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

Pending Publication Date: 2021-11-23
BEIJING UNIV OF POSTS & TELECOMM
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Confidence correction has attracted considerable attention in deep learning, and many studies have shown that modern neural network models are overconfident in predictions, i.e., the prediction accuracy of the model is lower than its confidence
However, the problem of confidence correction has not been studied in GNNs, thus, this raises a fundamental question: Can current GNNs be as overconfident in their predictions as o

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • topological perception post-processing confidence coefficient correction method applied to GNN
  • topological perception post-processing confidence coefficient correction method applied to GNN
  • topological perception post-processing confidence coefficient correction method applied to GNN

Examples

Experimental program
Comparison scheme
Effect test

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...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a topological perception post-processing confidence coefficient correction method applied to a GNN. The confidence coefficient is corrected by using the homogeneity of the confidence coefficient in the GNN, the correction function is nonlinear transformation, while the classification precision of the original GNN is also saved. Besides, the invention provides a corrected GNN self-training method based on the correction method, the confidence is firstly calibrated by CaGCN and then is used for generating a pseudo tag, high-confidence prediction can be effectively utilized, and the effectiveness of the method provided by the invention in the aspects of correction and accuracy is proved through a large number of experiments.

Description

technical field [0001] The invention relates to the technical field of fiber lasers, in particular to a post-processing confidence correction method applied to GNN topology perception. Background technique [0002] Graphs are ubiquitous in the real world, including social networks, e-commerce networks, transportation networks, etc. Recently, graph neural networks (GNNs) based on message passing have attracted considerable attention in processing graph data. So far, GNNs have been widely used in various applications and achieved remarkable results, such as node classification, link prediction, and graph classification, etc. [0003] In practical applications, however, accuracy is not the only goal. In many applications, especially in the security domain, a trustworthy model is highly desirable. Generally speaking, a trustworthy model means that it should know when its predictions may be incorrect. In other words, the probability (confidence) associated with a predicted cl...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06F30/27G06N3/04G06N3/08G06F111/08
CPCG06F30/27G06N3/04G06N3/084G06F2111/08
Inventor 王啸石川刘洪瑞
Owner BEIJING UNIV OF POSTS & TELECOMM
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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