AI RESEARCH
Closed-Form Node Classification with Exact Graph Unlearning
arXiv CS.LG
•
ArXi:2605.25662v1 Announce Type: new Graph neural networks for node classification are typically trained by gradient descent over hundreds or thousands of epochs. Recent work has shown that, when properly tuned, classic GCN/SAGE/GAT architectures can match graph transformers on many node-classification benchmarks.