GraphMatch: Fusing Language and Graph Representations in a Dynamic Two-Sided Work Marketplace

2025-12-02

AI Summary

To address the challenge of matching recommendations in dynamic, text-rich two-sided job markets, this paper proposes an end-to-end joint learning framework that pioneers deep integration of pretrained language models (PLMs) and temporal graph neural networks (GNNs). Specifically, PLMs capture fine-grained semantic evolution from job postings and candidate profiles, while moment-wise subgraph sampling and adversarial negative sampling jointly model structural and temporal dynamics of interaction graphs. The method overcomes longstanding bottlenecks in synergistic language–graph representation learning and incorporates low-latency inference optimizations for scalable real-time deployment. Evaluated on the real-world Upwork dataset, it significantly outperforms unimodal baselines—both pure language- and pure graph-based—achieving superior matching accuracy and computational efficiency. The system has been successfully deployed in production.

Technology Category

Planning, Routing, and Scheduling: Planning with Language ModelsNatural Language Processing: Language Grounding & Multi-modal NLPMachine Learning: Graph-based Machine Learning

Application Category

Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphsSearch and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for rankingUser Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Recommending matches in a text-rich, dynamic two-sided marketplace presents unique challenges due to evolving content and interaction graphs. We introduce GraphMatch, a new large-scale recommendation framework that fuses pre-trained language models with graph neural networks to overcome these challenges. Unlike prior approaches centered on standalone models, GraphMatch is a comprehensive recipe built on powerful text encoders and GNNs working in tandem. It employs adversarial negative sampling alongside point-in-time subgraph training to learn representations that capture both the fine-grained semantics of evolving text and the time-sensitive structure of the graph. We evaluated extensively on interaction data from Upwork, a leading labor marketplace, at large scale, and discuss our approach towards low-latency inference suitable for real-time use. In our experiments, GraphMatch outperforms language-only and graph-only baselines on matching tasks while being efficient at runtime. These results demonstrate that unifying language and graph representations yields a highly effective solution to text-rich, dynamic two-sided recommendations, bridging the gap between powerful pretrained LMs and large-scale graphs in practice.

Problem

• Fuses language and graph models for dynamic marketplace recommendations
• Overcomes evolving content and interaction graph challenges
• Enables real-time matching with low-latency inference

Innovation

• Fuses pre-trained language models with graph neural networks
• Uses adversarial negative sampling and point-in-time subgraph training
• Enables low-latency inference for real-time recommendation systems