Workshop: The First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward

Self-Supervised Time Series Representation Learning with Temporal-Instance Similarity Distillation

Ainaz Hajimoradlou · Ainaz Hajimoradlou · Leila Pishdad · Leila Pishdad · Frederick Tung · Frederick Tung · Maryna Karpusha · Maryna Karpusha


We propose a self-supervised method for pre-training universal time series representations in which we learn contrastive representations using similarity distillation along the temporal and instance dimensions. We analyze the effectiveness of both dimensions, and evaluate our pre-trained representations on three downstream tasks: time series classification, anomaly detection, and forecasting.

Chat is not available.