Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence

ArXi:2605.18893v1 Announce Type: new Graph Neural Networks (GNNs) are powerful tools for learning from graph-structured data, but their scalability is increasingly strained by the size of real-world graphs in domains like recommender systems, fraud detection, and molecular biology. Graph condensation -- the task of generating a smaller synthetic graph that retains the performance of models trained on the original -- has emerged as a promising solution.