结构感知图弃权（不执行）用于可靠的择时预测
Structure-Aware Graph Abstention for Reliable Selective Forecasting
查看机构详情
- University of New South Wales（新南威尔士大学）
- Zayed University（扎耶德大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
针对多变量择时预测，提出基于学习稀疏图与Dirichlet结构能量的弃权（不执行）门控，在匹配覆盖率下较TEM降低MSE，增益在跨变量结构信息丰富时最大。
中文摘要 AI 辅助
择时预测在保留覆盖率预算下对高风险测试窗口进行弃权（不执行）。现有门控机制如TEM（Brusokas等人，2025）将每个预测整体评分；对于多变量输出，轨迹可能看起来合理但违反变量间的依赖关系。我们将实例级合理性和关系一致性视为不同的可靠性轴，并通过学习到的稀疏图和Dirichlet式结构能量E_struct实现后者，训练时采用误差加权图正则化和分数误差对齐。在七个长时程基准和四个骨干网络上，结构门控在匹配覆盖率下通常比TEM降低择时MSE，最大增益出现在跨变量结构在我们的基准中更具信息性的地方；增益并非普遍存在，表明这是一种互补的弃权（不执行）信号。表1是协议A排名诊断（种子2024）；三个种子的可部署协议B在对齐子集上见表3（完整验证到测试网格见附录A）。
英文摘要
Selective forecasting abstains on high-risk test windows under a retained-coverage budget. Existing gates such as TEM (Brusokas et al., 2025) score each forecast as a whole; for multivariate outputs, trajectories can look plausible while violating dependencies among variables. We treat instance-level plausibility and relational consistency as distinct reliability axes and operationalize the latter via a learned sparse graph and a Dirichlet-style structural energy E_struct, trained with error-weighted graph regularization and score-error alignment. On seven long-horizon benchmarks and four backbones, structural gating often reduces selective MSE versus TEM at matched coverage, with the largest gains where cross-variable structure appears more informative in our benchmarks; gains are not universal, indicating a complementary abstention signal. Table 1 is a Protocol A ranking diagnostic (seed 2024); three-seed deployable Protocol B on an aligned subset is in Table 3 (full validation-to-test grids: Appendix A).
