Stepwise reconstruction of higher-order networks from dynamics

Area of Science:

• Network science
• Complex systems analysis
• Data-driven modeling

Background:

• Higher-order networks offer advanced modeling capabilities but reconstructing their interactions is difficult.
• The exponential increase in potential interactions poses a significant computational challenge.

Purpose of the Study:

• To develop an efficient method for reconstructing higher-order networks from time series data.
• To address the challenge of the exponential growth in potential interactions.

Main Methods:

• A novel reconstruction scheme integrating a stepwise strategy.
• Incorporation of an optimization technique to infer higher-order interactions.
• Focus on networks with lower-order dependency and sparser higher-order connections.

Main Results:

• The proposed approach significantly reduces the search space for higher-order interactions.
• Demonstrated effectiveness and robustness across diverse networks and dynamical systems.
• Successful inference of higher-order network structures from time series.

Conclusions:

• The developed method provides an effective solution for higher-order network reconstruction.
• This approach advances the analysis and control of complex systems.
• The technique is robust and applicable to various network types and dynamic behaviors.