Overview of Graph Augmented LLM Systems

Hosted by Amir Feizpour and Percy Chen

Fri, Jul 25, 2025

4:00 PM UTC (45 minutes)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Build Multi-Agent Applications - A Bootcamp - LangGraph, Cursor, n8n
Amir Feizpour, PhD
View syllabus

What you'll learn

how graphs enhance retrieval-augmented generation

why graph design is critical for system performance

NodeRAG, GraphRAG and LightRAG

Why this topic matters

This talk introduces RAG frameworks on knowledge graphs. We'll focus on using these graphs to improve LLMs' performance on structured tasks such as multi-hop question answering. These frameworks combine the planning ability of LLMs and the relational knowledge stored in graphs to handle queries requiring complex reasoning chains and indirect facts that are not explicitly present in training data.

You'll learn from

Amir Feizpour

Founder @ Aggregate Intellect

Amir Feizpour is the founder, CEO, and Chief Scientist at Aggregate Intellect building a generative business brain for service and science based companies. Amir has built and grown a global community of 5000+ AI practitioners and researchers gathered around topics in AI research, engineering, product development, and responsibility. Prior to this, Amir was an NLP Product Lead at Royal Bank of Canada. Amir held a research position at University of Oxford conducting experiments on quantum computing resulting in high profile publications and patents. Amir holds a PhD in Physics from University of Toronto. Amir also serves the AI ecosystem as an advisor at MaRS Discovery District, works with several startups as fractional chief AI officer, and engages with a wide range of community audiences (business executives to hands-on developers) through training and educational programs. Amir leads Aggregate Intellect’s R&D via several academic collaborations.

Percy Chen

PhD Candidate, McGill University

Percy is a PhD candidate in the Department of Electrical and Computer Engineering at McGill University, where he is supervised by Prof. Daniel Varro and Prof. Gunter Mussbacher. His research focuses on applying model-based techniques to enhance the reliability and robustness of machine learning systems. Percy’s work spans evaluating machine learning model quality for tasks like model generation, bug detection, and code summarization, with a keen interest in leveraging large language models for software engineering.

In addition to his academic pursuits, Percy works as an R&D Engineer at Aggregate Intellect through a Mitacs grant, contributing to practical innovations in AI and is an active contributor to Sherpa, an open-source framework aimed at making large language models more robust and user-friendly. He also serves as a part-time Research Associate at Huawei Waterloo Research Center.

Learn directly from Amir Feizpour and Percy Chen

By continuing, you agree to Maven's Terms and Privacy Policy.

© 2025 Maven Learning, Inc.