的SSCAL方法优化了持续主动学习中的伪标签

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-27 04:00

提出了一种名为SSCAL的新方法，以解决在不增加总体训练成本的情况下将伪标签纳入半监督持续主动学习（SSCAL）的挑战。该方法将问题形式化为两个决策：哪些未标记示例应被伪标记，以及它们应占小批量数据的比例。SSCAL限制了伪标签的比例，并重新加权标记示例以维持其梯度贡献，在各种数据集和采集函数上的平均表现优异。 AI

影响优化了在持续学习场景中利用标记和未标记数据的模型的训练效率。

排序理由详细介绍半监督持续主动学习新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

arXiv
SSCAL

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 12 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍半监督持续主动学习新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Shiqi Zhang, Tuomas Virtanen · 2026-10-27 04:00

伪标签是否应与有标签样本共享小批量？有限训练成本下的半监督持续主动学习

arXiv:2610.35345v1 Announce Type: cross Abstract: Active learning (AL) reduces annotation by querying informative examples. Continual active learning (CAL) also cuts the training cost, the total number of gradient steps, by training one model across AL rounds with a fixed number …

本文如何被排名

报道来源 [1]

伪标签是否应与有标签样本共享小批量？有限训练成本下的半监督持续主动学习

相关实体

相关话题