伪标签应与标注样本共享 mini-batch 吗？SSCAL 提出低训练成本的半监督持续主动学习
Should Pseudo-Labels Share Mini-Batches with Labeled Examples? Semi-Supervised Continual Active Learning with Limited Training Cost
AI 导读
一篇 arXiv 论文首次将伪标签如何在持续主动学习（CAL）中与标注样本共享 mini-batch 问题形式化为两个决策：选择哪些未标注样本进入训练以及它们在 mini-batch 中的占比。
正文 · 原文
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 of mini-batch steps per round. Pseudo-labels add supervision without annotation, but they increase training cost. In CAL, where every round trains on a fixed number of mini-batches, whether and how pseudo-labeled examples should share these mini-batches with labeled examples is therefore open. We provide the first formalization of this problem as two decisions after each query, namely (i) which unlabeled examples should enter training with a pseudo-label and (ii) what share of each mini-batch they should take. Our method, semi-supervised continual active learning (SSCAL), works with any acquisition function. It admits pseudo-labels based on distances from unlabeled examples to labeled neighbors, caps their share, and reweights the loss on labeled examples to keep their expected gradient contribution unchanged. On frozen embeddings, its pseudo-labeler updates incrementally without extra model forward passes. Across two audio datasets, two frozen encoders, six acquisition functions and ten seeds, SSCAL ranks first on average among four protocols with equal training steps, answering the question affirmatively.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Sound (cs.SD); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2610.35345 [cs.LG] |
| (or arXiv:2610.35345v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35345 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shiqi Zhang [view email]
[v1]
Mon, 26 Oct 2026 12:37:21 UTC (54 KB)
来源：arXiv cs.AI · arxiv.org