用双重标准动态选难易数据，提升时序预测训练效果
Dual-Criterion Curriculum Learning: Application to Temporal Data
- 结合损失与数据密度双指标评估样本难度
- 在多变量时序数据上优于单一损失基准
- 适合需要高效训练的时序建模场景
课程学习（CL）是一种元学习范式，通过按难度递增顺序逐步输入数据实例来训练模型。定义有意义的难度评估指标是关键，但通常成为有效学习的主要瓶颈，且多数启发式方法具有特定应用场景局限。本文提出双准则课程学习（DCCL）框架，融合基于损失的难度评估与在数据表示空间中学习的密度准则。本质上，DCCL在考虑数据稀疏性会加剧学习难度的前提下，校准基于训练的证据（损失）。以时间序列预测为测试任务，在多变量时序基准数据集上，对标准单次遍历和婴儿步训练策略进行评估。实验证明，密度基础及混合双准则课程学习在该设置下优于仅基于损失的基线和标准非课程学习训练。
原文摘要 · Abstract (English)
Curriculum Learning (CL) is a meta-learning paradigm that trains a model by feeding the data instances incrementally according to a schedule, which is based on difficulty progression. Defining meaningful difficulty assessment measures is crucial and most usually the main bottleneck for effective learning, while also in many cases the employed heuristics are only application-specific. In this work, we propose the Dual-Criterion Curriculum Learning (DCCL) framework that combines two views of assessing instance-wise difficulty: a loss-based criterion is complemented by a density-based criterion learned in the data representation space. Essentially, DCCL calibrates training-based evidence (loss) under the consideration that data sparseness amplifies the learning difficulty. As a testbed, we choose the time-series forecasting task. We evaluate our framework on multivariate time-series benchmarks under standard One-Pass and Baby-Steps training schedules. Empirical results show the interest of density-based and hybrid dual-criterion curricula over loss-only baselines and standard non-CL training in this setting.
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。