paper-with-me

Papers

GOTabPFN: From Feature Ordering to Compact Tokenization for Tabular Foundation Models on High-Dimensional Data

2026-06-03 · Al Zadid Sultan Bin Habib, Md Younus Ahamed, Prashnna Kumar Gyawali, Gianfranco Doretto, Donald A. Adjeroh arxiv

We investigate how to make small tabular foundation models effective for High-Dimensional, Low-Sample Size (HDLSS) tabular prediction without retraining large backbones. We introduce Graph-guided Ordering with Local Refinement (GO-LR), show its equivalence to weighted Minimum Linear Arrangement, and interpret the practical solver as a TSP-path-style surrogate. We propose GOTabPFN,which builds on GO-LR, and a Neuro-Inspired Subunit Compression (NSC) unit to pool locally adjacent ordered features into meta-features, yielding a compact representation that makes TabPFN-style prediction practical in HDLSS regimes. Across tabular benchmarks, GOTabPFN improves stability and accuracy under tight token budgets.

📄 PDF Abstract BibTeX arXiv:2606.05441

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Discrete Tokenization Unlocks Transformers for Calibrated Tabular Forecasting

2026-03-08 · Yael S. Elmatad arxiv

Gradient boosting still dominates Transformers on tabular benchmarks. Our tokenizer uses a deliberately simplistic discretized vocabulary so we can highlight how even basic tokenization unlocks the power of attention on …

DynaTab: Dynamic Feature Ordering as Neural Rewiring for High-Dimensional Tabular Data

2026-05-05 · Al Zadid Sultan Bin Habib, Gianfranco Doretto, Donald A. Adjeroh arxiv

High-dimensional tabular data lacks a natural feature order, limiting the applicability of permutation-sensitive deep learning models. We propose DynaTab, a dynamic feature ordering-enabled architecture inspired by neura…

LimiX-2M: Mitigating Low-Rank Collapse and Attention Bottlenecks in Tabular Foundation Models

2026-06-03 · Yuanrui Wang, Xingxuan Zhang, Han Yu, Mingchao Hao 외 arxiv

Tabular foundation models (TFMs) increasingly rival tree ensembles, but their performance is often compute-inefficient: with standard affine scalar tokenization, each feature injects value variation through an essentiall…

TabSeq: A Framework for Deep Learning on Tabular Data via Sequential Ordering

2024-10-17 · Al Zadid Sultan Bin Habib, Kesheng Wang, Mary-Anne Hartley, Gianfranco Doretto 외

Effective analysis of tabular data still poses a significant problem in deep learning, mainly because features in tabular datasets are often heterogeneous and have different levels of relevance. This work introduces TabS…

ClusteringDeep LearningDenoising

SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape Generation

2026-05-28 · Yuan Li, Congyi Zhang, Xifeng Gao, Xiaohu Guo arxiv

Autoregressive multimodal large language models (MLLMs) enable 3D generation but struggle to scale to high-resolution shapes due to inadequate 3D tokenizations. Compact set-based representations discard deterministic spa…

3D Generation