发表机构
Neurogica Inc.; LTS, Inc.（Neurogica公司; LTS公司）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TERN提出一种带季节参考和在线自适应的增量规则记忆预测器，在流感基准上超越现有模型，验证了记忆机制的有效性。
AI 中文摘要
每周流感监测计数指导疫苗分发和公共卫生警报，然而它们难以预测。每个地区仅提供几个季节，波次每年在时间和高度上都会变化，并且在波次增长期间有帮助的信息在峰值后会误导，而上一季度的形状在一年内仍具有参考价值。现有的流行病图模型和通用预测器读取一个固定的短窗口，并同等对待所有过去的信息，因此它们既不能利用更早的季节，也不能在流行病阶段变化时丢弃过时的关联。为解决这些局限性，我们提出了TERN，一种预测器，其核心是一个增量规则快速权重记忆，该记忆在局部流行病阶段特征驱动的门控下，沿学习到的地址进行通道级衰减和擦除，并结合显式的季节参考和在线自适应。在三个Cola-GNN流感基准上，TERN优于流行病图模型和通用预测器，达到或超过季节参考，并且一项受控比较证实了记忆本身的贡献。
英文摘要
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.
