DropoutTS: Sample-Adaptive Dropout for Robust Time Series Forecasting
This addresses robustness issues in time series forecasting for real-world applications, offering an efficient solution without architectural changes.
The paper tackles the problem of deep time series models being vulnerable to noisy data by introducing DropoutTS, a model-agnostic plugin that uses sample-adaptive dropout to dynamically calibrate learning capacity based on noise levels, resulting in consistent performance boosts across diverse benchmarks with negligible overhead.
Deep time series models are vulnerable to noisy data ubiquitous in real-world applications. Existing robustness strategies either prune data or rely on costly prior quantification, failing to balance effectiveness and efficiency. In this paper, we introduce DropoutTS, a model-agnostic plugin that shifts the paradigm from "what" to learn to "how much" to learn. DropoutTS employs a Sample-Adaptive Dropout mechanism: leveraging spectral sparsity to efficiently quantify instance-level noise via reconstruction residuals, it dynamically calibrates model learning capacity by mapping noise to adaptive dropout rates - selectively suppressing spurious fluctuations while preserving fine-grained fidelity. Extensive experiments across diverse noise regimes and open benchmarks show DropoutTS consistently boosts superior backbones' performance, delivering advanced robustness with negligible parameter overhead and no architectural modifications. Our code is available at https://github.com/CityMind-Lab/DropoutTS.