Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Models

2025-11-07

AI Summary

Existing time-series foundation models (TSFMs) exhibit substantial performance variability across tasks, domains, and forecasting horizons due to heterogeneous training protocols and data distributions, yet their complementary strengths remain systematically unexploited. Method: We propose Synapse—the first dynamic arbitration framework for TSFMs—featuring context-aware model selection and prediction-range distribution analysis to adaptively weight multi-model outputs; it further incorporates a quantile-based ensemble mechanism to produce robust probabilistic forecasts. Results: Extensive experiments demonstrate that Synapse consistently outperforms individual TSFMs and state-of-the-art ensemble methods across multiple benchmarks, achieving superior generalization and stability. To our knowledge, this is the first work to systematically validate that complementary knowledge among TSFMs can be effectively modeled and leveraged for enhanced forecasting.

Technology Category

• Machine Learning: Ensemble Methods
• Reasoning under Uncertainty: Relational Probabilistic Models
• Multiagent Systems: Other Foundations of Multi Agent Systems

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Pre-trained Time Series Foundational Models (TSFMs) represent a significant advance, capable of forecasting diverse time series with complex characteristics, including varied seasonalities, trends, and long-range dependencies. Despite their primary goal of universal time series forecasting, their efficacy is far from uniform; divergent training protocols and data sources cause individual TSFMs to exhibit highly variable performance across different forecasting tasks, domains, and horizons. Leveraging this complementary expertise by arbitrating existing TSFM outputs presents a compelling strategy, yet this remains a largely unexplored area of research. In this paper, we conduct a thorough examination of how different TSFMs exhibit specialized performance profiles across various forecasting settings, and how we can effectively leverage this behavior in arbitration between different time series models. We specifically analyze how factors such as model selection and forecast horizon distribution can influence the efficacy of arbitration strategies. Based on this analysis, we propose Synapse, a novel arbitration framework for TSFMs. Synapse is designed to dynamically leverage a pool of TSFMs, assign and adjust predictive weights based on their relative, context-dependent performance, and construct a robust forecast distribution by adaptively sampling from the output quantiles of constituent models. Experimental results demonstrate that Synapse consistently outperforms other popular ensembling techniques as well as individual TSFMs, demonstrating Synapse's efficacy in time series forecasting.

Problem

• Arbitrating complementary expertise among diverse pre-trained time series foundational models
• Addressing variable performance across forecasting tasks, domains, and horizons
• Dynamically weighting and combining model outputs for robust time series forecasting

Innovation

• Adaptive arbitration of complementary expertise
• Dynamic weight assignment based on performance
• Robust forecast via adaptive quantile sampling