提出新基准评估合成时序表格数据的时序保真度
Seq2Synth: Benchmarking Temporal Fidelity in Synthetic Sequential Tabular Data
- 构建统一评估框架，覆盖时间戳、纵向轨迹等时序特性
- 8个生成模型在静态指标上表现优异但时序结构严重失真
- 时序保真度需独立评估，不能由静态指标推断
合成时序表格数据在隐私保护共享与研究中日益重要，但传统表格评估指标常忽略时序结构。现有单表和关系型评估协议多将记录简化为静态分布，导致关键时序属性评估不足。我们提出 Seq2Synth，一个统一的评估基准，其分类体系可识别适用的评估维度，涵盖时间戳、横截面、纵向及结构保真度，以及轨迹感知的效用与隐私性。在来自13个数据集基准的7个核心数据集和8个生成器上，即使模型在静态保真度接近完美，仍存在重复时间戳、不规则时间间隔和观测网格不完整等问题。此外，静态与时序感知排名显著不同，表明时序保真度必须直接评估，而非通过静态或关系评分推断。项目主页与在线附录见：https://seq2synth.github.io/。
原文摘要 · Abstract (English)
Synthetic sequential tabular data are increasingly used for privacy-preserving data sharing and research, yet conventional tabular metrics often overlook temporal structure. Existing single-table and relational evaluation protocols largely collapse records into static distributions, leaving key temporal properties insufficiently evaluated. We introduce Seq2Synth, a unified benchmark for assessing these properties. Its taxonomy characterizes temporal and schema properties to determine applicable evaluations, covering timestamp, cross-sectional, longitudinal, and structural fidelity, alongside trajectory-aware utility and privacy. Across seven core datasets from a 13-dataset benchmark and eight generators, models with near-perfect static fidelity still violate basic temporal constraints, producing duplicate timestamps, irregular intervals, and incomplete observation grids. Moreover, static and temporal-aware rankings diverge substantially, showing that temporal fidelity must be evaluated directly rather than inferred from static or relational scores. Project page and online appendices are available at: https://seq2synth.github.io/.
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。