Research explainers on graph neural networks — GCNs, GATs, message passing, and graph-based representation learning.
Picture a strip of land seen through radar instead of a camera. A river cuts a clean line through farmland, a cluster of buildings sits in a blocky grid, and a forest spreads out as a grainy, speckled mess. To…
Manifold Aware Fusion for PolSAR Image Classification 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 »
Brain network analysis usually works like this. Take a resting state fMRI scan, split the brain into a fixed number of regions using an anatomical atlas such as AAL with its 116 regions, measure how correlated each region’s activity is…
Clustering data that comes from more than one source, several sensors describing the same object, or several feature extractors run on the same image, is called multi-view clustering, and the whole point is to combine complementary information across those views…
How Frequency Truncation Improves Multi-View Spectral Clustering Read More »
Most of what the research community knows about backdoor attacks on graphs comes from homogeneous graphs, where every node and every edge is the same type. In that setting, an attacker can attach almost any subgraph to almost any node,…
Backdoor Attacks Now Target Heterogeneous Graph Neural Networks Read More »
Most real recommendation catalogs are lopsided by design. A small number of items collect the overwhelming majority of clicks, purchases, or plays, while a much larger number sit with only a handful of interactions each. Collaborative filtering, the workhorse behind…
CHAKG Lets Popular Items Rescue Long Tail Recommendations Read More »
Retail demand planning would be simple if every product existed in isolation. It does not. A grocery chain needs a forecast for total daily revenue, for each brand it stocks, for each store, and for each item on the shelf,…
Graph Neural Networks Bring Coherent Forecasts to Retail Read More »
AngioGraphCAD models coronary arteries as graphs, letting a graph neural network assess lesion-level risk the way cardiologists reason — one lesion at a time.