KAP-CPD: Kernel Aggregation for Change-Point Detection in Dynamic Networks

2026-05-14

AI Summary

This work addresses the sensitivity of change-point detection in dynamic networks to kernel choice and the difficulty of pre-specifying an appropriate kernel under unknown change patterns. To overcome these limitations, the authors propose KAP-CPD, a novel framework that introduces multi-kernel aggregation into this task for the first time, adaptively fusing information from multiple kernels to achieve both flexibility and robustness without assuming a specific network distribution. Furthermore, they develop KAPf-CPD, a fast analytical testing procedure that replaces computationally intensive permutation tests, substantially improving scalability for long sequences. Experimental results demonstrate that the proposed approach achieves superior detection power and computational efficiency across diverse synthetic scenarios as well as real-world datasets, including email communication logs and functional brain connectivity networks.

Abstract

Change-point detection in dynamic networks has received much attention due to its broad applications in social networks and biological systems. Kernel-based methods have shown strong potential for this problem. However, their performance can depend sensitively on the choice of kernel, and selecting an appropriate kernel is challenging when the underlying change pattern is unknown. Motivated by this challenge, we propose KAP-CPD, a new kernel-based testing framework for change-point detection in dynamic networks. KAP-CPD aggregates information from multiple kernels, allowing it to adapt to diverse change patterns. The proposed method does not assume specific underlying network distribution, and achieves strong empirical power across a wide range of network change scenarios. To improve scalability, we further develop a fast analytic testing procedure, KAPf-CPD, that substantially reduces computation time for long network sequences compared with permutation-based alternatives and current state-of-the-art methods. We evaluate our proposed framework through extensive simulations and real-world data on email communication networks and brain functional connectivity networks.

Problem

• change-point detection
• dynamic networks
• kernel selection
• unknown change patterns

Innovation

• kernel aggregation
• change-point detection
• dynamic networks
• scalable testing
• nonparametric method