用图神经网络联合建模用户群体差异与行为动态，提升广告平台用户价值预测精度。
HT-GNN: Hyper-Temporal Graph Neural Network for Customer Lifetime Value Prediction in Baidu Ads
- 构建超图监督模块捕捉不同用户群间关系，解决群体差异问题
- 采用自适应加权的Transformer编码器处理不规则行为序列
- 多任务混合专家结构支持多时序长周期预测，适合广告投放场景
用户生命周期价值（LTV）预测对信息流广告至关重要，有助于平台优化出价与预算分配以实现长期收益增长。然而，该任务面临两大挑战：(1) 基于人口统计的定向策略导致各用户群体存在显著的LTV分布差异；(2) 动态营销策略引发非规则行为序列，参与模式快速演变。本文提出超时空图神经网络（HT-GNN），通过三个核心组件联合建模人口异质性与时间动态性：(i) 超图监督模块捕捉跨群体关系；(ii) 基于Transformer的时间编码器结合自适应权重机制；(iii) 任务自适应的混合专家结构与动态预测塔，支持多时序LTV预测。在包含1500万用户的百度广告数据集上实验表明，HT-GNN在所有指标和预测时长上均持续优于现有先进方法。
原文摘要 · Abstract (English)
Lifetime value (LTV) prediction is crucial for news feed advertising, enabling platforms to optimize bidding and budget allocation for long-term revenue growth. However, it faces two major challenges: (1) demographic-based targeting creates segment-specific LTV distributions with large value variations across user groups; and (2) dynamic marketing strategies generate irregular behavioral sequences where engagement patterns evolve rapidly. We propose a Hyper-Temporal Graph Neural Network (HT-GNN), which jointly models demographic heterogeneity and temporal dynamics through three key components: (i) a hypergraph-supervised module capturing inter-segment relationships; (ii) a transformer-based temporal encoder with adaptive weighting; and (iii) a task-adaptive mixture-of-experts with dynamic prediction towers for multi-horizon LTV forecasting. Experiments on \textit{Baidu Ads} with 15 million users demonstrate that HT-GNN consistently outperforms state-of-the-art methods across all metrics and prediction horizons.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。