Network Dismantling on Signed Network by Evolutionary Deep Reinforcement Learning
2024

Network Dismantling on Signed Network by Evolutionary Deep Reinforcement Learning

publication Evidence: high

Author Information

Author(s): Ou Yuxuan, Xiong Fujing, Zhang Hairong, Li Huijia

Primary Institution: School of Statistics and Data Science, Nankai University, Tianjin, China

Hypothesis

The study proposes a new algorithm, DSEDR, to effectively dismantle signed networks by integrating evolutionary computation and deep reinforcement learning.

Conclusion

The DSEDR algorithm outperforms existing methods in both efficiency and interpretability for signed network dismantling.

Supporting Evidence

  • DSEDR integrates evolutionary computation and deep reinforcement learning for optimal network dismantling.
  • The algorithm was tested on both artificial and real network datasets.
  • DSEDR showed superior performance compared to eight popular baseline methods.

Takeaway

This study created a smart way to break down complex networks by removing certain connections, which helps in understanding and managing relationships in social networks.

Methodology

The study uses a combination of evolutionary computation and deep reinforcement learning to optimize the dismantling of signed networks.

Digital Object Identifier (DOI)

10.3390/s24248026

Want to read the original?

Access the complete publication on the publisher's website

View Original Publication