What question did this study set out to answer?

To develop an automated, large-scale graph partitioning algorithm that simultaneously accounts for structural network topologies, user attribute disparities, and partition load balancing.

October 2, 2025Scientific ReportsOpen Access

A social network graph partitioning algorithm based on double deep Q-Network

View Full Paper

Ask AI

Bookmark

Authors

JCJie CaoShenyang Pharmaceutical University HWHaoxiang WangKing's College London KHKekun HuTongji University

Discussion

Member takes

Implication

Benchmarking study reveals reduced edge cuts and balanced load distribution in social networks, indicating enhanced computational efficiency for large-scale graph analysis.

Key Points

To develop an automated, large-scale graph partitioning algorithm that simultaneously accounts for structural network topologies, user attribute disparities, and partition load balancing.
Designed GP-DQN, combining Graph Convolutional Networks (GCN) to aggregate vertex attributes and local neighborhood structures into feature representations.
Implemented a Double Deep Q-Network (DDQN) guided by a specialized reward function to predict partition rewards and assign vertices iteratively using immediate and expected feedback.
GP-DQN consistently maintained a balanced computational load distribution across all target partitions.
Significantly reduced the number of edge cuts across partition boundaries compared to conventional partitioning baselines, improving intra-partition computing efficiency.

Cite This Study

Cao et al. (2025) studied this question.

synapsesocial.com/papers/6a7cb242704b28adc84c78ea https://doi.org/10.1038/s41598-025-16768-x

View Full Paper

Ask AI

Bookmark

Implication

Benchmarking study reveals reduced edge cuts and balanced load distribution in social networks, indicating enhanced computational efficiency for large-scale graph analysis.

A social network graph partitioning algorithm based on double deep Q-Network

Discussion

Member takes

Implication

Key Points

Cite This Study

A social network graph partitioning algorithm based on double deep Q-Network

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider