TimeBlocks: Foundational and Continual Time-Series Blockbase -- Extended Version
The ongoing digitization has led to a proliferation of time-series data streams that monitor a variety of processes, from which valuable insights may be obtained. Further, the emergence of successful foundational language models begs the question of whether it is possible to achieve time-series models with the foundational properties of handling multiple tasks, while being sufficiently lightweight to allow real-time data stream processing. Existing foundational time-series models are often large and only effective in offline settings without stringent time and computational constraints, and where repeated model calibration is not needed. However, when applied to data streams, these models are ineffective due to their size and lack of support for continual calibration, which compromise their ability to deliver accurate real-time responses, their durability, and their deployability in hardware-limited settings. We propose TimeBlocks to enable versatile time-series processing by facilitating the efficient building of lightweight models suitable for multiple tasks under variable conditions. In particular, the method maintains a pool of interchangeable and modular model blocks that can be used to construct new time-series models. When presented with specific time-series data, a routing strategy iteratively selects the most suitable blocks to construct a lightweight and accurate model for the data. We equip TimeBlocks with a method called StreamCore to build a representative small subset of the data stream, which preserves a guaranteed approximation of the stream over time, enabling continual model calibration. An experimental study on multiple data sets and covering multiple tasks shows that TimeBlocks enables to build models capable of outperforming existing baselines.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Time-MQA: Time Series Multi-Task Question Answering with Context Enhancement
Time series data are foundational in finance, healthcare, and energy domains. However, most existing methods and datasets remain focused on a narrow spectrum of tasks, such as forecasting or anomaly detection. To bridge …
Anomaly DetectionNatural Language QueriesOpen-Ended Question AnsweringQuestion Answering+1TSP-OCS: A Time-Series Prediction for Optimal Camera Selection in Multi-Viewpoint Surgical Video Analysis
Recording the open surgery process is essential for educational and medical evaluation purposes; however, traditional single-camera methods often face challenges such as occlusions caused by the surgeon's head and body, …
PredictionTime SeriesTime Series PredictionLow-Rank Adaptation of Time Series Foundational Models for Out-of-Domain Modality Forecasting
Low-Rank Adaptation (LoRA) is a widely used technique for fine-tuning large pre-trained or foundational models across different modalities and tasks. However, its application to time series data, particularly within foun…
Time SeriesBenchmarking Catastrophic Forgetting Mitigation Methods in Federated Time Series Forecasting
Catastrophic forgetting (CF) poses a persistent challenge in continual learning (CL), especially within federated learning (FL) environments characterized by non-i.i.d. time series data. While existing research has large…
Time Series ForecastingFederated LearningContinual LearningUNICON: UNIfied CONtinual Learning for Medical Foundational Models
Foundational models are trained on extensive datasets to capture the general trends of a domain. However, in medical imaging, the scarcity of data makes pre-training for every domain, modality, or task challenging. Conti…
Continual Learning