用于好友推荐的图神经网络扩展：多哈希用户嵌入与时序邻居采样
Scaling Graph Neural Networks for Friend Recommendation: Multi-Hash User Embeddings and Temporal Neighbor Sampling
浏览论文内容
中文总结 AI 辅助
该研究针对生产级社交图的好友推荐问题，提出结合多哈希用户嵌入与时序邻居采样的可扩展GNN排序系统，经实验验证可提升好友推荐效果并发布了相关分布式框架。
中文摘要 AI 辅助
好友推荐本质上是图结构问题：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，在拥有数亿用户、数百亿边的生产级社交图上部署消息传递图神经网络（GNN），需解决大量建模与系统挑战。本文提出一种面向生产级社交图的可扩展端到端GNN排序系统，重点关注该场景下两个关键设计选择：多哈希ID嵌入与时序邻居采样。多哈希嵌入常用于高基数特征，但工业级GNN系统通常要么忽略可训练ID，要么接受完整嵌入表，而本文所用图的嵌入表超过200GB。本文将多哈希作为主要节点表示，在保留排序质量的同时，将ID嵌入表大小减少98%以上。时序邻居采样原理已广为人知，但现有实现会扫描完整邻接表，对于拥有数万名好友的用户而言完全不可行。本文实现按时间戳排序的CSR存储并结合二分查找，将每节点时序采样成本从O(deg(v)+k)降至O(log(deg(v))+k)。除上述组件外，本文证明该组合具有可扩展性并产生可衡量的生产影响。在拥有1.94亿用户、280亿边的图上，离线 ablation 实验单独分析每个设计选择的贡献。在线A/B测试中，与强大的生产基线相比，本文系统使推荐带来的好友添加量增加16%，唯一好友添加者数量增加11.5%。本文发布了用于大型时序图分布式训练与推理的框架。
英文摘要
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 primary node representation, reducing the ID-embedding table size by more than 98 percent while preserving ranking quality. Temporal neighbor sampling is well understood in principle, but existing implementations scan full adjacency lists, which is a non-starter for users with tens of thousands of friends. We implement timestamp-sorted CSR storage with binary search, reducing the per-node temporal sampling cost from $O(deg(v) + k)$ to $O(\log(deg(v)) + k)$. Beyond these components, we show that this combination scales and yields measurable production impact. On a graph with 194M users and 28B edges, offline ablations isolate each design choice's contribution. In an online A/B test, our system increases friend additions from recommendations by 16 percent and unique friend adders by 11.5 percent over a strong production baseline. We release our framework for distributed training and inference on large temporal graphs.
发表机构
- AI VK
机构由 AI 辅助整理，请以论文原文为准。
