C-MAG: Cascade Multimodal Attributed Graphs for Supply Chain Link Prediction

TL;DR

This paper introduces C-MAG, a novel two-stage graph neural network architecture that leverages multimodal data to improve supply chain link prediction, supported by a new large-scale benchmark dataset PMGraph.

Contribution

It presents C-MAG, a new multimodal graph neural network architecture for supply chain link prediction, and introduces PMGraph, a comprehensive benchmark dataset for this domain.

Findings

C-MAG outperforms existing methods in link prediction accuracy.

PMGraph enables robust evaluation of multimodal supply chain graphs.

Guidelines for modality-aware fusion improve performance in noisy data.

Abstract

Workshop version accepted at KDD 2025 (AI4SupplyChain). Connecting an ever-expanding catalogue of products with suitable manufacturers and suppliers is critical for resilient, efficient global supply chains, yet traditional methods struggle to capture complex capabilities, certifications, geographic constraints, and rich multimodal data of real-world manufacturer profiles. To address these gaps, we introduce PMGraph, a public benchmark of bipartite and heterogeneous multimodal supply-chain graphs linking 8,888 manufacturers, over 70k products, more than 110k manufacturer-product edges, and over 29k product images. Building on this benchmark, we propose the Cascade Multimodal Attributed Graph C-MAG, a two-stage architecture that first aligns and aggregates textual and visual attributes into intermediate group embeddings, then propagates them through a manufacturer-product hetero-graph via multiscale message passing to enhance link prediction accuracy. C-MAG also provides practical guidelines for modality-aware fusion, preserving predictive performance in noisy, real-world settings.