[论文] [论文] Diffusion-Induced Spatial Attention Overlapping Community De...

论文概要

研究领域: 图学习
作者: Kosti Koistinen, Vesa Kuikka, Joni Herttuainen, Matthew Hendren, Brian Holt et al.
发布时间: 2026-09-22
arXiv: 2609.26737

中文摘要

重叠社区检测对节点同时参与多组的网络建模至关重要。现有 GNN 方法多依赖局部消息传递，平滑效应会模糊社区边界，且难表示结构相关的长程依赖。我们提出 DISCO——结合影响力传播动力学结构先验、稀疏多头注意力与非负社区归属学习的深度学习框架。先验识别直接邻居之外的候选交互并按结构接近性偏置注意力；Bernoulli-Poisson 边重建目标支持从节点属性、结构轮廓或两者推断重叠社区。基准实验显示 DISCO 在不同输入配置下相对成熟的图卷积/图注意力方法具竞争力。网络安全概念验证：连续通信网络快照的社区归属变化提供可解释异常信号，时间社区相似度识别结构偏离，节点级贡献帮助定位相关设备。DISCO 既是灵活的重叠社区检测方法，也为动态网络结构变化分析奠基。

原文摘要

Detection of overlapping communities is essential for modelling networks in which nodes participate simultaneously in multiple structural or functional groups. Existing graph neural network approaches commonly rely on local message passing, which can obscure community boundaries through smoothing and limit the representation of structurally relevant long-range dependencies. We introduce Diffusion-Induced Spatial Attention Community Detection (DISCO), a deep-learning framework that combines a structural prior derived from influence spreading dynamics, sparse multi-head attention, and non-negative community-affiliation learning. The prior identifies candidate interactions beyond immediate graph neighbours and biases attention according to their structural proximity, while a Bernoulli-Poisson edge-reconstruction objective enables overlapping community inference from node attributes and structural profiles, or both. Benchmark experiments show that DISCO performs competitively against established graph convolutional and graph attention approaches across different input configurations. To demonstrate its practical applicability, we present a proof-of-concept cybersecurity use case in which changes between community assignments inferred from consecutive communication-network snapshots provide an interpretable anomaly signal. Temporal community similarity identifies structural deviations, while node-level contributions help locate the devices associated with them. DISCO therefore provides both a flexible method for overlapping community detection and a foundation for analysing structural change in dynamic networks.

自动采集于 2026-09-24

#论文 #arXiv #图学习 #小凯