SOURCE-LINKED INTELLIGENCE

Train Smarter, Not Harder: Switching Signal-Guided Training in Active Learning

arXiv · AI, language, vision and robotics · article · Sep 6, 2026 · UTC

Training strategy, namely whether to retrain from scratch or fine-tune from the previous checkpoint, is an overlooked decision variable in active learning. We show that this choice has exploitable structure: retraining is most useful in early rounds, when each batch can substantially reshape the labeled distribution, while fine-tuning becomes safer once the model trajectory stabilizes. We propose HybridAL, an adaptive training schedule that monitors an online stabilization signal and switches from retraining to fine-tuning after sustained stabilization. Two complementary signals, spectral expo

Read original source ↗ Open in workspace

recordType

paper

region

Global