topological perception post-processing confidence coefficient correction method applied to GNN
A correction method and confidence level technology, applied in neural learning methods, biological neural network models, design optimization/simulation, etc., can solve problems such as overconfidence in prediction, low prediction accuracy of the model, and inability to be added to the training set, etc., to improve The effect of confidence
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0037] In the present invention, we focus on the properties of undirected FIG correction G = (V, E) adjacent matrix A∈R N*N And the node feature matrix X = [x 1 , ..., x N ]. V is the set of nodes, E∈V * V is the set of edges constituting the edge between nodes, N = | V | is the number of nodes. We give GNN is perfectly corrected definition:
[0038] Definition 1: Given a random variable And a GNN model f θ , Where θ is a learning parameter for node i, y is the label which is defined i ∈Y, GNN output is z i = F θ (x i , A) = (z i,1 ,...,z i,K ), And define with Respectively, and the corresponding prediction model of confidence, then we say when f θ Is the perfect time to meet the correction is defined as follows:
[0039]
[0040] 1 definition, only when the confidence When exactly equal to the true probability of each node to get a correct prediction, GNN was only perfect correction.
[0041] Next, we have two GNN (GCN and GAT) representative example to analyze whether or n...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap