Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization
About
Learning meaningful representations from medical time series (MedTS) such as ECG or EEG signals is a critical challenge. These signals are often high-dimensional, variable-length and rife with noise. Existing self-supervised approaches, such as Masked Autoencoders (MAEs) are highly effective for pre-training general-purpose encoders. However, they do not explicitly learn compact and semantically interpretable latent representations, typically relying on heuristic aggregation strategies such as global average pooling or a designated [CLS] token. We propose a novel framework that compresses a variable-length MedTS into a fixed-size set of $k$ latent Fingerprint Tokens. Our architecture employs a cross-attention bottleneck to generate these tokens and is trained with a dual-objective function. The first objective is a reconstruction loss, which ensures the tokens are \textit{sufficient statistics} for the original data. The second, a diversity penalty based on the Total Coding Rate (TCR), explicitly minimizes the redundancy between tokens, encouraging them to become statistically \textit{disentangled} representations. We present the theoretical justification for our method, framing it as a novel \textbf{Disentangled Rate-Distortion} problem. This approach produces a low-dimensional, interpretable, and sample-efficient representation, where each token is encouraged to capture an independent factor of variation, paving the way for more robust digital biomarkers.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Medical Time Series Classification | PTB-XL 5-Classes | Accuracy73.98 | 38 | |
| Medical Time Series Classification | ADFTD 3-Classes | Accuracy (%)53.91 | 38 | |
| Medical Time Series Classification | PTB 2-Classes | Accuracy85.39 | 12 | |
| Medical Time Series Classification | APAVA 2-Classes | Accuracy80.29 | 12 | |
| Medical Time Series Classification | SleepEDF 5-Classes | Accuracy84.18 | 12 | |
| Medical Time Series Classification | FLAAP 10-Classes | Accuracy77.59 | 12 | |
| Medical Time Series Classification | UCI-HAR 6-Classes | Accuracy90.87 | 12 |