# TopoPrimer：预测模型中缺失的拓扑上下文

- 来源：Apple Machine Learning Research（RSS）
- 发布时间：2026-07-06 08:00
- AIHOT 分数：50
- AIHOT 链接：https://aihot.virxact.com/items/cmr9jb1wn007dihe88r014iex
- 原文链接：https://machinelearning.apple.com/research/topoprimer-topological-context

## AI 摘要

TopoPrimer 框架将序列群体的全局拓扑结构作为显式输入加入预测模型。通过持续同调与谱坐标预计算，可部署为全训练模型的 per-token 输入或预训练骨干的轻量适配器。在 Chronos 和 TimesFM 的四个基准上，TopoPrimer 在 ECL 上最高提升 7.3% MSE，零样本与微调效果相近。面对季节性需求峰值，传统模型误差退化达 50%，TopoPrimer 控制在 10% 以内；冷启动场景下 MAE 降低 27%。

## 正文

research area Data Science and Annotation, research area Methods and Algorithms

content type paperpublished July 2026

TopoPrimer: The Missing Topological Context in Forecasting Models

AuthorsZara Zetlin, Kayhan Moharreri, Maria Safi

View publication

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.

Related readings and updates.

BayesCNS: A Unified Bayesian Approach to Address Cold Start and Non-Stationarity in Search Systems at Scale

December 11, 2024research area Knowledge Bases and Search, research area Methods and Algorithmsconference AAAI

Information Retrieval (IR) systems used in search and recommendation platforms frequently employ Learning-to-Rank (LTR) models to rank items in response to user queries. These models heavily rely on features derived from user interactions, such as clicks and engagement data. This dependence introduces cold start issues for items lacking user engagement and poses challenges in adapting to non-stationary shifts in user behavior over time. We…

Learning Insulin-Glucose Dynamics in the Wild

August 6, 2020research area Healthconference ML for Healthcare

We develop a new model of insulin-glucose dynamics for forecasting blood glucose in type 1 diabetics. We augment an existing biomedical model by introducing time-varying dynamics driven by a machine learning sequence model. Our model maintains a physiologically plausible inductive bias and clinically interpretable parameters — e.g., insulin sensitivity — while inheriting the flexibility of modern pattern recognition algorithms. Critical to…

Discover opportunities in Machine Learning.

Our research in machine learning breaks new ground every day.

Work with us