发表机构
University of Luxembourg; Hassiba Benbouali University of Chlef; Université Paris Cité; École Supérieure d’Informatique（卢森堡大学; 谢莱夫哈西巴·本布阿里大学; 巴黎西岱大学; 高等计算机学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
TSGuard是一个实时框架，通过轻量级图感知时间填补模型与约束感知验证相结合，在流式时间序列中检测并填补缺失数据，支持保留或替换决策，并提供交互式解释。
AI 中文摘要
流式传感器应用经常因故障、通信丢失或环境干扰而遭受延迟或缺失观测。尽管最近的填补方法有效利用了时间和空间依赖性，但大多数要么假设可离线访问未来观测值，要么优先考虑吞吐量而不强制执行领域合理性。我们提出了TSGuard，一个用于监控、验证和填补流式时间序列中缺失值的实时演示系统。TSGuard将轻量级图感知时间填补模型与约束感知验证、回退估计和面向操作员的解释相结合。TSGuard不将填补视为孤立的预测任务，而是将其整合到更广泛的数据质量循环中：检测有问题的观测值，填补缺失值，根据物理和空间约束验证估计值，并要么将原始值保留为合理的异常，要么在违反领域约束时替换它。以环境感知作为激励场景，该演示使用户能够实时检查延迟传感器、比较填补器、定义约束并验证标记值。轻量级在线时空填补、领域感知验证和明确的保留或替换决策的组合是我们的核心贡献，而交互式解释使这些决策对操作员可检查且可操作。
英文摘要
Streaming sensor applications routinely suffer from delayed or missing observations caused by faults, communication losses, or environmental interference. Although recent imputation methods exploit temporal and spatial dependencies effectively, most either assume offline access to future observations or prioritize throughput without enforcing domain plausibility. We present TSGuard, a real-time demonstration system for monitoring, validating, and imputing missing values in streaming time series. TSGuard combines a lightweight graph-aware temporal imputation model with constraint-aware validation, fallback estimation, and operator-facing explanations. Rather than treating imputation as an isolated prediction task, TSGuard integrates it into a broader data-quality loop: detect problematic observations, impute missing values, validate estimated against physical and spatial constraints, and either retain the original value as a plausible anomaly or replace it when it violates domain constraints. Using environmental sensing as a motivating setting, the demo enables users to inspect delayed sensors, compare imputers, define constraints, and validate flagged values in real time. The combination of lightweight online spatiotemporal imputation, domain-aware validation, and explicit retain-or-replace decisions is our central contribution, while interactive explanations make these decisions inspectable and actionable. for operators.
CommentsThe 35th ACM International Conference on Information and Knowledge Management (CIKM '26), November 07--11, 2026, Rome, Italy
Journal refProceedings of the 35th ACM International Conference on Information and Knowledge Management (CIKM '26), November 07--11, 2026, Rome, Italy
