Graph Analysis Algorithm Ranking via GXAI Correlation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing graph analysis algorithms for graph-structured data are numerous, making it difficult to determine which algorithms are most effective for a given dataset, and the results from graph explainable artificial intelligence (GXAI) techniques can be complex and difficult for users to interpret.

Innovation Solution

A method that involves obtaining a dataset of graph-structured data, determining the correlation between GXAI results and graph analysis algorithm results, ranking the graph analysis algorithms based on this correlation, and assigning a threshold number of algorithms to general characteristics of the dataset, with the results visualized in a graphical user interface (GUI).

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple graph analysis algorithms are used to analyze graph-structured data, then the comprehensiveness of analysis is improved, but the difficulty of selecting appropriate algorithms increases

Engineering Contradiction:

Improvecomprehensiveness of analysisVSAvoiddifficulty of selecting algorithms

Core Design Contradiction:

Adaptability or versatilityVSEase of operation

Solution Approach 1:

The patent introduces an intermediary system that automatically evaluates and ranks graph analysis algorithms based on their correlation with GXAI techniques. This intermediary assessment mechanism mediates between the user and the large number of algorithms, providing a ranked list that simplifies selection while maintaining comprehensive analysis coverage.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the parameter of algorithm selection from manual user choice to automated ranking based on correlation metrics. By introducing correlation coefficients as a new parameter to evaluate algorithm performance against GXAI techniques, the system transforms the selection process into an objective, data-driven ranking system.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If GXAI techniques are used to analyze graph-structured data, then the depth of analysis is improved, but the interpretability of results deteriorates

Engineering Contradiction:

Improvedepth of analysisVSAvoidinterpretability of results

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The patent uses correlation analysis as an intermediary to bridge GXAI techniques and traditional graph analysis algorithms. By measuring the correlation between GXAI results and algorithm outputs, the system translates complex GXAI findings into interpretable metric that users can understand while retaining the depth of GXAI analysis.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If a large number of graph analysis algorithms are available, then the coverage of analysis capabilities is improved, but the time required to select algorithms increases

Engineering Contradiction:

Improvecoverage of analysis capabilitiesVSAvoidtime required for selection

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent performs preliminary action by pre-evaluating and ranking all available graph analysis algorithms against GXAI techniques before actual data analysis. This advance ranking creates a ready-to-use ordered list that eliminates the time-consuming selection process during actual analysis tasks.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The automated correlation-based ranking system acts as an intermediary that quickly processes and evaluates multiple algorithms, providing a pre-ordered selection list that saves users significant time while maintaining comprehensive coverage of analysis capabilities.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12321391B2Enhancing graph explainability through graph analysis algorithms

Publication Date: 2025.06.03 FUJITSU LTD

AI summary

A method may include obtaining a dataset of graph-structured data, the dataset including one or more subgraphs. The method may include determining a correlation between analyses of the dataset using graph explainable artificial intelligence (GXAI) techniques and using a plurality of graph analysis algorithms. A ranked list of the plurality of graph analysis algorithms may be generated based on the correlation. The method may further include determining general characteristic of the dataset of graph-structured data, the general characteristic indicative of similarities among the one or more subgraphs. A threshold number of the graph analysis algorithms may be assigned to the general characteristic based on the ranked list of the plurality of graph analysis algorithms. An assignment table may be generated including the general characteristic and the threshold number of the graph analysis algorithms. A display may be generated within a graphical user interface (GUI) that visualizes the assignment table.