Abstract
Real-world time series exhibit complex dynamics characterized by multiple simultaneous temporal patterns: short-term fluctuations, periodic seasonal cycles, long-term trends, and irregular abrupt changes. However, many existing forecasting architectures rely on single-path temporal modeling—transformers capture long-range dependencies but smooth local variations, convolutions capture local patterns but have limited receptive fields, and linear models are efficient but cannot capture nonlinear dynamics. To address this, we introduce RhyMix (RHYthm MIXture), a hybrid neural architecture designed around a parallel dual-path modeling paradigm with adaptive gating mechanisms.
RhyMix integrates two complementary encoding branches:
- Cyclic Path: Incorporates explicit seasonal inductive bias through learnable cyclic embeddings, capturing predictable rhythmic patterns;
- Lightweight Multi-Scale Temporal Convolutional Network with Channel Attention Path: Employs multi-scale depthwise dilated convolutions to capture temporal dependencies across different receptive fields.
A key innovation is the use of adaptive gating at multiple levels: a path gate dynamically combines four specialized forecasting heads (Direct, Trend-Seasonal Decomposition, Local Convolution, and Periodic Fusion) per sample and channel, while a hybrid gate adaptively balances the Cyclic and MSTCN-CA Paths based on input characteristics. This design ensures the model adapts to specific temporal patterns while maintaining linear complexity in sequence length, channels, and prediction horizon.
Across extensive benchmarks on 12 real-world datasets for long-term forecasting, RhyMix achieves state-of-the-art performance on 10 of 12 datasets. The model remains lightweight (~40K params) with linear complexity and low-latency inference.
Blogger's Review: RhyMix effectively overcomes the limitations of traditional time series forecasting models by introducing a parallel dual-path model and adaptive gating mechanisms, showcasing its potential in capturing complex dynamics. Moreover, the model's lightweight nature and efficiency promise broad applicability in real-world scenarios.