SelectArena is a new benchmark for feature selection on real-world tabular data, evaluating 15 popular methods across 71 curated datasets for both classification and regression tasks. The study uses standardized protocols and modern foundation models, revealing trade-offs among predictive performance, runtime, stability, and validity. Tree-based methods (CART, RFImportance) and the F-Test emerge as Pareto-optimal choices, while search-based methods perform poorly in speed and stability.
By Bastian Sch\"afer, Dominika Matus, Lennart Purucker, Ricardo Knauer, Erik Rodner, Frank Hutter, Anton Sokolov, Arnaud Liefooghe
arXiv:2609.24126v1 Announce Type: cross
Abstract: Black-box machine learning models increasingly deliver strong predictions, but extracting useful information from them, such as a set of important fe...
By Xuhui Liu, Lili Zheng
arXiv:2606. 01566v1 Announce Type: new Abstract: Small-to-medium scientific datasets place machine learning pipelines under two compounding pressures.
By Amanda S Barnard
arXiv:2610.28556v1 Announce Type: cross
Abstract: Large language models (LLMs) can leverage semantic feature names alongside summary statistics for tabular feature selection, yet it remains unclear w...
By Fateme Memar, Dongjie Wang, Arvin Agah
The paper introduces Dr. Post-Training, a framework that treats general training data as a data‑induced regularizer to prevent overfitting to scarce target objectives, rather than merely a pool for selection. It constructs a feasible set of model update directions from general data and projects target‑driven updates onto this set, unifying standard training and existing data‑selection methods as special cases along a bias‑variance spectrum. Experiments on SFT, RLHF, and RLVR demonstrate that these methods outperform both standard training and state‑of‑the‑art data‑selection baselines, especially when general and target data are highly misaligned, while system optimizations keep overhead minimal.
By Pingbang Hu, Xueshen Liu, Z. Morley Mao, Jiaqi W. Ma
arXiv:2512. 17678v2 Announce Type: replace-cross Abstract: Selecting compact and informative gene subsets from single-cell transcriptomic data is essential for biomarker discovery, improving interpretability, and cost-effective profiling.
By Daphn\'e Chopard, Jorge da Silva Gon\c{c}alves, Irene Cannistraci, Thomas M. Sutter, Julia E. Vogt
Data-DPO is a target model‑oriented supervised fine‑tuning data selection method that uses one‑step probing of the target model to generate pairwise data preferences, trains a lightweight reward model to capture these preferences, and then selects a training subset by combining target‑model preference, external quality scores, and marginal diversity. Experiments on Vision‑Flan and LLaVA‑CoT demonstrate that Data‑DPO consistently outperforms existing data selection baselines across multiple data budgets and even surpasses full data training performance.
By Peng Sun, Yi Yang, Antong Zhang, Chunxiao Li, Yanbo Wang, Dianbo Liu, xin chen, Kai Yu, Lu Chen, Tianfan Fu
arXiv:2603. 02221v2 Announce Type: replace-cross Abstract: In clinical tabular prediction, classical machine learning models with feature engineering often outperform neural methods.
By Zizheng Zhang, Yiming Li, Justin Xu, Jinyu Wang, Rui Wang, Lei Song, Jiang Bian, David W Eyre, Jingjing Fu
The paper introduces a "nominate-then-adjudicate" pipeline for tuning mixed‑integer programming (MIP) solvers, where a fixed portfolio of configurations is sampled once and reused across instances, eliminating per‑instance search at inference. A 20‑feature representation maps structurally different instances to the same vector, enabling a one‑pass, zero‑solve selection process that outperforms default settings and per‑instance baselines such as ISAC+. The approach demonstrates significant practical gains, with the adjudicator achieving 538 wins over the top nominee and improving win rates against defaults from 84.9% to 90.2%.
By Yifan Zhao, Qianyang Zhao, Xinyu Guan, Kai Wei, Yuming Deng
arXiv:2603.02221v3 Announce Type: replace-cross
Abstract: In clinical tabular prediction, classical machine learning models with feature engineering often outperform neural methods. LLMs are increasi...
By Zizheng Zhang, Yiming Li, Justin Xu, Jinyu Wang, Rui Wang, Lei Song, Jiang Bian, David W Eyre, Jingjing Fu
The paper refactors and expands the scikit-rebate Python package, adding new Relief‑Based Algorithm (RBA) variants such as SWRF*, mu‑Relief, and five novel methods that use alternative neighbor selection and feature scoring strategies. Benchmarking across diverse genomic simulations shows that most RBAs, except mu‑Relief, effectively detect 2‑way interactions in noisy data, with far‑scoring variants like MultiSWRFDB* excelling at interaction detection but being less sensitive to main effects. The refactored package achieves 10‑ to 35‑fold runtime reductions, and the new RBAs maintain strong performance for both main effects and 2‑way epistatic interactions, preserving predictive signals for downstream modeling.
By Kia Kazemi-Nia, Harsh Bandhey, Philip J. Freda, Ryan J. Urbanowicz
The paper introduces the General Demographic Pre-trained (GDP) model, a lightweight foundation model that learns representations from the two most common clinical attributes—age and sex. By optimizing encoding and visit‑reordering strategies, GDP embeddings are shown to improve predictive performance when concatenated with raw features across various disease and geographic cohorts. The model outperforms several state‑of‑the‑art tabular foundation models and tree‑based algorithms, demonstrating that enriched demographic embeddings can enhance classification tasks while remaining fully compatible with standard classifiers.
By Li-Chin Chen, Ji-Tian Sheu, Yuh-Jue Chuang