Back to Catalog

Light Graph Convolutional Network for Recommender Systems

AdvancedGuided Project

Learn how to build a recommender system using Graph Convolutional Networks (GCN) with the LightGCN model. In this guided project, you’ll construct a user–item interaction graph, implement LightGCN in PyTorch, and evaluate it using Recall@K and NDCG@K. By the end, you’ll understand the theoretical foundations of LightGCN and apply it effectively to real recommendation tasks. You will also explore how message passing captures multi-hop collaborative signals, gaining a complete practical workflow for modern graph-based recommendation while learning to analyze embedding behavior in depth.

Language

  • English

Topic

  • Artificial Intelligence

Skills You Will Learn

  • Artificial Intelligence, Recommender Systems, Graph Convolutional Networks (GCNs), Collaborative Filtering, Bayesian Personalized Ranking (BPR), Bipartite Graph

Offered By

  • IBMSkillsNetwork

Estimated Effort

  • 60 minutes

Platform

  • SkillsNetwork

Last Update

  • January 28, 2026
About this Guided Project
In this project, you’ll walk through each stage of building a modern graph-based recommender system, from preparing the interaction data to implementing message passing and training the LightGCN model. You’ll gain both conceptual understanding and hands-on experience with real datasets and a complete end-to-end recommendation pipeline..

Who Is It For

This project is designed for software developers, data scientists, or AI practitioners interested in Graph Neural Networks (GNNs) and their applications in recommender systems. It is ideal for learners who want to understand how Graph Convolutional Networks (GCNs) model relational data such as user–item interactions, explore how LightGCN streamlines traditional GCN architectures to better handle large-scale recommendation scenarios, and gain practical experience by implementing a real graph-based recommendation pipeline that connects theoretical concepts directly to hands-on practice.

What You’ll Learn

By the end of this project, you will be able to:
  • Understand the theoretical foundations of Graph Convolutional Networks (GCNs) and how LightGCN simplifies them.
  • Build and train a LightGCN recommender system in PyTorch using the MovieLens dataset.
  • Evaluate the model using Recall@K and NDCG@K metrics, and generate Top-K recommendations.

What You'll Need

Learners should have proficiency in Python and prior experience with interactive coding environments. A working knowledge of machine learning fundamentals, including embeddings, loss functions, and evaluation metrics, is recommended. All required libraries can be installed directly within the IBM Skills Network Labs environment, allowing you to set up and run the workflow without external configuration. The project works best on modern browsers such as Chrome, Edge, Firefox, or Safari.

Instructors

Zikai Dou

Data Scientist at IBM

Ph.D. Candidate in Computer Science at McMaster University, specializing in Federated Learning (FL), Graph Neural Networks (GNNs), and Computer Vision (CV). I develop privacy-preserving, distributed AI systems that tackle real-world challenges in healthcare, finance, and enterprise applications. Passionate about bridging academic research with industry impact to advance scalable and trustworthy AI.

Read more

Contributors

Joseph Santarcangelo

Senior Data Scientist at IBM

Joseph has a Ph.D. in Electrical Engineering, his research focused on using machine learning, signal processing, and computer vision to determine how videos impact human cognition. Joseph has been working for IBM since he completed his PhD.

Read more

Wojciech "Victor" Fulmyk

Data Scientist at IBM

Wojciech "Victor" Fulmyk is a Data Scientist and AI Engineer on IBM’s Skills Network team, where he focuses on helping learners build expertise in data science, artificial intelligence, and machine learning. He is also a Kaggle competition expert, currently ranked in the top 3% globally among competition participants. An economist by training, he applies his knowledge of statistics and econometrics to bring a distinctive perspective to AI and ML—one that considers both technical depth and broader socioeconomic implications.

Read more