Samsung patents method to compress data for graph neural networks
Samsung describes a way to train graph neural networks, which are computer models that learn from data connected in a network like social media or maps. The method creates a smaller, compressed version of the data at each step of the training process to make the calculations more efficient.
In the filing’s own words
A processor-implemented method including generating, based on a first matrix multiplication between an adjacency matrix of train nodes for training a graph neural network (GNN) and a first feature matrix of the train nodes corresponding to a previous layer of the GNN, a second feature matrix corresponding to a current layer of the GNN, generating, by the second feature matrix, a first hidden feature vector of each of the train nodes and a second hidden feature vector of each of the train nodes, and generating a compressed representation of the second feature matrix based on the first hidden feature vector and the second hidden feature vector.
What exactly they claim (claim 1)
1. An electronic device, comprising: one or more processors comprising processing circuitry; and a memory comprising one or more storage media storing instructions that, when executed individually or collectively by the one or more processors, cause the electronic device to: generate, based on a first matrix multiplication between an adjacency matrix of train nodes for training a graph neural network (GNN) and a first feature matrix of the train nodes corresponding to a previous layer of the GNN, a second feature matrix corresponding to a current layer of the GNN; generate, by the second feature matrix, a first hidden feature vector of each of the train nodes and a second hidden feature vector of each of the train nodes; and generate a compressed representation of the second feature matrix based on the first hidden feature vector and the second hidden feature vector.
Facts
- Company
- Samsung (Samsung Electronics Co., Ltd.)
- Official title
- METHOD AND DEVICE WITH GNN-BASED INFERENCE
- Publication number
- US20260330183A1
- Application number
- 19468143
- Filed
- Feb 3, 2026
- Published
- Oct 22, 2026
- Inventors
- 3
- Claims
- 20
Classified under
G06N 3/042 Physics & computingMore from Samsung in AI & software
- Samsung patents tool to erase objects from photos using AI Sep 24, 2026
- Samsung patents drawing objects into photos with AI Oct 15, 2026
- Samsung patents AI that creates personalized exercise videos Sep 10, 2026
- Samsung patents AI summaries for paused TV shows based on your viewing habits Sep 24, 2026
- Samsung patents turning chat conversations into image prompts Oct 1, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.