arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2006.06427cs.SIcs.LGstat.ML
收藏

了解您的FATE:社交应用程序上用户参与预测的友谊,行动和时间解释

Knowing your FATE: Friendship, Action and Temporal Explanations for User Engagement Prediction on Social Apps

The Pennsylvania State University(宾夕法尼亚州立大学);Snap Inc.(Snap公司)

Xianfeng Tang, Yozen Liu, Neil Shah, Xiaolin Shi, Prasenjit Mitra, Suhang Wang

摘要:

随着近年来社交网络应用(App)的快速增长和普及,了解用户参与变得越来越重要,为未来App设计和开发提供有用的见解。虽然最近有几种有前途的神经建模方法被用于准确的用户参与预测,但不幸的是,它们的黑盒设计在模型的可解释性方面受到限制。在本文中,我们研究了一个新的问题,可解释的社交网络应用程序的用户参与预测。首先,我们提出了一个灵活的定义,用户参与各种业务场景的基础上,未来的指标预期。接下来,我们设计了一个端到端的神经框架FATE,它结合了我们确定的影响用户参与的三个关键因素,即友谊,用户行为和时间动态,以实现可解释的参与预测。FATE基于基于张量的图神经网络(GNN)、LSTM和混合注意力机制,它允许(a)基于不同特征类别的学习权重进行预测解释,(b)降低网络复杂性,(c)提高预测准确性和训练/推理时间的性能。我们在Snapchat的两个大规模数据集上进行了广泛的实验,其中FATE通过${\approx}10\%$错误和${\approx}20\%$运行时间减少来优于最先进的方法。我们还评估了FATE的解释,显示出强大的定量和定性性能。

英文摘要:

With the rapid growth and prevalence of social network applications (Apps) in recent years, understanding user engagement has become increasingly important, to provide useful insights for future App design and development. While several promising neural modeling approaches were recently pioneered for accurate user engagement prediction, their black-box designs are unfortunately limited in model explainability. In this paper, we study a novel problem of explainable user engagement prediction for social network Apps. First, we propose a flexible definition of user engagement for various business scenarios, based on future metric expectations. Next, we design an end-to-end neural framework, FATE, which incorporates three key factors that we identify to influence user engagement, namely friendships, user actions, and temporal dynamics to achieve explainable engagement predictions. FATE is based on a tensor-based graph neural network (GNN), LSTM and a mixture attention mechanism, which allows for (a) predictive explanations based on learned weights across different feature categories, (b) reduced network complexity, and (c) improved performance in both prediction accuracy and training/inference time. We conduct extensive experiments on two large-scale datasets from Snapchat, where FATE outperforms state-of-the-art approaches by ${\approx}10\%$ error and ${\approx}20\%$ runtime reduction. We also evaluate explanations from FATE, showing strong quantitative and qualitative performance.

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。

↑