Research explainers on graph neural networks — GCNs, GATs, message passing, and graph-based representation learning.
Most machine learning arguments are about the model. This one is about the starting line. A team at the University of Southern California took a leading system for completing uncertain knowledge graphs, changed nothing about how it scores facts, and…
QUEST Fixes Where Uncertain Knowledge Graph Models Start Read More »
Delete a fifth of the edges in a protein interaction graph, or swap a handful of atom labels in a molecule, and most graph neural networks start guessing. A team at Dalian University of Technology built a classifier that barely…
HPGRL: How Hierarchical Prototypes Make Graph Classification Resist Noise Read More »
A materials scientist sits down with a fresh stack of papers and already knows the stack is a rounding error. The field now publishes more abstracts in a year than any one person could read in a decade of weekends.…
How LLMs and Concept Graphs Predict New Materials Research Read More »
For half a century, simulating how atoms move has followed the same ritual. Work out the force on every atom, nudge each one a tiny step, then do it again, and again, millions of times over, with each step covering…
Force Free Molecular Dynamics With Equivariant Networks Read More »
A radiologist scanning a chest film is not looking at one pixel at a time. A hazy patch of infiltration blurs into the surrounding lung field, and the eye naturally follows that blur rather than treating it as a hard…
FadeFormer: Graph Diffusion Sharpens Medical Image Classification Read More »
Picture a grid operator in Haikou staring at a wind farm dashboard the night before a typhoon brushes past the coast. Wind speed matters, but so does wind direction, since a turbine yawed the wrong way loses power and takes…
Adaptive Graph Attention Improves Wind Vector Forecasting Read More »
Ask a radiology resident to find the spleen on a single unfamiliar scan after seeing only one labeled example beforehand and you are asking for exactly the problem this paper takes on, except the resident here is a neural network.…
Prototype Guided Graph Reasoning for Few Shot Medical Segmentation Read More »
Transformers rewrote what was possible in language and vision, so pointing them at graphs looked like a sure bet. The bet mostly paid off on small graphs and mostly stalled on large ones. The reason is simple to state and…
A Graph Transformer That Scales to Billions of Nodes Read More »
Imagine a citation graph with more than seven hundred thousand papers, each carrying a bag of words feature vector and a web of references to its neighbors. Training a graph neural network on something that size can exhaust memory before…
Universal Graph Coarsening Made Fast With Hashing Read More »
Open a Julia REPL, type using GraphNeuralNetworks, and you are three lines away from training a graph convolutional network on a GPU without ever touching Python. That sentence would have sounded like wishful thinking five years ago. Carlo Lucibello and…
GraphNeuralNetworks.jl Brings Serious GNN Tooling to Julia Read More »