TopoPrimer: The Missing Topological Context in Forecasting Models
For time-series forecasting practitioners, TopoPrimer provides a plug-in framework that enhances accuracy and robustness, particularly in challenging regimes like seasonal spikes and cold-start scenarios.
TopoPrimer improves forecasting accuracy across diverse domains by incorporating global topological structure as an explicit input, achieving up to 7.3% MSE reduction on ECL, stabilizing forecasts under seasonal spikes (degradation within 10% vs. 50% for baselines), and reducing cold-start MAE by 27%.
We introduce TopoPrimer, a framework that makes the global topological structure of the series population an explicit input to any forecasting model. TopoPrimer improves accuracy across diverse domains, stabilizes forecasts under seasonal demand spikes, and closes the cold-start gap. Precomputed once per domain via persistent homology and spectral sheaf coordinates, TopoPrimer deploys per token for fully-trained models and as a lightweight adapter for pre-trained backbones. Of these two components, sheaf coordinates are the primary accuracy driver. Across four public benchmarks on Chronos and TimesFM, TopoPrimer consistently improves forecasting accuracy, with gains of up to 7.3% MSE on ECL. The topology advantage persists with near-identical magnitude across zero-shot and fine-tuned backbones, suggesting topology and per-series training capture complementary signals. The gains are most pronounced in difficult regimes. Under peak seasonal demand, classical and zero-shot models degrade by up to 50%, while TopoPrimer stays within 10%. At cold start with no item history, TopoPrimer reduces MAE by 27% over a topology-free baseline.