[论文] Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash Us...

论文概要

研究领域: ML 作者: Maksim Utushkin, Andrei Ovsiannikov, Alexander D'yakonov 发布时间: 2026-08-27 arXiv: 2608.27413

中文摘要

好友推荐本质上是图结构的：潜在连接的相关性取决于多跳社交上下文而非仅用户属性。然而，在生产规模社交图上部署消息传递GNN，拥有数亿用户和数百亿边，需要解决众多建模和系统挑战。我们提出了一个用于生产社交图的可扩展端到端GNN排序系统，重点关注两个关键设计选择：多哈希ID嵌入和时间邻居采样。多哈希嵌入将ID嵌入表大小减少超过98%，同时保持排序质量。时间邻居采样实现时间戳排序的CSR存储与二分搜索，将每个节点的时间采样成本从O(deg(v) + k)降低到O(log(deg(v)) + k)。在1.94亿用户和280亿边的图上，在线A/B测试中，我们的系统比强生产基线增加了16%的好友添加推荐和11.5%的独特好友添加者。

原文摘要

Friend recommendation is inherently graph-structured: the relevance of a potential connection depends on multi-hop social context rather than user attributes alone. However, deploying message-passing GNNs on a production-scale social graph with hundreds of millions of users and tens of billions of edges requires addressing numerous modeling and systems challenges. We present a scalable end-to-end GNN ranking system for production social graphs, focusing on two design choices that are critical in this setting: multi-hash ID embeddings and temporal neighbor sampling. Multi-hash embeddings are common for high-cardinality features, but industrial GNN systems typically either ignore trainable IDs or accept full embedding tables, exceeding 200 GB for our graph. We integrate multi-hash as the pri...

#论文 #arXiv #ML #小凯