Symmetry-Aware GFlowNets
stat.ML, cs.LG
Submitted: 2025-06-03
Updated: 2025-10-16
Comments: 29 pages; Accepted at ICML 2025
Journal ref: Proceedings of the 42nd International Conference on Machine Learning (ICML 2025), pp. 30334-30362
Code: https://github.com/hohyun312/sagfn
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation
- Graph Neural Networks with Learnable Structural and Positional Representations
- Adam: A Method for Stochastic Optimization
- Learning Deep Generative Models of Graphs
- Baking Symmetry into GFlowNets
- MolecularRNN: Generating realistic molecular graphs with optimized properties
- GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
- Learning-Order Autoregressive Models with Application to Molecular Graph Generation
- How Powerful are Graph Neural Networks?
Related papers
- Behavior of prediction performance metrics with rare events
- Optimal Estimation of Generic Dynamics by Path-Dependent Neural Jump ODEs
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Scalable Posterior Uncertainty for Flexible Density-Based Clustering
- Efficient quadratic entropy with distance sketches
- Embedding-Bias in Conditional Independence Testing