- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Automatic Translation feature is available on CiNii Labs
- Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
Interpretable Social Network Forecasting based on Multi-Agent Reinforcement Learning
-
- MIYAKE Kentaro
- University of Tsukuba
-
- ITO Hiroyoshi
- University of Tsukuba
-
- FUALOUTSOS Christos
- Carnegie Mellon University
-
- MATSUMOTO Hirotomo
- University of Tsukuba
-
- MORISHIMA Atsuyuki
- University of Tsukuba
Bibliographic Information
- Other Title
-
- マルチエージェント強化学習に基づくソーシャルネットワークの解釈可能な将来予測手法
Search this article
Description
Predicting how social networks change in the future is important in many applications. Results in social network research have shown that the change in the network can be explained by a small number of concepts, such as “homophily” and “transitivity”. However, existing prediction methods require many latent features making the methods' black boxes and their prediction results difficult to interpret, and making them harder to derive scientific knowledge. In this study, we propose NETEVOLVE a novel multi-agent reinforcement learning-based method that predicts changes in a given social network. Given a sequence of changes as training data, NETEVOLVE learns the characteristics of the nodes with interpretable features, such as how the node feels rewards for connecting with similar people and the cost of the connection itself. Based on the learned feature, NETEVOLVE makes a forecast based on multi-agent simulation. NETEVOLVE achieves comparable or better accuracy than existing methods in predicting network changes in real-world social networks while keeping the prediction results interpretable.
Journal
-
- 電子情報通信学会論文誌D 情報・システム
-
電子情報通信学会論文誌D 情報・システム J108-D (5), 307-317, 2025-05-01
The Institute of Electronics, Information and Communication Engineers
- Tweet
Details 詳細情報について
-
- CRID
- 1390022476719856640
-
- ISSN
- 18810225
- 18804535
-
- Text Lang
- ja
-
- Data Source
-
- JaLC
-
- Abstract License Flag
- Disallowed