Hierarchical Classification Auxiliary Network for Time Series Forecasting

TL;DR

This paper introduces HCAN, a hierarchical classification auxiliary network that improves time series forecasting by capturing high-entropy features and reducing over-smooth predictions through a novel hierarchy-aware attention and uncertainty modeling.

Contribution

The paper presents HCAN, a model-agnostic framework that enhances forecasting models with hierarchical classification and evidence theory to better handle complex, high-variability time series data.

Findings

HCAN improves forecasting accuracy on multiple datasets.

The hierarchical approach captures multi-granularity features effectively.

Uncertainty-aware classifiers reduce over-confidence in predictions.

Abstract

Deep learning has significantly advanced time series forecasting through its powerful capacity to capture sequence relationships. However, training these models with the Mean Square Error (MSE) loss often results in over-smooth predictions, making it challenging to handle the complexity and learn high-entropy features from time series data with high variability and unpredictability. In this work, we introduce a novel approach by tokenizing time series values to train forecasting models via cross-entropy loss, while considering the continuous nature of time series data. Specifically, we propose a Hierarchical Classification Auxiliary Network, HCAN, a general model-agnostic component that can be integrated with any forecasting model. HCAN is based on a Hierarchy-Aware Attention module that integrates multi-granularity high-entropy features at different hierarchy levels. At each level, we assign a class label for timesteps to train an Uncertainty-Aware Classifier. This classifier mitigates the over-confidence in softmax loss via evidence theory. We also implement a Hierarchical Consistency Loss to maintain prediction consistency across hierarchy levels. Extensive experiments integrating HCAN with state-of-the-art forecasting models demonstrate substantial improvements over baselines on several real-world datasets.