CheckMate! Watermarking Graph Diffusion Models in Polynomial Time
Roberto Gheda, Abele Malan, Robert Birke, Maksim Kitsak, Lydia Y. Chen A watermarking framework for graph diffusion models, with verification in polynomial time.
Collaborative and Confidential Junction Trees for Hybrid Bayesian Networks
Roberto Gheda, Abele Malan, Thiago Guzella, Carlo Lancia, Robert Birke, Lydia Y. Chen A multi-party root-cause analysis framework for Bayesian Networks, with improved scalability and precision.
Workshop Papers
ICLR 2026 Workshop on Test-Time Updates | Graph Diffusion Models
Test-time Graph Extrapolation via Progressive Anchor-Guided Expansion
Abele Malan, Roberto Gheda, Robert Birke, Lydia Y. Chen Sampling conditioning to preserve validity of graphs generated by diffusion models at scale.
Under Review
Under Review | Graph Diffusion Models, Attributed Graphs
Attributed Graph Generation via Mixed-type Diffusion and Coarsening
Abele Malan, Roberto Gheda, Robert Birke, Lydia Y. Chen A diffusion model for generating graphs with rich node features.
Under Review | Federated Learning, Diffusion Models
Variance-Informed Latent Guidance for Private Time-Series Generation
Antreas Ioannou, Aditya Shankar, Roberto Gheda, Lydia Y. Chen A framework for server-side privacy-preserving synthesis of time series data.