TopoPrimer: The Missing Topological Context in Forecasting Models

Hugging Face Daily Papers Papers
forecasting topological-structures persistent-homology spectral-sheaf chronos timesfm cold-start

Summary

TopoPrimer is a framework that improves forecasting accuracy by integrating global topological structures into existing models, showing significant gains in challenging scenarios like seasonal spikes and cold starts.

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.
Original Article
View Cached Full Text

Cached at: 05/19/26, 06:33 PM

Paper page - TopoPrimer: The Missing Topological Context in Forecasting Models

Source: https://huggingface.co/papers/2605.15035

Abstract

TopoPrimer enhances forecasting accuracy by incorporating global topological structures via persistent homology and spectral sheaf coordinates, demonstrating consistent improvements across diverse domains and challenging scenarios.

We introduce TopoPrimer, a framework that makes the globaltopological structureof the series population an explicit input to any forecasting model. TopoPrimer improves accuracy across diverse domains, stabilizes forecasts under seasonal demand spikes, and closes thecold-start gap. Precomputed once per domain viapersistent homologyandspectral 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 onChronosandTimesFM, 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 andfine-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.

View arXiv pageView PDFAdd to collection

Get this paper in your agent:

hf papers read 2605\.15035

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.15035 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.15035 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.15035 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.

Similar Articles

Nested Spatio-Temporal Time Series Forecasting

arXiv cs.LG

This paper proposes a nested spatiotemporal forecasting framework that uses spectral clustering to construct semantically coherent macro-level regions, which provide top-down guidance for fine-grained micro-level predictions. Experiments on high-dimensional datasets show consistent improvements over state-of-the-art baselines.