Learning Short-Term and Long-Term Patterns of High-Order Dynamics in Real-World Networks

2025-08-24

AI Summary

Real-world networks exhibit higher-order relationships characterized by both short-term structural dependencies and long-term periodic recurrence—properties that existing methods struggle to jointly model. To address this, we propose LINCOLN, the first framework unifying bidirectional short-range interaction effects (O1) and periodic long-range reoccurrence (O2) in higher-order relational dynamics. LINCOLN innovatively integrates dual-interaction hyperedge encoding, periodic temporal injection, and intermediate node representation learning to jointly capture local structural constraints and global temporal regularities. Evaluated on dynamic hyperedge prediction, LINCOLN consistently outperforms nine state-of-the-art baselines across multiple benchmarks, demonstrating superior accuracy in modeling complex, time-varying higher-order network evolution.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems
• Web Mining and Content Analysis: Models for Web evolution

Abstract

Real-world networks have high-order relationships among objects and they evolve over time. To capture such dynamics, many works have been studied in a range of fields. Via an in-depth preliminary analysis, we observe two important characteristics of high-order dynamics in real-world networks: high-order relations tend to (O1) have a structural and temporal influence on other relations in a short term and (O2) periodically re-appear in a long term. In this paper, we propose LINCOLN, a method for Learning hIgh-order dyNamiCs Of reaL-world Networks, that employs (1) bi-interactional hyperedge encoding for short-term patterns, (2) periodic time injection and (3) intermediate node representation for long-term patterns. Via extensive experiments, we show that LINCOLN outperforms nine state-of-the-art methods in the dynamic hyperedge prediction task.

Problem

• Modeling short-term structural and temporal influences in networks
• Capturing long-term periodic reappearance of high-order relations
• Predicting dynamic hyperedge evolution in real-world networks

Innovation

• Bi-interactional hyperedge encoding for short-term patterns
• Periodic time injection for long-term patterns
• Intermediate node representation for long-term patterns