FedChronos：用于隐私保护商品价格预测的时间序列基础模型联邦微调
FedChronos: Federated Fine-Tuning of Time-Series Foundation Models for Privacy-Preserving Commodity Price Forecasting
AI总结：
FedChronos是用于时间序列基础模型联邦微调的框架，结合LoRA与差分隐私，在非IID商品价格联邦预测中实现隐私与准确性互补，适配边缘部署
AI中文摘要：
Chronos等时间序列基础模型（TSFM）已在各领域展现出强大的预测能力，但将其适配到机构分散的场景中仍未得到探索——这类场景因监管、竞争或主权限制无法集中数据。我们提出FedChronos框架，用于对已预训练的TSFM进行联邦参数高效微调，现有联邦时间序列研究未涉及该场景，此前方法要么从头预训练，要么对齐原型而非适配固定骨干。我们的方法将低秩适配（LoRA）应用于Chronos-T5骨干，通过FedAvg和FedProx在分布式客户端训练，仅传输轻量适配器权重（每轮384KB，比全模型交换减少86倍）。我们在印度9个邦的15个农业市场的每日商品价格上评估FedChronos，这是一个天然的非独立同分布（non-IID）联邦场景，发现单纯的LoRA微调会在每个客户端的小数据集上严重过拟合，性能低于零样本表现。我们进一步观察到差分隐私（DP）噪声可作为隐式正则化来抵消这种过拟合：实验中最强配置（ε=5）使平均绝对百分比误差（MAPE）比零样本降低31%，比最佳传统基准降低26%，同时通过每轮(ε,δ)-差分隐私限制每轮的信息泄露。由于模型紧凑且更新量小，该方法也适用于网络链路和客户端设备均受约束的边缘AI部署。总体而言，我们的发现表明，在联邦TSFM微调中，隐私和准确性是互补而非相互竞争的目标。
英文摘要：
Time-series foundation models (TSFMs) such as Chronos have demonstrated strong forecasting capabilities across domains, yet adapting them to institutionally fragmented settings, where data cannot be centralized due to regulatory, competitive, or sovereignty constraints, remains unexplored. We introduce FedChronos, a framework for federated parameter-efficient fine-tuning of an already pre-trained TSFM, a setting that existing federated time-series work has not addressed, since prior methods either pre-train from scratch or align prototypes rather than adapt a fixed backbone. Our approach applies Low-Rank Adaptation (LoRA) to the Chronos-T5 backbone and trains across distributed clients using FedAvg and FedProx, transmitting only lightweight adapter weights (384~KB per round, an 86$\times$ reduction over full-model exchange). We evaluate FedChronos on daily commodity prices from 15 Indian agricultural markets across 9 states, a naturally non-IID federated setting, and find that naïve LoRA fine-tuning overfits substantially on small per-client datasets, dropping below zero-shot performance. We further observe that differential privacy (DP) noise can act as implicit regularization and counteract this overfitting: in our experiments the strongest configuration ($\varepsilon = 5$) reduces mean absolute percentage error (MAPE) by 31% over zero-shot and 26% over the best traditional baseline, while bounding each round's information leakage via per-round $(\varepsilon, δ)$-differential privacy. Because the model is compact and the updates are small, the approach also suits edge AI deployments where both the network link and the client device are constrained. Overall, our findings suggest that privacy and accuracy can be complementary rather than competing objectives in federated TSFM fine-tuning.
