pTNAS: Progressive Neural Architecture Search for Tabular Data

Jian Pei, Shaofeng Cai, Jiaqi Zhu, Beng Ooi, Peng Lu, Naili Xing, Lingze Zeng

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 2 functions out of this paper's own repositories and ran 1 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

Repositories linked to this paper

• NLGithubWP/pTNAS

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent advances have shifted the paradigm of tabular learning toward tabular foundation models, yet their accuracy relies on a heavy inference cost that scales poorly with context size. Deep neural networks remain a highly competitive and more efficient modeling paradigm when equipped with well-designed architectures; however, identifying such architectures in a data-adaptive and budgetaware manner remains challenging. We propose pTNAS, the first progressive neural architecture search (NAS) approach tailored for tabular data, which enables fast identification of a viable architecture and continuously improves its search performance as more budget becomes available. pTNAS adopts a filter-and-refine optimization strategy that combines efficient training-free and effective training-based architecture evaluation. In the filtering phase, we introduce pTProxy, a novel zero-cost proxy specifically designed for tabular networks that jointly captures architectural trainability and expressivity, enabling fast filtering of large architecture search spaces. In the refinement phase, pTNAS employs a fixedbudget scheduling algorithm to accurately identify the best-performing architecture from a small set of promising candidates. We further propose a budget-aware coordinator to optimize budget allocation holistically. Experiments show that pT-NAS reduces the time to reach the globally best architecture by up to 82.75× compared with other NAS approaches, achieves the best average predictive rank, and improves end-to-end efficiency by up to 4.78× compared with TabPFN.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2403.10318")
get_code_for_paper("2403.10318")
have("2403.10318")

Connect an agent — have() is free.