EXAONE Demand 1.0：用于需求预测的时间序列基础模型
EXAONE Demand 1.0: A Time Series Foundation Model for Demand Forecasting
浏览论文内容
中文总结 AI 辅助
针对需求数据特性，提出基于需求专用语料库和需求感知适配器的时间序列基础模型EXAONE Demand，在22个数据集上优于36个TSFM，真实数据带来额外增益。
中文摘要 AI 辅助
时间序列基础模型（TSFMs）在来自不同领域的序列上进行预训练，其中需求序列仅占一小部分。需求数据具有此类语料库很少包含的特性：历史记录短、频繁出现零值、因缺货导致的截断，以及序列未记录的外生事件。为此，我们提出了EXAONE Demand，它建立在1）一个需求专用语料库和2）一个需求感知适配器之上。对于语料库，我们从73个来源汇集了1130万条序列和484亿个观测值，并且一个合成生成器提供了开放需求数据代表性不足的行为。对于适配器，我们将低秩分支附加到一个冻结的通用领域骨干网络上，每个分支对应四类需求（平滑、间歇、不稳定和块状）中的一类，并且一个读取输入序列的八个无尺度统计量的路由器决定每个分支的贡献程度。我们构建了EXAONE Demand的两个版本，一个在真实世界和合成需求上共同训练，另一个仅在合成语料库上训练。在22个保留数据集上，两个版本均优于36个TSFMs，并且真实世界需求在合成数据基础上带来了额外增益。
英文摘要
Time series foundation models (TSFMs) are pretrained on series from diverse domains, where demand series make up only a small fraction. Demand data has properties that such corpora rarely contain: Short histories, frequent zeros, censoring by stock-outs, and exogenous events that the series does not record. To this end, we propose EXAONE Demand, built on 1) a demand-specific corpus and 2) a demand-aware adapter. For the corpus, we assemble 11.3M series and 48.4B observations from 73 sources, and a synthetic generator supplies the behaviour that open demand data under-represents. For the adapter, we attach low-rank branches to a frozen general-domain backbone, one for each of the four demand classes (smooth, intermittent, erratic, and lumpy), and a router that reads eight scale-free statistics of the input series decides how much each branch contributes. We build EXAONE Demand in two versions, one trained on real-world and synthetic demand together and one trained on the synthetic corpus alone. On 22 held-out datasets, both versions outperform 36 TSFMs, and real-world demand adds a gain over synthetic data alone.
发表机构
- LG AI Research（LG AI研究院）
机构由 AI 辅助整理，请以论文原文为准。
