Hierarchical Job Classification with Similarity Graph Integration

2025-07-14

AI Summary

To address low classification accuracy, difficulty in modeling hierarchical industry-category relationships, and cold-start challenges in online job recruitment, this paper proposes Carotene—a semantic-enhanced representation learning framework that jointly leverages a hierarchical taxonomy and a job similarity graph structure. Carotene is the first approach to simultaneously encode hierarchical constraints of occupational classification systems and graph-structured relational semantics, embedding both jobs and categories into a shared latent space. It introduces a hierarchical classification loss and integrates graph neural networks for end-to-end optimization. Evaluated on a large-scale real-world job dataset, Carotene significantly outperforms state-of-the-art baselines, achieving substantial gains in classification accuracy. Empirical results demonstrate its strong capability in capturing both hierarchical semantics and structural dependencies. The framework establishes a scalable, robust paradigm for dynamic job matching, personalized job recommendation, and labor market analytics.

Technology Category

• Machine Learning: Representation Learning
• Search and Optimization: Learning to Search
• Knowledge Representation and Reasoning: Ontologies

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies

Abstract

In the dynamic realm of online recruitment, accurate job classification is paramount for optimizing job recommendation systems, search rankings, and labor market analyses. As job markets evolve, the increasing complexity of job titles and descriptions necessitates sophisticated models that can effectively leverage intricate relationships within job data. Traditional text classification methods often fall short, particularly due to their inability to fully utilize the hierarchical nature of industry categories. To address these limitations, we propose a novel representation learning and classification model that embeds jobs and hierarchical industry categories into a latent embedding space. Our model integrates the Standard Occupational Classification (SOC) system and an in-house hierarchical taxonomy, Carotene, to capture both graph and hierarchical relationships, thereby improving classification accuracy. By embedding hierarchical industry categories into a shared latent space, we tackle cold start issues and enhance the dynamic matching of candidates to job opportunities. Extensive experimentation on a large-scale dataset of job postings demonstrates the model's superior ability to leverage hierarchical structures and rich semantic features, significantly outperforming existing methods. This research provides a robust framework for improving job classification accuracy, supporting more informed decision-making in the recruitment industry.

Problem

• Improving job classification accuracy in dynamic online recruitment
• Addressing limitations of traditional text classification methods
• Enhancing candidate-job matching with hierarchical industry categories

Innovation

• Embedding jobs into latent space
• Integrating SOC and Carotene taxonomies
• Leveraging hierarchical semantic features