GraphMuon adapts Muon optimizer to GNNs for faster convergence
Guy Hadad · hf · 2026-11-12
Researchers from Ben-Gurion University introduced GraphMuon, adapting Muon's matrix orthogonalization to the covariance of graph-propagated representations. Since graph propagation amplifies updates in GNNs, GraphMuon's module-aware optimization suppresses this graph-induced amplification, reaching target validation loss faster on graph benchmarks.
More from Research
- E11 Bio hiring computational scientist for petabyte imaging and agentic AI labs — anderssandberg · 2026-11-12
- EPFL: Claude writes EEG network weights by reasoning, matching gradient training with 6x fewer subjects — epfl-ch · 2026-11-12
- Differentiable SSSS framework brings single-image real-time skin digitization to game engines — ssh4net · 2026-11-12
- NeurIPS paper proves when RNN+MLP can provably recover true robot state — chriswolfvision · 2026-11-12
- Curated 9-paper reading list for LLM quantization beginners, from QLoRA to BitNet — East-Muffin-6472 · 2026-11-12
- A Quick Diagnostic Guide to 4 Common ML Training Errors and Their Causes — cneuralnetwork · 2026-11-12