Distilling Time Series Foundation Models for Efficient Forecasting
Time Series foundation models (TSFMs) deliver strong forecasting performance through large-scale pretraining, but their large parameter sizes make deployment costly. While knowledge distillation offers a natural and effective approach for model compression, techniques developed for general machine learning tasks are not directly applicable to time series forecasting due to the unique characteristics. To address this, we present DistilTS, the first distillation framework specifically designed for TSFMs. DistilTS addresses two key challenges: (1) task difficulty discrepancy, specific to forecasting, where uniform weighting makes optimization dominated by easier short-term horizons, while long-term horizons receive weaker supervision; and (2) architecture discrepancy, a general challenge in distillation, for which we design an alignment mechanism in the time series forecasting. To overcome these issues, DistilTS introduces horizon-weighted objectives to balance learning across horizons, and a temporal alignment strategy that reduces architectural mismatch, enabling compact models. Experiments on multiple benchmarks demonstrate that DistilTS achieves forecasting performance comparable to full-sized TSFMs, while reducing parameters by up to 1/150 and accelerating inference by up to 6000x. Code is available at: https://github.com/itsnotacie/DistilTS-ICASSP2026.
Code (0)
등록된 구현이 없습니다.
Tasks
Time Series ForecastingKnowledge DistillationModel CompressionSimilar Papers 제목 키워드 기반
TimeFound: A Foundation Model for Time Series Forecasting
We present TimeFound, an encoder-decoder transformer-based time series foundation model for out-of-the-box zero-shot forecasting. To handle time series data from various domains, TimeFound employs a multi-resolution patc…
DecoderTime SeriesTime Series ForecastingReverso: Efficient Time Series Foundation Models for Zero-shot Forecasting
Learning time series foundation models has been shown to be a promising approach for zero-shot time series forecasting across diverse time series domains. Insofar as scaling has been a critical driver of performance of f…
Time Series ForecastingData AugmentationLag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
Over the past years, foundation models have caused a paradigm shift in machine learning due to their unprecedented capabilities for zero-shot and few-shot generalization. However, despite the success of foundation models…
DecoderProbabilistic Time Series ForecastingTime SeriesTime Series Forecasting+1Toto: Time Series Optimized Transformer for Observability
This technical report describes the Time Series Optimized Transformer for Observability (Toto), a new state of the art foundation model for time series forecasting developed by Datadog. In addition to advancing the state…
Time SeriesTime Series ForecastingHow Foundational are Foundation Models for Time Series Forecasting?
Foundation Models are designed to serve as versatile embedding machines, with strong zero shot capabilities and superior generalization performance when fine-tuned on diverse downstream tasks. While this is largely true …
Time Series Forecasting