Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore advanced techniques for scaling Graph-based Retrieval-Augmented Generation (GraphRAG) systems to handle massive, planetary-scale knowledge graphs in this 42-minute conference talk. Discover cutting-edge research from leading institutions including work on PyG 2.0 for scalable learning on real-world graphs, methods for extending GraphRAG to millions of documents through the "Millions of GeAR-s" approach, and query-aware multi-path knowledge graph fusion techniques that enhance retrieval-augmented generation in large language models. Learn from researchers at Huawei Technologies, University of Edinburgh, University of Science and Technology Beijing, and other institutions as they present breakthrough solutions for processing and querying enormous knowledge graphs. Gain insights into the technical challenges and innovative approaches required to make GraphRAG systems work effectively at unprecedented scales, from handling millions of documents to implementing sophisticated fusion strategies that improve the performance of large language models in knowledge-intensive tasks.
