C3RL: Rethinking the Combination of Channel-independence and Channel-mixing from Representation Learning
This addresses the challenge of balancing inter-variable dependencies and variable-specific patterns in time series forecasting, offering improved generalization for practitioners in fields like finance or healthcare.
The paper tackled the problem of multivariate time series forecasting by proposing C3RL, a representation learning framework that jointly models channel-mixing and channel-independence strategies, resulting in boosting the best-case performance rate to 81.4% for CI-based models and 76.3% for CM-based models.
Multivariate time series forecasting has drawn increasing attention due to its practical importance. Existing approaches typically adopt either channel-mixing (CM) or channel-independence (CI) strategies. CM strategy can capture inter-variable dependencies but fails to discern variable-specific temporal patterns. CI strategy improves this aspect but fails to fully exploit cross-variable dependencies like CM. Hybrid strategies based on feature fusion offer limited generalization and interpretability. To address these issues, we propose C3RL, a novel representation learning framework that jointly models both CM and CI strategies. Motivated by contrastive learning in computer vision, C3RL treats the inputs of the two strategies as transposed views and builds a siamese network architecture: one strategy serves as the backbone, while the other complements it. By jointly optimizing contrastive and prediction losses with adaptive weighting, C3RL balances representation and forecasting performance. Extensive experiments on seven models show that C3RL boosts the best-case performance rate to 81.4\% for models based on CI strategy and to 76.3\% for models based on CM strategy, demonstrating strong generalization and effectiveness. The code will be available once the paper is accepted.