Neural Graph Databases (NGDBs) facilitate complex logical reasoning over incomplete knowledge structures, yet their training efficiency and expressivity are constrained by rigid query-level batching and structure-exclusive embeddings. We present NGDB-Zoo, a unified framework that resolves these bottlenecks by synergizing operator-level training with semantic augmentation. By decoupling logical operators from query topologies, NGDB-Zoo transforms the training loop into a dynamically scheduled data-flow execution, enabling multi-stream parallelism and achieving a 1.8× - 6.8× throughput compared to baselines. Furthermore, we formalize a decoupled architecture to integrate high-dimensional semantic priors from Pre-trained Text Encoders (PTEs) without triggering I/O stalls or memory overflows. Extensive evaluations on six benchmarks, including massive graphs like ogbl-wikikg2 and ATLAS-Wiki, demonstrate that NGDB-Zoo maintains high GPU utilization across diverse logical patterns and significantly mitigates representation friction in hybrid neuro-symbolic reasoning.
@article{arxiv.2602.21597,
title = {NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases Training},
author = {Zhongwei Xie and Jiaxin Bai and Shujie Liu and Haoyu Huang and Yufei Li and Yisen Gao and Hong Ting Tsang and Yangqiu Song},
journal= {arXiv preprint arXiv:2602.21597},
year = {2026}
}