AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models

Xiyuan Zhang, Danielle C. Maddix, Junming Yin, Nick Erickson, Abdul Fatir Ansari, Boran Han, Shuai Zhang, Leman Akoglu, Christos Faloutsos, Michael W. Mahoney, Cuixiong Hu, Huzefa Rangwala and 2 more

NeurIPS 2025 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Systematically analyzes synthetic data priors for tabular foundation models and builds Mitra, a 2D-attention TFM pretrained on a mixture of SCM and tree-based priors that outperforms TabPFNv2 and TabICL on classification and regression benchmarks.

Problem

Tabular foundation models based on in-context learning are pretrained on synthetic data, but the principles for designing the synthetic priors (what makes a good prior and how to mix them) remain poorly understood.

Approach

Identify three prior-quality factors (standalone performance on real data, diversity, and distinctiveness within a mixture) via a generalizability matrix, then build a mixture of SCM and tree-based priors (DT, ET, GB, RF, plus a directly sampled RF) to pretrain a TFM that is model-agnostic across 1D and 2D attention.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the full mixed-prior method with ensembling and fine-tuningMitra · Merged classification benchmarksElo: 1015 -> 1136Improved
Use the full mixed-prior method with ensembling and fine-tuningMitra · TabRepo regressionElo: 963 -> 1140Improved
Add ET prior to SCM (ablation)Mitra prior mixture · TabRepo classificationElo: 1000 -> 1063 (+63)Improved
Add GB prior to SCM + ET (ablation)Mitra prior mixture · TabRepo classificationElo: 1063 -> 1076Improved
Add RF prior to SCM + ET + GB (ablation)Mitra prior mixture · TabRepo classificationElo: 1076 -> 1050No clear effect
Add DSRF prior to SCM + ET + GB (ablation)Mitra prior mixture · TabRepo classificationElo: 1076 -> 1046No clear effect
Add DT prior to SCM + ET + GB (ablation)Mitra prior mixture · TabRepo classificationElo: 1076 -> 1059No clear effect
Add DT prior to SCM + ET (ablation)Mitra prior mixture · TabRepo classificationElo: 1063 -> 1028Hurt
Add RF prior to SCM (ablation)Mitra prior mixture · TabRepo classificationElo: 1000 -> 1005No clear effect
Add DT prior to SCM (ablation)Mitra prior mixture · TabRepo classificationElo: 1000 -> 1025Improved
Add GB prior to SCM (ablation)Mitra prior mixture · TabRepo classificationElo: 1000 -> 1028Improved
Add DSRF prior to SCM (ablation)Mitra prior mixture · TabRepo classificationElo: 1000 -> 1058Improved

Experimental setup

Baselines: TabPFNv2 TabICL Attic TabPFN TabForestPFN RealMLP AutoGluon LightGBM XGBoost CatBoost

Builds on: TabPFN TabPFNv2 Attic TabForestPFN

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy