Tripartite Vector Representations for Better Job Recommendation
This addresses job matching for online recruitment platforms, though it appears incremental as it builds on existing graph-based representation learning approaches.
The paper tackles job recommendation by learning joint representations of job titles and skills from three information graphs, then combining them with location information. Results show significant improvement in relevancy compared to baseline methods.
Job recommendation is a crucial part of the online job recruitment business. To match the right person with the right job, a good representation of job postings is required. Such representations should ideally recommend jobs with fitting titles, aligned skill set, and reasonable commute. To address these aspects, we utilize three information graphs ( job-job, skill-skill, job-skill) from historical job data to learn a joint representation for both job titles and skills in a shared latent space. This allows us to gain a representation of job postings/ resume using both elements, which subsequently can be combined with location. In this paper, we first present how the presentation of each component is obtained, and then we discuss how these different representations are combined together into one single space to acquire the final representation. The results of comparing the proposed methodology against different base-line methods show significant improvement in terms of relevancy.