SDSC:A Structure-Aware Metric for Semantic Signal Representation Learning
This work addresses the challenge of semantic representation learning for time series data, offering a novel metric that enhances interpretability and performance, though it is incremental as it builds on existing self-supervised learning frameworks.
The authors tackled the problem of self-supervised learning for time series signals by proposing the Signal Dice Similarity Coefficient (SDSC), a structure-aware metric that improves semantic alignment over traditional distance-based methods like MSE, achieving comparable or better performance in forecasting and classification tasks, especially in in-domain and low-resource settings.
We propose the Signal Dice Similarity Coefficient (SDSC), a structure-aware metric function for time series self-supervised representation learning. Most Self-Supervised Learning (SSL) methods for signals commonly adopt distance-based objectives such as mean squared error (MSE), which are sensitive to amplitude, invariant to waveform polarity, and unbounded in scale. These properties hinder semantic alignment and reduce interpretability. SDSC addresses this by quantifying structural agreement between temporal signals based on the intersection of signed amplitudes, derived from the Dice Similarity Coefficient (DSC).Although SDSC is defined as a structure-aware metric, it can be used as a loss by subtracting from 1 and applying a differentiable approximation of the Heaviside function for gradient-based optimization. A hybrid loss formulation is also proposed to combine SDSC with MSE, improving stability and preserving amplitude where necessary. Experiments on forecasting and classification benchmarks demonstrate that SDSC-based pre-training achieves comparable or improved performance over MSE, particularly in in-domain and low-resource scenarios. The results suggest that structural fidelity in signal representations enhances the semantic representation quality, supporting the consideration of structure-aware metrics as viable alternatives to conventional distance-based methods.