A Scalable and Efficient Signal Integration System for Job Matching
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916842110451712 |
|---|---|
| author | Liu, Ping Arora, Rajat Shi, Xiao Le, Benjamin Shen, Qianqi Shen, Jianqiang Jiang, Chengming Zhiltsov, Nikita Bannur, Priya Zhu, Yidan Dong, Liming Wei, Haichao Guo, Qi Simon, Luke Hong, Liangjie Zhang, Wenjing |
| author_facet | Liu, Ping Arora, Rajat Shi, Xiao Le, Benjamin Shen, Qianqi Shen, Jianqiang Jiang, Chengming Zhiltsov, Nikita Bannur, Priya Zhu, Yidan Dong, Liming Wei, Haichao Guo, Qi Simon, Luke Hong, Liangjie Zhang, Wenjing |
| contents | LinkedIn, one of the world's largest platforms for professional networking and job seeking, encounters various modeling challenges in building recommendation systems for its job matching product, including cold-start, filter bubbles, and biases affecting candidate-job matching. To address these, we developed the STAR (Signal Integration for Talent And Recruiters) system, leveraging the combined strengths of Large Language Models (LLMs) and Graph Neural Networks (GNNs). LLMs excel at understanding textual data, such as member profiles and job postings, while GNNs capture intricate relationships and mitigate cold-start issues through network effects. STAR integrates diverse signals by uniting LLM and GNN capabilities with industrial-scale paradigms including adaptive sampling and version management. It provides an end-to-end solution for developing and deploying embeddings in large-scale recommender systems. Our key contributions include a robust methodology for building embeddings in industrial applications, a scalable GNN-LLM integration for high-performing recommendations, and practical insights for real-world model deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09797 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A Scalable and Efficient Signal Integration System for Job Matching Liu, Ping Arora, Rajat Shi, Xiao Le, Benjamin Shen, Qianqi Shen, Jianqiang Jiang, Chengming Zhiltsov, Nikita Bannur, Priya Zhu, Yidan Dong, Liming Wei, Haichao Guo, Qi Simon, Luke Hong, Liangjie Zhang, Wenjing Machine Learning LinkedIn, one of the world's largest platforms for professional networking and job seeking, encounters various modeling challenges in building recommendation systems for its job matching product, including cold-start, filter bubbles, and biases affecting candidate-job matching. To address these, we developed the STAR (Signal Integration for Talent And Recruiters) system, leveraging the combined strengths of Large Language Models (LLMs) and Graph Neural Networks (GNNs). LLMs excel at understanding textual data, such as member profiles and job postings, while GNNs capture intricate relationships and mitigate cold-start issues through network effects. STAR integrates diverse signals by uniting LLM and GNN capabilities with industrial-scale paradigms including adaptive sampling and version management. It provides an end-to-end solution for developing and deploying embeddings in large-scale recommender systems. Our key contributions include a robust methodology for building embeddings in industrial applications, a scalable GNN-LLM integration for high-performing recommendations, and practical insights for real-world model deployment. |
| title | A Scalable and Efficient Signal Integration System for Job Matching |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2507.09797 |