arXiv cs.AI· Wei Pang, Xiangru Jian, Hehan Li, Zhixuan Yu, Alex Xue, Jinyang Li, Zhengyuan Dong, Xinjian Zhao, Hao Xu, Chao Zhang, Reynold Cheng, M. Tamer \"Ozsu, Tianshu Yu·· 1 天前AI 评分32
TRL-Bench：表格编码器跨范式表示级评估基准
TRL-Bench: Standardizing Cross-Paradigm Representation-Level Evaluation of Tabular Encoders
AI 导读
TRL-Bench 是一个多粒度表格表示学习基准，通过统一封装导出 row、column、table 嵌入并用共享轻量头探测，实现跨范式表示级评估。基准包含 50 个 OpenML 表格与 123 个验证目标、16 个行对连接改写，以及由 1,379 个父表派生的 47,772 表 DLTE 数据湖，覆盖 20 个模型和 16 项任务。
正文 · 原文
Authors:Wei Pang, Xiangru Jian, Hehan Li, Zhixuan Yu, Alex Xue, Jinyang Li, Zhengyuan Dong, Xinjian Zhao, Hao Xu, Chao Zhang, Reynold Cheng, M. Tamer Özsu, Tianshu Yu
Abstract:Tabular encoders are usually evaluated inside task-specific end-to-end pipelines, so models from different training paradigms are difficult to compare directly even when they operate on similar tabular signals. We introduce TRL-Bench, a multi-granular tabular representation learning (TRL) benchmark that standardizes cross-paradigm representation-level evaluation: each encoder exports row-, column-, or table embeddings through its supported wrapper, and shared lightweight heads probe them across three suites: TRL-CTbench (column/table), TRL-Rbench (row), and TRL-DLTE (compositional Data-Lake Table Enrichment spanning all three granularities). To support this standardized setting, we release curated benchmark assets and task reformulations, including 50 OpenML tables with 123 verified targets, 16 row-pair linkage rewrites, and a 47,772-table DLTE lake derived from 1,379 parent tables. Across 20 models and 16 tasks, TRL-Bench shows that once downstream conditions are standardized, encoder quality is capability-specific rather than captured by a single leaderboard. In TRL-CTbench, generic text encoders often lead on tasks with strong surface-text signal, while tabular specialists win where their pretraining objective aligns with the task. In TRL-Rbench, within-table prediction and cross-table linkage favor different training regimes, with atomic linkage performance correlating strongly with the row-matching stage of DLTE pipelines. In TRL-DLTE, the strongest pipelines combine capability-matched specialists rather than reuse a single encoder, and top end-to-end quality depends on non-additive compositional fit rather than per-stage marginal rank alone. TRL-Bench provides a common protocol for measuring reusable signal in exported tabular representations under shared downstream conditions. Code: this https URL data is released on Hugging Face.
| Subjects: | Artificial Intelligence (cs.AI); Databases (cs.DB) |
| Cite as: | arXiv:2606.09323 [cs.AI] |
| (or arXiv:2606.09323v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.09323 arXiv-issued DOI via DataCite |
Submission history
From: Wei Pang [view email]
[v1]
Mon, 8 Jun 2026 10:39:25 UTC (1,573 KB)
[v2]
Wed, 11 Nov 2026 13:11:02 UTC (2,477 KB)
来源：arXiv cs.AI · arxiv.org