Position: The Inevitable End of One-Architecture-Fits-All-Domains in Time Series Forecasting

TL;DR

This paper argues that the pursuit of universal neural network architectures for time series forecasting is futile, advocating for a focus on domain-specific methods or meta-learning approaches for better practical results.

Contribution

The paper critically analyzes the limitations of current general-purpose neural architectures and calls for a strategic shift towards domain-specific or meta-learning solutions.

Findings

General neural architectures have saturated in performance.

Domain-specific methods outperform general architectures in practice.

Meta-learning offers a promising direction for generalization.

Abstract

Recent work has questioned the effectiveness and robustness of neural network architectures for time series forecasting tasks. We summarize these concerns and analyze groundly their inherent limitations: i.e. the irreconcilable conflict between single (or few similar) domains SOTA and generalizability over general domains for time series forecasting neural network architecture designs. Moreover, neural networks architectures for general domain time series forecasting are becoming more and more complicated and their performance has almost saturated in recent years. As a result, network architectures developed aiming at fitting general time series domains are almost not inspiring for real world practices for certain single (or few similar) domains such as Finance, Weather, Traffic, etc: each specific domain develops their own methods that rarely utilize advances in neural network architectures of time series community in recent 2-3 years. As a result, we call for the time series community to shift focus away from research on time series neural network architectures for general domains: these researches have become saturated and away from domain-specific SOTAs over time. We should either (1) focus on deep learning methods for certain specific domain(s), or (2) turn to the development of meta-learning methods for general domains.