将用户-物品交互图结构融入事件序列模型，提升预测准确性。
Beyond Isolated Clients: Integrating Graph-Based Embeddings into Event Sequence Models
- 用图嵌入增强事件表示，捕捉全局交互关系。
- 在四个数据集上最高提升2.3% AUC，验证方法有效性。
- 适合做风控与推荐系统的研究者参考。
大规模数字平台生成数十亿条带时间戳的用户-物品交互事件，对欺诈检测和推荐系统至关重要。尽管自监督学习能有效建模事件的时间顺序，但通常忽略用户-物品交互图的全局结构。为此，我们提出三种模型无关的策略，将结构信息融入对比自监督学习：丰富事件嵌入、对齐客户端表示与图嵌入、引入结构化预训练任务。在四个金融与电商数据集上的实验表明，该方法显著提升准确率（最高达2.3% AUC），并揭示图密度是选择最优融合策略的关键因素。
原文摘要 · Abstract (English)
Large-scale digital platforms generate billions of timestamped user-item interactions (events) that are crucial for predicting user attributes in, e.g., fraud prevention and recommendations. While self-supervised learning (SSL) effectively models the temporal order of events, it typically overlooks the global structure of the user-item interaction graph. To bridge this gap, we propose three model-agnostic strategies for integrating this structural information into contrastive SSL: enriching event embeddings, aligning client representations with graph embeddings, and adding a structural pretext task. Experiments on four financial and e-commerce datasets demonstrate that our approach consistently improves the accuracy (up to a 2.3% AUC) and reveals that graph density is a key factor in selecting the optimal integration strategy.
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。