Research and ACM SRC Posters Archive

GNNs on Evolving Graphs: A Benchmark of Incremental Updates and Meta-Learning Approaches

Poster Type: Research Posters

Author: Sriram Srinivasan (Bowie State University), Sanjukta Bhowmick (University of North Texas), Hamdan Alabsi (Bowie State University), Rand Obeidat (Bowie State University)

Supervisor:

Abstract: The 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.

Best Poster Finalist (BP): no
Poster: PDF
Poster Summary: PDF

Back to Poster Archive Listing