TopoPrimer: The Missing Topological Context in Forecasting Models
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.
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
TopoBrick: Agentic Topology Sampling of Exogenous Variables for Zero-Shot Building IoT Forecasting
TopoBrick is a training-free framework for zero-shot building IoT forecasting that uses building knowledge graphs and an agentic topology sampler to select target-specific exogenous variables. It outperforms strong zero-shot foundation-model baselines and remains competitive with fully trained building-specific models.
TopoTuner: Topological Finetuning of Large Language Models
Introduces TopoTuner, a topology-guided fine-tuning framework that selectively freezes attention projection matrices by measuring topological drift via Wasserstein distances between persistence diagrams. It achieves competitive performance to full fine-tuning while training only 1-2% of parameters and outperforms LoRA in most settings.
TopoExplore: Topological Discrimination for Archive-Based Exploration
TopoExplore augments Go-Explore with topological detection of enclosed regions to avoid wasting budget on sealed areas, achieving speedups on MiniGrid and HM3D environments.
Topolines
Topolines is a tool for generating topologic contours.
TopoEvo: A Topology-Aware Self-Evolving Multi-Agent Framework for Root Cause Analysis in Microservices
TopoEvo is a topology-aware self-evolving multi-agent framework for root cause analysis in microservices that couples graph representation learning with structured, topology-constrained reasoning. It achieves absolute improvements of up to 3.44% in root cause localization accuracy and boosts fault-type classification performance by 4.39% to 16.81% across diverse datasets.