用时间门控机制，在资源受限下实现持续学习的高效适应。
TIMEGATE: Sustainable Time-Boxed Promotion Gates for Continual ML Adaptation Under Resource Constraints
- 设计时间盒策略，动态分配标注、训练、评估资源
- 100轮模拟中节省66%计算量，无误提升
- 适合边缘设备或低算力场景的持续学习部署
随着机器学习系统向持续适应演进，每次重训练均消耗计算、标注和能源。本文提出TIMEGATE，一种管理适应过程的策略层，通过预算时间、标注、训练和评估来控制资源使用。它输出度量可用性信号M，用于决定部分或完整评估。验证结果表明：(i) 在Adult表格数据集上，标注效率比训练高2.3倍；(ii) 在LLaMA-3.1-8B + QLoRA的SST-2任务中，准确率从0.80提升至0.96，且在35/36次运行中M=1；(iii) M具有信息量，28单元敏感性分析显示，紧阈值下M降至0.81；(iv) 100轮模拟实现66%评估计算节省，无静默误提升；(v) 对LLaMA进行10%采样评估，在单张H200上减少89%墙钟时间和能源，比例一致性达0.2。
原文摘要 · Abstract (English)
As machine learning(ML) systems evolve to continual adaptation, each re-training cycle uses compute, annotation, and energy. We introduce TIMEGATE, a policy layer managing adaptation by budgeting time, labeling, training, and evaluation. TIMEGATE emits a metric-availability signal M for partial vs. full-evaluation decisions. We validate: (i) labeling outperforms training by 2.3x on Adult tabular; (ii) it transfers to LLaMA-3.1-8B + QLoRA on SST-2 (accuracy 0.80 to 0.96; M =1 in 35/36 runs); (iii) M is informative, 28-cell sensitivity shows M drops to 0.81 at tight thresholds; (iv) 100-cycle simulation achieves 66% evaluation-compute savings with no silent mis-promotions; (v) 10%-slice evaluation on LLaMA uses 89% less wall-clock and energy on a single H200 (ratios agree to 0.2%).
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。