Fracast-0：仅85K参数的时间序列基础模型的分形权重共享
Fracast-0: Fractal Weight Sharing for a Time Series Foundation Model with Only 85K Parameters
浏览论文内容
中文总结 AI 辅助
Fracast-0通过分形权重共享在时间尺度间重用算子，以85K参数实现多领域概率预测，在GIFT-Eval上以更小参数达到可比精度，验证了跨尺度压缩的有效性。
中文摘要 AI 辅助
时间序列基础模型必须保持多领域广度、概率输出和多个时间尺度，但当每个尺度获得单独表示时，参数数量会增加。我们引入Fracast-0，一个概率预测基础模型，利用时间自相似性在尺度间重用单个算子。一个无参数检测器提取显著的季节结构。编码器沿几何膨胀阶梯应用共享局部块，并带有尺度条件，而解码器将上下文收集的状态与显式季节未来状态结合，并沿另一阶梯重用第二个块，然后输出九个分位数。在六个语料库上的预训练在85,001个参数内保持了多领域广度。在97个GIFT-Eval配置上，无需按数据集微调，Fracast-0是28个评估检查点中最小的，并在聚合参数-精度平面上保持非支配，MASE为0.808，WQL为0.564。它比TinyCast少使用42.0%的参数，TinyCast的MASE和WQL分别低4.2%和3.3%。这些结果支持跨尺度权重重用作为进一步压缩时间序列基础模型的实用途径。
英文摘要
Time series foundation models must preserve multi-domain breadth, probabilistic output, and multiple temporal scales, but parameter count grows when each scale receives a separate representation. We introduce Fracast-0, a probabilistic forecasting foundation model that exploits temporal self-similarity to reuse one operator across scales. A parameter-free detector extracts significant seasonal structure. The encoder applies a shared local block along a geometric dilation ladder with scale conditioning, while the decoder combines context-gathered states with an explicit seasonal future state and reuses a second block along another ladder before emitting nine quantiles. Pretraining across six corpora preserves multi-domain breadth within 85,001 parameters. On 97 GIFT-Eval configurations without per-dataset fine-tuning, Fracast-0 is the smallest of 28 evaluated checkpoints and remains non-dominated in the aggregate parameter-accuracy plane with MASE 0.808 and WQL 0.564. It uses 42.0% fewer parameters than TinyCast, whose MASE and WQL are 4.2% and 3.3% lower. These results support cross-scale weight reuse as a practical route to further time series foundation model compression.
