Title | ||
---|---|---|
RIMNet: Recommendation Incentive Mechanism based on evolutionary game dynamics in peer-to-peer service networks. |
Abstract | ||
---|---|---|
In peer-to-peer service networks, autonomous agents gain utilities through getting services from others. However, providing services is so costly that rational agents may prefer to defect rather than to cooperate. In order to provide scalable and robust services in such networks, incentive mechanisms need to be introduced. In this paper, we propose a novel approach RIM (Recommendation Incentive Mechanism) by building a cooperative agents recommendation system. And, in order to investigate the acceptance and performance of the proposed RIM, evolutionary game theory has been used. By studying the evolutionary stable state, we demonstrate the performance of the RIM-based model by both considering two scenarios PRIM/IRIM (Perfect/Imperfect Recommendation Incentive Mechanism). To comprehensively confirm the robustness of our mechanism: (1) OCMP (One Consumer Multi-service Providers) method has been discussed, in which agent could simultaneously request services from k (k>1) different agents; (2) a FS (Four-Strategies) game model has been further introduced; (3) QS (Quantity Sensitivity) scenario has been researched, in which the utility of an agent is sensitive to the amount of received services. By using the Lyapunov stability theory, it is qualitatively proved that non-cooperative agents can be well suppressed in our proposed RIM. Finally, extensive numerical and simulation experiments are conducted to highlight the performance and validate the theoretical properties of our model. |
Year | DOI | Venue |
---|---|---|
2019 | 10.1016/j.knosys.2018.12.024 | Knowledge-Based Systems |
Keywords | Field | DocType |
Evolutionary game theory,Cooperation theory,Incentive mechanism,Peer-to-peer service networks,Eigentrust | Recommender system,Autonomous agent,Peer-to-peer,Incentive,Rational agent,Computer science,Robustness (computer science),Artificial intelligence,Evolutionary game theory,Machine learning,Distributed computing,Scalability | Journal |
Volume | ISSN | Citations |
166 | 0950-7051 | 1 |
PageRank | References | Authors |
0.34 | 28 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mingchu Li | 1 | 469 | 78.10 |
Xing Jin | 2 | 2 | 2.05 |
Cheng Guo | 3 | 47 | 9.84 |
Jia Liu | 4 | 3 | 4.77 |
Guanghai Cui | 5 | 6 | 2.76 |
Tie Qiu | 6 | 895 | 80.18 |