Graph Energy Matching: Transport-Aligned Energy-Based Modeling for Graph Generation

ArXi:2603.23398v1 Announce Type: cross Energy-based models for discrete domains, such as graphs, explicitly capture relative likelihoods, naturally enabling composable probabilistic inference tasks like conditional generation or enforcing constraints at test-time. However, discrete energy-based models typically struggle with efficient and high-quality sampling, as off- regions often contain spurious local minima, trapping samplers and causing