发表机构
Amazon（亚马逊）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究推出仅用5% TabFM参数量（77M）的开源表格基础模型Mitra-v2，在TabArena、TALENT等基准上超越多数同类模型，在多类分类任务表现突出，性能达行业级水平。
AI 中文摘要
我们推出 Mitra-v2，这是一种表格基础模型，在现实世界的分类和回归问题上实现了最先进的性能，涵盖信用风险评分、临床预测、设备故障检测以及房价估算等场景。Mitra-v2 仅在合成数据上进行训练，其预训练分布比 Mitra-v1 大得多且更多样。它基于小型 2D Transformer 骨干构建，支持更长的上下文和更大的特征空间，改进的优化使其能够从更大的任务分布中学习。我们在包含 300 多个现实世界数据集的 TabArena 和 TALENT 基准上，采用两种评估协议对 Mitra-v2 进行评估。在完整 TabArena 基准上，Mitra-v2 达到了与行业规模的 TabFM 和 EXAONE Tabular 模型相当的最先进性能，同时在分类和回归任务上大幅超越 TabPFN-3。Mitra-v2 仅用 7700 万参数（仅为 16 亿参数的 TabFM 的 5%）就达到了与 TabFM 相当的前沿性能，成本仅为其一小部分。在 TALENT 上，Mitra-v2 仍处于领先模型之列，明显优于 TabPFN-3 和 TabICLv2。尽管仅在最多 10 类的任务上进行了预训练，但它在 10 类以上的分类任务中排名第一。这些结果使 Mitra-v2 成为迄今为止发布的最强大、适用性最广的开源表格基础模型之一。我们根据 Apache-2.0 许可证发布模型权重、推理和微调代码以及我们的评估结果。
英文摘要
We introduce Mitra-v2, a tabular foundation model that delivers state-of-the-art performance on real-world classification and regression problems, from credit-risk scoring and clinical prediction to equipment-failure detection and house-price estimation. Mitra-v2 is trained only on synthetic data, with a pretraining distribution that is much larger and more diverse than Mitra-v1's. Built on a small 2D Transformer backbone, Mitra-v2 supports longer contexts and larger feature spaces. Improved optimization lets it learn from this larger task distribution. We evaluate Mitra-v2 on the TabArena and TALENT benchmarks, comprising more than 300 real-world datasets under two evaluation protocols. On the full TabArena benchmark, Mitra-v2 delivers state-of-the-art performance at the level of the industry-scale TabFM and EXAONE Tabular models, while surpassing TabPFN-3 by a wide margin in both classification and regression. Mitra-v2 matches the 1.6B-parameter TabFM with only 5% of its size (77M parameters), delivering frontier performance at a fraction of the cost. On TALENT, Mitra-v2 remains among the leading models, clearly outperforming TabPFN-3 and TabICLv2. It also ranks first on classification tasks with more than ten classes, even though it was pretrained only on tasks with at most ten classes. These results make Mitra-v2 one of the strongest and most broadly applicable open tabular foundation models released to date. We release the model weights, the inference and fine-tuning code, and our evaluation results under the Apache-2.0 license.
Comments38 pages. Model weights, inference and fine-tuning code, and evaluation results: https://huggingface.co/autogluon/mitra-finetune
