Presentation
GNNs on Evolving Graphs: A Benchmark of Incremental Updates and Meta-Learning Approaches
DescriptionThe field of graph machine learning has seen significant growth with the success of graph neural networks (GCNs). However, most traditional GCNs are designed for static graphs. In the real world, graphs are constantly evolving—new users join social networks, molecules change shape, and data streams into a network. Re-computing a GCN's embeddings for the entire graph every time a small change occurs is computationally expensive and inefficient. This research explores two more efficient approaches: a standard incremental update method and a novel meta-learning approach, which are then benchmarked to compare their performance.
Event Type
Research and ACM SRC Posters
TimeFriday, 21 November 20258:00am - 12:00pm CST
LocationSecond Floor Atrium
Archive
view