Channel Normalization for Time Series Channel Identification
Preprint
Abstract
Channel identifiability (CID) refers to the ability to distinguish between individual channels in time series (TS) modeling. The absence of CID often results in producing identical outputs for identical inputs, disregarding channel-specific characteristics. In this paper, we highlight the importance of CID and propose Channel Normalization (CN), a simple yet effective normalization strategy that enhances CID by assigning distinct affine transformation parameters to each channel. We further extend CN in two ways: 1) Adaptive CN (ACN) dynamically adjusts parameters based on the input TS, improving adaptability in TS models, and 2) Prototypical CN (PCN) introduces a set of learnable prototypes instead of per-channel parameters, enabling applicability to datasets with unknown or varying number of channels and facilitating use in TS foundation models. We demonstrate the effectiveness of CN and its variants by applying them to various TS models, achieving significant performance gains for both non-CID and CID models. In addition, we analyze the success of our approach from an information theory perspective. Code is available at https://github.com/seunghan96/CN.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Is Mamba effective for time series forecasting?Neurocomputing, 2024
- Channel-Aware Low-Rank Adaptation in Time Series Forecasting2024
- Learning on Bandwidth Constrained Multi-Source Data With MIMO-Inspired DPP MAP InferenceIEEE Transactions on Machine Learning in Communications and Networking, 2024
- The Capacity and Robustness Trade-Off: Revisiting the Channel Independent Strategy for Multivariate Time Series ForecastingIEEE Transactions on Knowledge and Data Engineering, 2024
- Predicting Best-Selling New Products in a Major Promotion Campaign Through Graph Convolutional NetworksIEEE Transactions on Neural Networks and Learning Systems, 2022
- Informer: Beyond Efficient Transformer for Long Sequence Time-Series ForecastingProceedings of the AAAI Conference on Artificial Intelligence, 2021
- A Hybrid Residual Dilated LSTM and Exponential Smoothing Model for Midterm Electric Load ForecastingIEEE Transactions on Neural Networks and Learning Systems, 2021
- Deep Adaptive Input Normalization for Time Series ForecastingIEEE Transactions on Neural Networks and Learning Systems, 2019
- Communications-Inspired Projection Design with Application to Compressive SensingSIAM Journal on Imaging Sciences, 2012
- Learning representations by back-propagating errorsNature, 1986