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

2025/12/02 by Mikołaj Sacha, Hammad Jafri, Sacha, Mikołaj +7
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Machine Learning (cs.LG) #Multimodal Machine Learning Applications #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2512.02849

openalex publication_date 2025/12/02 · openalex created_date 2025/12/04 · openalex updated_date 2026/07/28

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.

Citations

• Unifying Text Semantics and Graph Structures for Temporal Text-attributed Graphs with Large Language Models
• Embedding And Clustering Your Data Can Improve Contrastive Pretraining
• DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs
• SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning
• Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs
• Text Embeddings by Weakly-Supervised Contrastive Pre-training
• Learning on Large-scale Text-attributed Graphs via Variational Inference
• Large Dual Encoders Are Generalizable Retrievers
• Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
• How Attentive are Graph Attention Networks?
• GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
• Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling
• Understanding Negative Samples in Instance Discriminative Self-supervised Representation Learning
• Large-Scale Representation Learning on Graphs via Bootstrapping
• Graph Contrastive Learning with Augmentations
• Contrastive Learning with Hard Negative Samples
• Hard Negative Mixing for Contrastive Learning
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• Graph Attention Networks
• Inductive Representation Learning on Large Graphs

Related

• Graph Learning in the Era of LLMs: A Survey from the Perspective of Data, Models, and Tasks
• Enhancing Collaborative Semantics of Language Model-Driven Recommendations via Graph-Aware Learning
• Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations
• Parameter-Efficient Tuning Large Language Models for Graph Representation Learning
• LOGIN: A Large Language Model Consulted Graph Neural Network Training Framework