基于Transformer的表格数据合成中LLM敏感性测量
Measuring LLM Sensitivity in Transformer-based Tabular Data Synthesis
AI总结：
本研究评估了Transformer-based TDS工具（GReaT和REaLTabFormer）对超参数的敏感性，发现REaLTabFormer在大型数据集上平衡了数据质量与计算成本，但运行时间仍较高。
摘要：
合成表格数据用于隐私保护的数据共享和数据驱动的模型开发。然而，其有效性在很大程度上取决于所使用的表格数据合成（TDS）工具。近期研究表明，基于Transformer的模型在数据质量方面优于其他最先进的模型，如生成对抗网络（GANs）和扩散模型。然而，基于Transformer的模型也带来了高昂的计算成本，这使得它们在拥有产消者硬件的最终用户中有时不可行。本研究对超参数（如层数或隐藏维度）的选择如何影响合成数据的质量和计算性能进行了敏感性评估。该评估在GReaT和REaLTabFormer两个工具上进行，评估了10种在架构类型和深度上有所不同的模型设置。我们从三个维度评估敏感性：运行时间、机器学习（ML）效用以及与真实数据分布的相似性。实验在四个真实世界数据集上进行。我们的研究结果显示，运行时间与超参数数量成正比，较浅的配置完成得更快。GReaT始终比REaLTabFormer实现更低的运行时间，并且仅在最大的数据集上它们具有可比的运行时间。对于小数据集，两种工具都能实现具有高效用和最佳相似性的合成数据，但在较大的数据集上，只有REaLTabFormer能保持强大的效用和相似性。因此，具有轻量级LLM的REaLTabFormer提供了最佳平衡，因为它在降低计算需求的同时保持了数据质量。尽管如此，其运行时间仍然高于GReaT和其他TDS工具，这表明效率提升是可能的，但只能达到一定水平。
英文摘要：
Synthetic tabular data is used for privacy-preserving data sharing and data-driven model development. Its effectiveness, however, depends heavily on the used Tabular Data Synthesis (TDS) tool. Recent studies have shown that Transformer-based models outperform other state-of-the-art models such as Generative Adversarial Networks (GANs) and Diffusion models in terms of data quality. However, Transformer-based models also come with high computational costs, making them sometimes unfeasible for end users with prosumer hardware. This study presents a sensitivity assessment on how the choice of hyperparameters, such as number of layers or hidden dimension affects the quality of the resultant synthetic data and the computational performance. It is performed across two tools, GReaT and REaLTabFormer, evaluating 10 model setups that vary in architecture type and depth. We assess the sensitivity on three dimensions: runtime, machine learning (ML) utility, and similarity to real data distributions. Experiments were conducted on four real-world datasets. Our findings reveal that runtime is proportional to the number of hyperparameters, with shallower configurations completing faster. GReaT consistently achieves lower runtimes than REaLTabFormer, and only on the largest dataset they have comparable runtime. For small datasets, both tools achieve synthetic data with high utility and optimal similarity, but on larger datasets only REaLTabFormer sustains strong utility and similarity. As a result, REaLTabFormer with lightweight LLMs provides the best balance, since it preserves data quality while reducing computational requirements. Nonetheless, its runtime remains higher than that of GReaT and other TDS tools, suggesting that efficiency gains are possible but only up to a certain level.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
