analiza aiqbench
TERN introduces a novel memory mechanism combining delta-rule fast-weight decay with explicit seasonal references to improve influenza forecasting accuracy. By dynamically gating information based on local epidemic phases, the model effectively handles shifting wave patterns and stale data that typically hinder standard graph neural networks. This approach demonstrates significant performance gains over existing benchmarks, offering a robust tool for public health surveillance systems reliant on precise predictive modeling.
TERN: A Delta-rule Memory with a Seasonal Reference and Online Adaptation for Epidemic Forecasting
arXiv:2609.18407v1 Announce Type: cross Abstract: Weekly influenza surveillance counts guide vaccine distribution and public-health alerts, yet they are hard to forecast. Each region offers only a few seasons, waves shift in timing and height every year, and information that helps while a wave grows misleads after its peak, whereas last season's shape stays informative for a year. Existing epidemic graph models and general forecasters read a short fixed window and treat all past information alike, so they neither exploit earlier seasons nor discard stale associations when the epidemic phase changes. To address these limitations, we propose TERN, a forecaster built around a delta-rule fast-weight memory that decays channel-wise and erases along a learned address under gates driven by local epidemic-phase features, combined with an explicit seasonal reference and online adaptation. On three Cola-GNN influenza benchmarks, TERN outperformed epidemic graph models and general forecasters, matched or exceeded seasonal references, and a controlled comparison confirmed the contribution of the memory itself.
Abstract:Weekly influenza surveillance counts guide vaccine distribution and public-health alerts, yet they are hard to forecast. Each region offers only a few seasons, waves shift in timing and height every year, and information that helps while a wave grows misleads after its peak, whereas last season's shape stays informative for a year. Existing epidemic graph models and general forecasters read a short fixed window and treat all past information alike, so they neither exploit earlier seasons nor discard stale associations when the epidemic phase changes. To address these limitations, we propose TERN, a forecaster built around a delta-rule fast-weight memory that decays channel-wise and erases along a learned address under gates driven by local epidemic-phase features, combined with an explicit seasonal reference and online adaptation. On three Cola-GNN influenza benchmarks, TERN outperformed epidemic graph models and general forecasters, matched or exceeded seasonal references, and a controlled comparison confirmed the contribution of the memory itself.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2609.18407 [cs.LG]
(or arXiv:2609.18407v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.18407 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 251 cuvinte
Subiecte conexe
Tech Hits a Wall & Netflix Plunges | The Motley Fool
fool.com · 25 iul. 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · 27 aug. 2026
Optimizing ATOM and vLLM-ATOM for High-Interactivity Inference
AMD · 1 sept. 2026
LiveLaw Supreme Court Half-Yearly Digest: January - June 2026 [Part 2]
livelaw.in · 13 sept. 2026