HierCVAE通过分层注意力提升多尺度时间建模精度与不确定性量化。
HierCVAE: Hierarchical Attention-Driven Conditional Variational Autoencoders for Multi-Scale Temporal Modeling
- 分层注意力+条件变分自编码，捕捉局部、全局与跨时域依赖
- 在能耗数据上预测准确率提升15%-40%，长期预测更优
- 适合需要精准预测与置信度评估的复杂时序任务
复杂系统中的时间建模需同时捕捉多尺度依赖关系并处理内在不确定性。我们提出HierCVAE，一种融合分层注意力机制与条件变分自编码器的新架构。该模型采用三层注意力结构（局部、全局、跨时域），结合多模态条件编码，以捕获时间、统计及趋势信息。潜空间中引入ResFormer模块，并通过预测头实现显式不确定性量化。在能源消耗数据集上的实验表明，HierCVAE相比前沿方法预测准确率提升15%-40%，且不确定性校准表现更优，尤其在长期预测与复杂多变量依赖场景下表现突出。
原文摘要 · Abstract (English)
Temporal modeling in complex systems requires capturing dependencies across multiple time scales while managing inherent uncertainties. We propose HierCVAE, a novel architecture that integrates hierarchical attention mechanisms with conditional variational autoencoders to address these challenges. HierCVAE employs a three-tier attention structure (local, global, cross-temporal) combined with multi-modal condition encoding to capture temporal, statistical, and trend information. The approach incorporates ResFormer blocks in the latent space and provides explicit uncertainty quantification via prediction heads. Through evaluations on energy consumption datasets, HierCVAE demonstrates a 15-40% improvement in prediction accuracy and superior uncertainty calibration compared to state-of-the-art methods, excelling in long-term forecasting and complex multi-variate dependencies.
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。