Deploying dynamic heterogeneous graph embeddings in production faces key challenges of scalability, data freshness, and cold-start. This paper introduces a practical, two-stage solution that balances deep graph representation with low-latency incremental updates. Our framework combines HetSGFormer, a scalable graph transformer for static learning, with Incremental Locally Linear Embedding (ILLE), a lightweight, CPU-based algorithm for real-time updates. HetSGFormer captures global structure with linear scalability, while ILLE provides rapid, targeted updates to incorporate new data, thus avoiding costly full retraining. This dual approach is cold-start resilient, leveraging the graph to create meaningful embeddings from sparse data. On billion-scale graphs, A/B tests show HetSGFormer achieved up to a 6.11% lift in Advertiser Value over previous methods, while the ILLE module added another 3.22% lift and improved embedding refresh timeliness by 83.2%. Our work provides a validated framework for deploying dynamic graph learning in production environments.

翻译：在生产环境中部署动态异质图嵌入面临可扩展性、数据新鲜度和冷启动等关键挑战。本文提出一种实用的两阶段解决方案，在深度图表示与低延迟增量更新之间取得平衡。我们的框架结合了HetSGFormer（一种用于静态学习的可扩展图Transformer）与增量局部线性嵌入（ILLE，一种基于CPU的轻量级实时更新算法）。HetSGFormer以线性可扩展性捕获全局结构，而ILLE则提供快速、定向的更新以纳入新数据，从而避免代价高昂的完整重训练。这种双重方法具备冷启动鲁棒性，利用图结构从稀疏数据中生成有意义的嵌入。在十亿级规模的图上，A/B测试表明HetSGFormer相比先前方法在广告主价值上实现了最高6.11%的提升，而ILLE模块进一步带来了3.22%的提升，并将嵌入刷新及时性提高了83.2%。我们的工作为在生产环境中部署动态图学习提供了一个经过验证的框架。