LinkSAGE:利用图神经网络优化职位匹配
LinkSAGE: Optimizing Job Matching Using Graph Neural Networks
AI总结:
LinkSAGE 通过构建大规模职位市场图,并将 GNN 训练与现有 DNN 解耦、结合近线推理,在 LinkedIn 场景中显著提升职位匹配的参与度、相关性和留存率。
摘要:
我们提出 LinkSAGE,这是一个创新框架,将图神经网络(GNNs)集成到大规模个性化职位匹配系统中,旨在应对 LinkedIn 庞大职业网络的复杂动态。我们的方法利用了一个新颖的职位市场图,这是业界同类中规模最大、最复杂的图,拥有数十亿节点和边。该图不仅规模庞大,而且细节丰富,包含会员节点和职位节点及其关键属性,从而构建出一个广阔且相互交织的网络。LinkSAGE 的一个关键创新在于其训练与 serving 方法,该方法在异构、动态演化的图上有效地结合了归纳式图学习与编码器-解码器 GNN 模型。该方法将 GNN 模型的训练与现有深度神经网络(DNN)模型的训练解耦,无需频繁重新训练 GNN,同时保持近实时的最新图信号,从而能够通过迁移学习有效整合 GNN 洞察。随后的近线推理系统在真实环境中 serving GNN 编码器,显著降低在线延迟,并避免了对昂贵的实时 GNN 基础设施的需求。LinkSAGE 在多种产品场景的多个在线 A/B 测试中得到验证,在会员参与度、相关性匹配和会员留存方面均表现出显著提升,证实了其通用性和实际影响。
英文摘要:
We present LinkSAGE, an innovative framework that integrates Graph Neural Networks (GNNs) into large-scale personalized job matching systems, designed to address the complex dynamics of LinkedIns extensive professional network. Our approach capitalizes on a novel job marketplace graph, the largest and most intricate of its kind in industry, with billions of nodes and edges. This graph is not merely extensive but also richly detailed, encompassing member and job nodes along with key attributes, thus creating an expansive and interwoven network. A key innovation in LinkSAGE is its training and serving methodology, which effectively combines inductive graph learning on a heterogeneous, evolving graph with an encoder-decoder GNN model. This methodology decouples the training of the GNN model from that of existing Deep Neural Nets (DNN) models, eliminating the need for frequent GNN retraining while maintaining up-to-date graph signals in near realtime, allowing for the effective integration of GNN insights through transfer learning. The subsequent nearline inference system serves the GNN encoder within a real-world setting, significantly reducing online latency and obviating the need for costly real-time GNN infrastructure. Validated across multiple online A/B tests in diverse product scenarios, LinkSAGE demonstrates marked improvements in member engagement, relevance matching, and member retention, confirming its generalizability and practical impact.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。