Research explainers on graph neural networks — GCNs, GATs, message passing, and graph-based representation learning.
A grading crew on an Alabama highway project trusts a stream of centimeter level corrections to steer its machines. Those corrections come from a statewide network of permanent GNSS reference stations that the Department of Transportation owns and maintains. If…
Statewide CORS Networks as a GNSS Spoofing Sensor Read More »
Graph pattern matching asks a deceptively simple question. Given a small pattern graph, maybe a triangle, maybe a four node clique, find every place in a much larger data graph where that exact shape of connections appears. It shows up…
PGMiner Tackles the Three Ways GPUs Waste Work on Graphs Read More »
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 »
Graph neural networks look deceptively sturdy on paper. Stack a few convolution layers, pool the node embeddings, feed the result to a classifier, and you get strong numbers on clean benchmark data. The trouble starts once the input graph stops…
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 »
Vision transformers earned their place in medical imaging because self attention lets a model connect a finding in one part of an image to context somewhere else entirely, the kind of long range reasoning a small convolution kernel cannot do…
FadeFormer: Graph Diffusion Sharpens Medical Image Classification Read More »
Wind speed forecasting has a long history built on physical simulation, statistical time series methods, and more recently deep networks. Global wind capacity keeps climbing, and China alone added 80 gigawatts in 2024, which the paper notes was roughly seventy…
Adaptive Graph Attention Improves Wind Vector Forecasting Read More »
Unsupervised image segmentation asks a model to draw meaningful boundaries around objects in a photo without ever being told what those objects are. No labeled training data, no annotated masks, just pixels in and a partition of the image out.…
DeepCut++’s Single Best Fusion Weight Does Not Actually Win Every Task 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 »