[论文解读] Modeling the Sequential Dependence among Audience Multi-step Conversions with Multi-task Learning in Targeted Display Advertising

Dongbo Xi, Zhen Chen+5 more|arXiv (Cornell University)|May 18, 2021

Data Stream Mining Techniques参考文献 32被引用 7

一句话总结

本文提出自适应信息迁移多任务（AITM）框架，用于建模目标展示广告中多步骤受众转化的序列依赖关系，通过自适应信息迁移模块动态控制各阶段之间的知识共享。该方法在工业和公开数据集上均取得当前最优性能，显著提升了端到端转化预测效果，尤其在严重类别不平衡情况下表现突出。

ABSTRACT

In most real-world large-scale online applications (e.g., e-commerce or finance), customer acquisition is usually a multi-step conversion process of audiences. For example, an impression->click->purchase process is usually performed of audiences for e-commerce platforms. However, it is more difficult to acquire customers in financial advertising (e.g., credit card advertising) than in traditional advertising. On the one hand, the audience multi-step conversion path is longer. On the other hand, the positive feedback is sparser (class imbalance) step by step, and it is difficult to obtain the final positive feedback due to the delayed feedback of activation. Multi-task learning is a typical solution in this direction. While considerable multi-task efforts have been made in this direction, a long-standing challenge is how to explicitly model the long-path sequential dependence among audience multi-step conversions for improving the end-to-end conversion. In this paper, we propose an Adaptive Information Transfer Multi-task (AITM) framework, which models the sequential dependence among audience multi-step conversions via the Adaptive Information Transfer (AIT) module. The AIT module can adaptively learn what and how much information to transfer for different conversion stages. Besides, by combining the Behavioral Expectation Calibrator in the loss function, the AITM framework can yield more accurate end-to-end conversion identification. The proposed framework is deployed in Meituan app, which utilizes it to real-timely show a banner to the audience with a high end-to-end conversion rate for Meituan Co-Branded Credit Cards. Offline experimental results on both industrial and public real-world datasets clearly demonstrate that the proposed framework achieves significantly better performance compared with state-of-the-art baselines.

研究动机与目标

• 为解决金融广告中因反馈延迟和稀疏导致的长序列依赖问题，特别是多步骤受众转化中的挑战。
• 通过利用早期阶段的有益信号，缓解后期转化阶段（如激活）中严重的类别不平衡问题。
• 提升真实世界目标展示广告系统中长级联转化路径下的端到端转化预测准确率。
• 开发一种灵活的多任务学习框架，基于任务特定反馈自适应控制各阶段间的信息传递。

提出的方法

• 引入自适应信息迁移（AIT）模块，学习从早期阶段到后期阶段传递表示的动态、任务特定权重。
• 采用共享底座与任务特定塔堆叠的多任务学习架构，其中 AIT 模块控制信息从一阶段向下一阶段的传递程度。
• 在损失函数中引入行为期望校准器，使预测与逻辑约束对齐：若前序步骤失败，则后续步骤必然失败。
• 采用残差式信息融合机制，使每个任务的输入同时包含原始特征和来自前一阶段的迁移信息。
• 使用带校准监督的交叉熵损失端到端训练模型，以稳定学习过程并提升泛化能力。
• 采用 t-SNE 可视化分析 AIT 模块在不同转化阶段的表征学习质量。

实验结果

研究问题

• RQ1 多任务学习如何有效建模具有级联约束的受众多步骤转化中的长序列依赖？
• RQ2 早期转化阶段的知识能在多大程度上提升后期、标签稀疏且反馈延迟的阶段的预测性能？
• RQ3 如何根据中间预测的可靠性与置信度，动态调整阶段间的信息传递？
• RQ4 自适应信息迁移对模型在严重类别不平衡情况下的鲁棒性与性能有何影响？
• RQ5 所提出的框架是否能在不同真实世界数据集和工业部署场景中实现良好泛化？

主要发现

• AITM 框架在工业和公开数据集上均显著优于当前最优基线模型，展现出更优的泛化能力与鲁棒性。
• 离线实验表明，所有五个转化阶段均实现一致性能提升，尤其在最难预测的最终阶段（激活）提升最为显著。
• 在美团联名信用卡活动的线上 A/B 测试中，与现有在线模型相比，端到端转化率获得显著提升。
• AIT 模块能有效学习在早期预测不确定性较高时传递更多信息，从而降低下游任务的误分类率。
• 该框架在广泛超参数范围内（特别是嵌入维度和正样本比例）表现稳定，体现出强大的实际鲁棒性。
• t-SNE 可视化结果表明，AIT 模块通过增强各阶段间特征对齐，尤其在高置信区域，显著提升了表征学习质量。