PaperScope
LIVE · 2026-09-09 05:40 UTC

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

Nagham Omar, Maya Rozenshtein, Evgeny Mishlyakov, Avigdor Gal

Latestcs.CLcs.LGcs.AIcs.CV
arXiv ID
2609.06806 v1
Category
Submitted
2026-09-06

Abstract

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 exponent change $Δα$ (weight-based) and accuracy change $Δ$Acc (validation-based), span different points on the time-calibration trade-off. Across three encoder backbones and six text-classification tasks (five seeds each), HybridAL keeps endpoint macro-F1 non-inferior to retraining and fine-tuning at a 0.010 margin, saves up to 49% of retraining time, and recovers a substantial fraction of retraining's calibration advantage as measured by negative log-likelihood (NLL). Compared with schedules that switch at a pre-committed round, HybridAL obtains lower NLL at moderate additional cost, showing that trajectory-dependent switching provides a stronger time-calibration trade-off than fixed early switching.

Comment: Accepted to EMNLP 2026 Main Conference

arXiv abs page · PDF · same-day batch