Channel Normalization for Time Series Channel Identification
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 30 of its 47 references that are in the map. First posted on arXiv 31 May 2025.
Builds on
30 of 47 references.
References · 30
- 2017Attention Is All You Needcited by 60,361
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
- 2016Layer Normalizationcited by 5,669
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,718
- 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,169
- 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 2,039
- 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,676
- 2018Group Normalizationcited by 1,524
- 2022Are Transformers Effective for Time Series Forecasting?cited by 1,424
- 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
- 2023iTransformer: Inverted Transformers Are Effective for Time Series Forecastingcited by 931
18 more
- 2017Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networkscited by 879
- 2021SCINet: Time Series Modeling and Forecasting with Sample Convolution and Interactioncited by 338
- 2023TSMixer: An All-MLP Architecture for Time Series Forecastingcited by 240
- 2020Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reductioncited by 142
- 2024Is Mamba Effective for Time Series Forecasting?cited by 114
- 2023The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecastingcited by 101
- 2024TimeMachine: A Time Series is Worth 4 Mambas for Long-term Forecastingcited by 64
- 2022Towards Spatio-Temporal Aware Traffic Time Series Forecasting--Full Versioncited by 59
- 2024From Similarity to Superiority: Channel Clustering for Time Series Forecastingcited by 37
- 2024Bi-Mamba+: Bidirectional Mamba for Time Series Forecastingcited by 15
- 2024MambaTS: Improved Selective State Space Models for Long-term Time Series Forecastingcited by 14
- 2024Channel-Aware Low-Rank Adaptation in Time Series Forecastingcited by 12
- 2024CMamba: Channel Correlation Enhanced State Space Models for Multivariate Time Series Forecastingcited by 8
- 2024FMamba: Mamba based on Fast-attention for Multivariate Time-series Forecastingcited by 8
- 2024Sequential Order-Robust Mamba for Time Series Forecastingcited by 5
- 2025Sequence Complementor: Complementing Transformers For Time Series Forecasting with Learnable Sequencescited by 3
- 2023Learning on Bandwidth Constrained Multi-Source Data with MIMO-inspired DPP MAP Inferencecited by 2
- 2024InjectTST: A Transformer Method of Injecting Global Information into Independent Channels for Long Time Series Forecastingcited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.