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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sacha, Mikołaj, Jafri, Hammad, Terzolo, Mattie, Sinha, Ayan, Rabinovich, Andrew
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915648924286976
author Sacha, Mikołaj
Jafri, Hammad
Terzolo, Mattie
Sinha, Ayan
Rabinovich, Andrew
author_facet Sacha, Mikołaj
Jafri, Hammad
Terzolo, Mattie
Sinha, Ayan
Rabinovich, Andrew
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_02849
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle GraphMatch: Fusing Language and Graph Representations in a Dynamic Two-Sided Work Marketplace
Sacha, Mikołaj
Jafri, Hammad
Terzolo, Mattie
Sinha, Ayan
Rabinovich, Andrew
Machine Learning
Artificial Intelligence
Information Retrieval
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.
title GraphMatch: Fusing Language and Graph Representations in a Dynamic Two-Sided Work Marketplace
topic Machine Learning
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2512.02849