https://www.infoq.com InfoQ Graph Database feed https://www.infoq.com/presentations/graph-neural-networks/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Graph+Database <img src="https://res.infoq.com/presentations/graph-neural-networks/en/mediumimage/Mariia-Bulycheva-medium-1775048997053.jpeg"/><p>Mariia Bulycheva discusses the transition from classic deep learning to GNNs for Zalando's landing page. She explains the complexities of converting user logs into heterogeneous graphs, the "message passing" training process, and the technical pitfalls of graph data leakage. She shares how a hybrid architecture solved inference latency, delivering contextual embeddings to a downstream model.</p> <i>By Mariia Bulycheva</i> Machine Learning Transcripts Neural Networks Graph Database InfoQ Dev Summit Munich 2025 AI, ML & Data Engineering presentation Mon, 13 Apr 2026 13:23:00 GMT https://www.infoq.com/presentations/graph-neural-networks/?utm_campaign=infoq_content&utm_source=infoq&utm_medium=feed&utm_term=Graph+Database Mariia Bulycheva 2026-04-13T13:23:00Z /presentations/graph-neural-networks/en