ACFormer: Mitigating Non-linearity with Auto Convolutional Encoder for Time Series Forecasting
This work addresses the problem of capturing non-linear dependencies in time series forecasting for domains like finance or weather, representing an incremental improvement over existing linear and hybrid models.
The paper tackled the challenge of modeling non-linear signals in time series forecasting by proposing ACFormer, which combines linear efficiency with convolutional feature extraction, achieving state-of-the-art performance on multiple benchmark datasets.
Time series forecasting (TSF) faces challenges in modeling complex intra-channel temporal dependencies and inter-channel correlations. Although recent research has highlighted the efficiency of linear architectures in capturing global trends, these models often struggle with non-linear signals. To address this gap, we conducted a systematic receptive field analysis of convolutional neural network (CNN) TSF models. We introduce the "individual receptive field" to uncover granular structural dependencies, revealing that convolutional layers act as feature extractors that mirror channel-wise attention while exhibiting superior robustness to non-linear fluctuations. Based on these insights, we propose ACFormer, an architecture designed to reconcile the efficiency of linear projections with the non-linear feature-extraction power of convolutions. ACFormer captures fine-grained information through a shared compression module, preserves temporal locality via gated attention, and reconstructs variable-specific temporal patterns using an independent patch expansion layer. Extensive experiments on multiple benchmark datasets demonstrate that ACFormer consistently achieves state-of-the-art performance, effectively mitigating the inherent drawbacks of linear models in capturing high-frequency components.