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
Abstract
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.
Successful Page Load