Graph Evolution Rule Generation for Network Pattern Mining
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for analyzing the temporal evolution of social networks are inefficient and require significant computational resources, failing to effectively identify and utilize evolutional patterns for predictive and discriminative purposes across various applications.
Innovation Solution
A system and method that characterizes network evolution by generating graph evolution rules through mining temporal patterns in a network's graph representation, where patterns are identified and used to create rules indicating the occurrence of subgraphs over time, enabling predictive analysis and discrimination among different networks.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If conventional network analysis methods are used to examine social networks, then network evolution can be analyzed, but significant computational resources are consumed and efficiency is low
Solution Approach 1:
The patent segments the network evolution analysis into distinct temporal snapshots and identifies specific evolutional patterns (subgraphs) within these snapshots. By dividing the complex analysis into manageable segments representing different time points and pattern types, the system achieves higher efficiency while reducing overall computational resource requirements.
Solution Approach 2:
The patent performs preliminary actions by pre-identifying evolutional patterns and generating graph evolution rules from historical network snapshots before actual predictive analysis is needed. This preliminary pattern recognition and rule generation enables faster, more efficient analysis when predicting future network evolution, thereby improving productivity while reducing real-time computational resource consumption.
2Reliability
If comprehensive network evolution analysis is performed to identify patterns, then predictive capabilities are enhanced, but computational complexity increases
Solution Approach 1:
The patent extracts and focuses specifically on evolutional patterns (subgraphs) that are relevant to network evolution, separating these key features from the complete network data. By taking out only the essential pattern information needed for prediction rather than analyzing all network characteristics, the system enhances predictive reliability while reducing computational complexity.
Solution Approach 2:
The patent changes parameters by representing network evolution through graph evolution rules that capture temporal relationships between patterns. This parameter transformation from raw network data to structured evolution rules simplifies the computational model while maintaining or enhancing predictive capability for future network states.
3Measurement precision
If detailed evolutional patterns are mined from network graphs, then discrimination among different networks is improved, but analysis time increases
Solution Approach 1:
The patent performs preliminary pattern mining and rule generation from historical network data before actual discrimination tasks are performed. By pre-extracting evolutional patterns and encoding them into graph evolution rules, the system achieves high network discrimination accuracy when needed while minimizing analysis time during actual use.
Solution Approach 2:
The patent creates simplified representations (copies) of network evolution through graph evolution rules that capture essential discriminative features without requiring analysis of the complete original network data. These rule-based copies enable rapid, accurate network discrimination while significantly reducing analysis time compared to examining full network structures.
Data Source
AI summary
A network's evolution is characterized by graph evolution rules. A graph, formed by merging multiple graphs representing the multiple snapshots of the network, that represents an evolutionary network is mined to identify evolutional patterns of the network. A pattern is selected from the identified patterns. Graph evolution rules are generated using identified evolutional patterns. The generated graph evolution rules represent the evolutional patterns of the network, the rules indicating that any occurrence of a child pattern of the selected pattern implies a corresponding occurrence of the selected pattern.