SiGMA: Learning under Graph-Level Heterogeneity with Gated Message-Passing and Attention
A gated hybrid GNN that adapts message-passing and attention to graph-level heterogeneity.
Publications
You can also find my articles on my Google Scholar profile.
Filter by area
Broad areas sit on the first row; narrower areas nest underneath. Use the arrows to fold a row. Click a tag to filter; click again to clear.
No publications match this area yet.
Higher-Order Learning with Graph Neural Networks via Hypergraph Encodings
Hypergraph encodings that make higher-order structure useful for graph neural networks in relational learning.
Transfer Learning with Physics-Informed Neural Networks for Efficient Simulation of Branched Flows
Transfer learning with physics-informed neural networks for efficient simulation of branched flows.
SiGMA: Learning under Graph-Level Heterogeneity with Gated Message-Passing and Attention
Proceedings of the Fifth Learning on Graphs Conference (LoG 2026), 2026
A gated hybrid GNN that adapts message-passing and attention to graph-level heterogeneity.
Higher-Order Learning with Graph Neural Networks via Hypergraph Encodings
NeurIPS, 2025
Hypergraph encodings that make higher-order structure useful for graph neural networks in relational learning.
Transfer Learning with Physics-Informed Neural Networks for Efficient Simulation of Branched Flows
NeurIPS, Machine Learning and the Physical Sciences Workshop, 2022
Transfer learning with physics-informed neural networks for efficient simulation of branched flows.