[论文解读] How LinkedIn Economic Graph Bonds Information and Product: Applications in LinkedIn Salary

Xi Chen, Yiqun Liu+2 more|arXiv (Cornell University)|Jun 24, 2018

Data Mining Algorithms and Applications参考文献 18被引用 9

一句话总结

本文提出了一种两阶段框架，利用领英的经济图谱推断无直接数据的群体的公司级薪资洞察。通过利用基于成员流动模式的 Company2vec 嵌入表示，并结合同行公司群体的贝叶斯平滑方法，该方法在保持精度略有提升的同时，将美国职位-地区-公司组合的洞察覆盖范围扩大了 35 倍，实现了可扩展的、保护隐私的薪资洞察，惠及数百万用户。

ABSTRACT

The LinkedIn Salary product was launched in late 2016 with the goal of providing insights on compensation distribution to job seekers, so that they can make more informed decisions when discovering and assessing career opportunities. The compensation insights are provided based on data collected from LinkedIn members and aggregated in a privacy-preserving manner. Given the simultaneous desire for computing robust, reliable insights and for having insights to satisfy as many job seekers as possible, a key challenge is to reliably infer the insights at the company level when there is limited or no data at all. We propose a two-step framework that utilizes a novel, semantic representation of companies (Company2vec) and a Bayesian statistical model to address this problem. Our approach makes use of the rich information present in the LinkedIn Economic Graph, and in particular, uses the intuition that two companies are likely to be similar if employees are very likely to transition from one company to the other and vice versa. We compute embeddings for companies by analyzing the LinkedIn members' company transition data using machine learning algorithms, then compute pairwise similarities between companies based on these embeddings, and finally incorporate company similarities in the form of peer company groups as part of the proposed Bayesian statistical model to predict insights at the company level. We perform extensive validation using several different evaluation techniques, and show that we can significantly increase the coverage of insights while, in fact, even improving the quality of the obtained insights. For example, we were able to compute salary insights for 35 times as many title-region-company combinations in the U.S. as compared to previous work, corresponding to 4.9 times as many monthly active users. Finally, we highlight the lessons learned from deployment of our system.

研究动机与目标

• 解决在缺乏或无成员提交数据的情况下，提供可靠且保护隐私的公司级薪资洞察的挑战。
• 通过将洞察扩展至数据丰富的群体之外，提升产品覆盖范围，以服务更多求职者。
• 确保即使在无直接薪酬提交数据的公司中，洞察依然具备鲁棒性和可靠性。
• 利用领英经济图谱，基于员工流动模式建模公司间的相似性。
• 在领英薪资产品中实现可扩展、可投入生产的公司级洞察页面。

提出的方法

• 使用带有负采样的跳字模型方法，在领英成员的公司流动历史数据上训练 Company2vec 嵌入表示。
• 基于学习到的嵌入表示计算公司间的成对相似度，为每家公司定义同行公司群体。
• 将同行公司群体信息整合进贝叶斯分层平滑模型，以估计公司级薪资洞察。
• 结合（职位，地区）层级的估计值与公司特定的调整项，利用同行群体数据对稀疏或零数据情形进行平滑处理。
• 应用去标识化、聚合和阈值化等隐私保护技术，以保护成员数据。
• 采用具有分层先验的统计建模方法，在数据稀缺时从相似公司中借用信息。

实验结果

研究问题

• RQ1 如何可靠地推断无成员提交数据的公司的薪资洞察？
• RQ2 员工在公司之间的流动模式在多大程度上可作为薪酬情境下公司相似性的代理指标？
• RQ3 学习到的公司嵌入表示能否在保护隐私的前提下提升薪资洞察的准确性和覆盖范围？
• RQ4 与基线模型相比，通过贝叶斯平滑方法整合同行公司群体信息，如何提升洞察质量和覆盖范围？
• RQ5 该框架对现实产品指标（如洞察覆盖范围和用户触达）产生了何种影响？

主要发现

• 所提出的框架使美国（职位，地区，公司）群体中可获得薪资洞察的数量相比以往工作提升了 35 倍。
• 洞察覆盖范围扩展至涵盖 4.9 倍的月活跃领英用户，显著提升了产品的可及性。
• 尽管覆盖范围大幅增加，但洞察质量仍略有提升，经与去标识化的成员数据对比验证。
• Company2vec 模型成功捕捉了基于流动模式的语义公司关系，从而实现了有效的同行群体构建。
• 贝叶斯平滑模型有效利用了同行群体信息，在低数据环境下稳定了估计值，且未损害准确性。
• 该系统展现出强大的生产可行性，已成功部署六个月以上，并产生了可衡量的业务影响。