ProtoSSL: Interpretable Prototype Learning from Unlabeled Time-Series Data

TL;DR

ProtoSSL is a self-supervised framework that learns interpretable prototypes from unlabeled time-series data, improving label efficiency and interpretability in downstream tasks like ECG and audio classification.

Contribution

It introduces a novel approach to separate motif discovery from label alignment, enabling reusable prototypes from unlabeled data adaptable to various tasks.

Findings

ProtoSSL outperforms supervised prototypes in low-data regimes.

Prototypes learned are more interpretable and human-judged more favorable.

Framework extends successfully to audio classification.

Abstract

In time-series domains where both predictive performance and interpretability are essential, deep neural networks achieve strong results but provide limited insight into how their predictions are made. Projection-based prototype networks address this limitation by grounding predictions in similarity to representative training examples, enabling case-based explanations and global prototype inspection. However, existing approaches rely on label supervision, tying prototypes to a specific task and requiring large labeled datasets. We introduce ProtoSSL, a novel framework for learning interpretable, projection-based prototypes from unlabeled time-series data and adapting them to downstream tasks. Our key idea is to separate motif discovery from label alignment. ProtoSSL first learns a reusable prototype bank using a self-supervised objective applied directly to prototype activations, and then aligns these prototypes to downstream tasks through an efficient assignment procedure. Across six electrocardiography (ECG) datasets, ProtoSSL improves label efficiency, outperforming supervised prototype baselines in low-data regimes with as few as 256 labeled examples; with fine-tuning, ProtoSSL outperforms supervised prototype baselines at full dataset scale. In a human evaluation study, ProtoSSL produces prototypes and prototype-based explanations that are judged more favorably than those learned with direct label supervision. We further show that the framework extends to audio classification. Thus, ProtoSSL enables both learning generalizable prototypes from unlabeled data before the downstream label space is known, and subsequent assignment of interpretable, projection-grounded prototypes to new time-series tasks.