GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks
Read the original on arXiv AI →GraphFAS is a distributed system that automates graph feature generation and selection for industrial transaction networks. It uses a non‑parametric module to create explicit, interpretable structural features through multi‑hop subgraph extraction and multi‑scale aggregation, and extends the Boruta algorithm with median‑based aggregation across partitions for robust feature selection. The approach decouples feature aggregation from model training, allowing integration with tabular models and TreeSHAP explanations, and has been deployed in Alipay, yielding significant engineering efficiency gains and strong performance against expert‑driven and graph‑learning baselines.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.