用单次前向传播实现多任务时间序列补全与预测，适合数据少的场景。
Temporal Variational Implicit Neural Representations
- 将隐式神经表示与潜在变量模型结合，学习信号特异的连续生成函数分布。
- 单个模型在多个数据集上实现低误差补全，部分任务误差降低一个数量级。
- 无需训练或微调，适合小样本、实时应用，计算高效且可扩展。
我们提出时序变分隐式神经表示（TV-INRs），一种用于建模不规则多变量时间序列的概率框架，支持高效准确的个体化补全与预测。通过将隐式神经表示与潜在变量模型结合，TV-INRs 学习在信号特异性协变量条件下，时间连续生成函数的分布。与现有 INR 方法需大量训练、微调或元学习不同，本方法仅通过一次前向传播即可实现精确的个体化预测。实验表明，仅使用一个 TV-INRs 实例，即可在多种补全与预测任务中取得高精度表现，提供一种计算高效且可扩展的现实应用解决方案。在低数据环境下表现尤为出色，在多个数据集上实现显著更低的补全误差，部分任务误差降低一个数量级。
原文摘要 · Abstract (English)
We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient and accurate individualized imputation and forecasting. By integrating implicit neural representations with latent variable models, TV-INRs learn distributions over time-continuous generator functions conditioned on signal-specific covariates. Unlike existing INR approaches that require extensive training, fine-tuning or meta-learning, our method achieves accurate individualized predictions through a single forward pass. Our experiments demonstrate that with a single TV-INRs instance, we can accurately solve diverse imputation and forecasting tasks, offering a computationally efficient and scalable solution for real-world applications. TV-INRs performs particularly well in low-data regimes, where on several datasets it achieves substantially lower imputation error, including order-of-magnitude improvements.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。