Amortized Predictability-aware Training Framework for Time Series Forecasting and Classification

TL;DR

This paper introduces a novel training framework for time series tasks that dynamically identifies and penalizes low-predictability samples, improving model robustness and accuracy in forecasting and classification.

Contribution

It proposes the Amortized Predictability-aware Training Framework (APTF) with a hierarchical loss and amortization model to enhance training stability and performance.

Findings

Improves model focus on high-predictability samples

Reduces training instability caused by noisy data

Enhances accuracy in time series forecasting and classification

Abstract

Time series data are prone to noise in various domains, and training samples may contain low-predictability patterns that deviate from the normal data distribution, leading to training instability or convergence to poor local minima. Therefore, mitigating the adverse effects of low-predictability samples is crucial for time series analysis tasks such as time series forecasting (TSF) and time series classification (TSC). While many deep learning models have achieved promising performance, few consider how to identify and penalize low-predictability samples to improve model performance from the training perspective. To fill this gap, we propose a general Amortized Predictability-aware Training Framework (APTF) for both TSF and TSC. APTF introduces two key designs that enable the model to focus on high-predictability samples while still learning appropriately from low-predictability ones: (i) a Hierarchical Predictability-aware Loss (HPL) that dynamically identifies low-predictability samples and progressively expands their loss penalty as training evolves, and (ii) an amortization model that mitigates predictability estimation errors caused by model bias, further enhancing HPL's effectiveness. The code is available at https://github.com/Meteor-Stars/APTF.