We present a Task-aware modulation using Representation Learning (TAM-RL)
framework that enhances personalized predictions in few-shot settings for
heterogeneous systems when individual task characteristics are not known.
TAM-RL extracts embeddings representing the actual inherent characteristics of
these entities and uses these characteristics to personalize the predictions
for each entity/task. Using real-world hydrological and flux tower benchmark
data sets, we show that TAM-RL can significantly outperform existing baseline
approaches such as MAML and multi-modal MAML (MMAML) while being much faster
and simpler to train due to less complexity. Specifically, TAM-RL eliminates
the need for sensitive hyper-parameters like inner loop steps and inner loop
learning rate, which are crucial for model convergence in MAML, MMAML. We
further present an empirical evaluation via synthetic data to explore the
impact of heterogeneity amongst the entities on the relative performance of
MAML, MMAML, and TAM-RL. We show that TAM-RL significantly improves predictive
performance for cases where it is possible to learn distinct representations
for different tasks.

本研究通过使用任务感知的表示学习（TAM-RL）框架，在不了解单个任务特征的异构系统中提升个性化预测。TAM-RL 提取代表实体的实际内在特征的嵌入，并将这些特征用于为每个实体 / 任务个性化预测。通过使用真实的水文和通量塔基准数据集，我们展示了 TAM-RL 能够在更快且更简单的训练过程中显著优于现有的基准方法，如 MAML 和多模态 MAML（MMAML）。具体而言，TAM-RL 消除了对 MAML、MMAML 模型收敛至关重要的敏感超参数，如内循环步骤和内循环学习率的需求。我们进一步通过使用合成数据进行实证评估，探究实体的异质性对 MAML、MMAML 和 TAM-RL 相对性能的影响。结论显示，当可能学习到不同任务的不同表示时，TAM-RL 显著提高了预测性能。