更聰明地訓練，而非更努力地訓練：主動學習中的切換信號引導訓練

摘要

訓練策略，亦即要從頭重新訓練，或從先前的檢查點微調，是主動學習中一個被忽略的決策變數。我們顯示此選擇具有可資利用的結構：重新訓練在早期輪次最有用，此時每個批次都能大幅重塑標記分布；而一旦模型軌跡趨於穩定，微調便變得更安全。我們提出 HybridAL，一種自適應訓練排程，會監控線上穩定訊號，並在持續穩定後由重新訓練切換為微調。兩個互補訊號——頻譜指數變化 Δα（基於權重）與準確率變化 ΔAcc（基於驗證）——位於時間—校準權衡上的不同位置。在三個編碼器主幹與六項文本分類任務（各五個隨機種子）上，HybridAL 使最終 macro-F1 在 0.010 邊界內不劣於重新訓練與微調，節省最多 49% 的重新訓練時間，並恢復重新訓練相當比例的校準優勢（以負對數似然 NLL 衡量）。與在預先設定輪次切換的排程相比，HybridAL 以適度的額外成本獲得較低的 NLL，顯示依軌跡而定的切換比固定提早切換提供更強的時間—校準權衡。

English

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 ΔAcc (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.