A survey on deep graph generation: Methods and applications
Graphs are ubiquitous in encoding relational information of real-world objects in many
domains. Graph generation, whose purpose is to generate new graphs from a distribution …
domains. Graph generation, whose purpose is to generate new graphs from a distribution …
Diffusion models for graphs benefit from discrete state spaces
Denoising diffusion probabilistic models and score-matching models have proven to be very
powerful for generative tasks. While these approaches have also been applied to the …
powerful for generative tasks. While these approaches have also been applied to the …
Molecule generation for drug design: a graph learning perspective
Machine learning, particularly graph learning, is gaining increasing recognition for its
transformative impact across various fields. One such promising application is in the realm of …
transformative impact across various fields. One such promising application is in the realm of …
ChemSpacE: interpretable and interactive chemical space exploration
Discovering meaningful molecules in the vast combinatorial chemical space has been a
long-standing challenge in many fields from materials science to drug discovery. Recent …
long-standing challenge in many fields from materials science to drug discovery. Recent …
[PDF][PDF] Towards better graph generative models and glob-ally accurate evaluation metrics
R Wattenhofer - tik-db.ee.ethz.ch
Graph generation is an interesting problem which is encountered when trying to generate
novel molecules or proteins with desired properties or variations of social graphs that used …
novel molecules or proteins with desired properties or variations of social graphs that used …