Predictive modeling on web-scale tabular data with billions of instances and hundreds of heterogeneous numerical features faces significant scalability challenges. These features exhibit anisotropy, heavy-tailed distributions, and non-stationarity, creating bottlenecks for models like Gradient Boosting Decision Trees and requiring laborious manual feature engineering. We introduce KMLP, a hybrid deep architecture integrating a shallow Kolmogorov-Arnold Network (KAN) front-end with a Gated Multilayer Perceptron (gMLP) backbone. The KAN front-end uses learnable activation functions to automatically model complex non-linear transformations for each feature, while the gMLP backbone captures high-order interactions. Experiments on public benchmarks and an industrial dataset with billions of samples show KMLP achieves state-of-the-art performance, with advantages over baselines like GBDTs increasing at larger scales, validating KMLP as a scalable deep learning paradigm for large-scale web tabular data.
@article{arxiv.2602.22777,
title = {KMLP: A Scalable Hybrid Architecture for Web-Scale Tabular Data Modeling},
author = {Mingming Zhang and Pengfei Shi and Zhiqing Xiao and Feng Zhao and Guandong Sun and Yulin Kang and Ruizhe Gao and Ningtao Wang and Xing Fu and Weiqiang Wang and Junbo Zhao},
journal= {arXiv preprint arXiv:2602.22777},
year = {2026}
}