用于缓解多任务推荐中信号侵蚀的个性化任务依赖图
Personalized Task Dependency Graphs for Mitigating Signal Erosion in Multi-Task Recommendation
浏览论文内容
中文总结 AI 辅助
针对多任务推荐的信号侵蚀问题，提出个性化任务依赖图（PTDG），结合GCN传播与自适应渐进掩码策略，在多数据集实验及在线测试中均实现了推荐性能提升。
中文摘要 AI 辅助
优化多种转化目标是工业推荐的核心挑战，常受限于刚性架构中的信号侵蚀问题。现有多任务学习（MTL）方法通常在静态转化漏斗中强制统一的依赖强度，忽略了任务相关性会随物品特性自然变化的情况。沿这些固定链的分层消息传递会导致信号累积衰减，进而降低稀疏、深层漏斗目标的性能。为解决该问题，我们提出了个性化任务依赖图（PTDG）。在尊重必要物理因果约束（如点击→支付）的同时，PTDG通过低秩近似动态为每个物品“重连”依赖路径的强度，以确保结构稳健性。我们实现了基于GCN的传播并结合硬因果掩码，以建立自适应信息捷径。此外，我们引入了自适应渐进掩码（APM）策略，该策略根据任务稀疏性解耦共享参数，有助于稳定优化过程。在KuaiRand1K和某工业数据集上的实验表明，PTDG使稀疏转化任务的AUC显著提升了1.45%，同时在密集目标上保持了相当的性能。在线A/B测试显示，与基线相比，PTDG使转化率（CVR）提升了1.2%，有效千次展示成本（eCPM）提升了1.9%。
英文摘要
Optimizing multiple conversion objectives is a core challenge in industrial recommendation, often limited by signal erosion in rigid architectures. Existing Multi-Task Learning (MTL) methods typically enforce uniform dependency strengths across a static conversion funnel, overlooking how task correlations naturally vary based on item characteristics. Hierarchical message passing along these fixed chains leads to cumulative signal attenuation, which degrades performance on sparse, deep-funnel objectives. To address this, we propose the Personalized Task Dependency Graphs (PTDG). While respecting necessary physical causal constraints (e.g., Click -> Pay), PTDG dynamically "rewires" the intensity of dependency pathways for each item via low-rank approximation to ensure structural robustness. We implement a GCN-based propagation with hard causal masking to establish adaptive information shortcuts. Additionally, we introduce an Adaptive Progressive Masking (APM) strategy that decouples shared parameters according to task sparsity, helping to stabilize optimization. Experiments on KuaiRand1K and an industrial dataset show that PTDG significantly improves AUC on sparse conversion tasks by up to 1.45%, while maintaining comparable performance on dense objectives. Online A/B testing shows PTDG improves Conversion Rate (CVR) by 1.2% and effective Cost Per Mille (eCPM) by 1.9% relative to the baseline.
发表机构
- Huawei Technologies Co., Ltd.（华为技术有限公司）
机构由 AI 辅助整理，请以论文原文为准。
