ProtoSSL: Interpretable Prototype Learning from Unlabeled Time-Series Data

2026-05-07

AI Summary

This work addresses the poor interpretability of existing deep time series models and the reliance of prototype-based methods on labeled data, which hinders learning generalizable prototypes under label scarcity. The authors propose ProtoSSL, a novel framework that, for the first time, enables unsupervised discovery of reusable and interpretable time series prototypes through self-supervised learning, decoupling prototype learning from downstream tasks. By integrating a projective prototypical network, prototype activation optimization, and a task-adaptive assignment mechanism, ProtoSSL achieves superior performance over supervised prototypical methods on six ECG datasets using only 256 labeled samples. Human evaluations confirm that its explanations are more trustworthy, and the approach successfully generalizes to audio classification tasks.

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.

Problem

• prototype learning
• time-series
• interpretability
• self-supervised learning
• label efficiency

Innovation

• prototype learning
• self-supervised learning
• interpretable AI
• time-series representation
• label efficiency