超图形半监督对比学习用于基于增强注意力聚合器的超边缘预测
Hanyu Xie1, Changjian Song1, Hao Shao1
1College of Electronic Engineering, National University of Defense Technology, Hefei 230031, China.
Entropy (Basel, Switzerland)
|October 28, 2025
概括
本研究介绍了Order propagation Fusion Self-supervised learning for Hyperedge prediction (OFSH),用于改善复杂系统中的超边缘预测. 这项研究旨在提高复杂系统中的超边缘预测. 通过解决节点异质性,超边缘顺序和数据稀疏性挑战,OFSH提高了准确性.
科学领域:
- 复杂系统科学 复杂系统科学
- 网络科学 网络科学
- 机器学习 机器学习
背景情况:
- 超边缘预测对于理解复杂系统至关重要,但受到节点影响变化,超边缘排序和稀疏数据的阻碍.
- 由于这些固有的挑战,现有的方法难以有效地捕捉高阶关系.
研究的目的:
- 提出一个新的框架,顺序传播融合超边缘预测 (OFSH) 的自我监督学习,以解决当前超边缘预测技术的局限性.
- 通过建模更高阶交互和减轻数据稀疏性来提高超边缘预测的准确性和稳定性.
主要方法:
- OFSH使用了一个超边缘顺序传播机制,具有动态节点重要性权重和最大-最小聚合用于特征放大.
- 使用带有自适应掩盖的关键节点引导增强策略来对抗数据稀疏性和保存语义信息.
- 实现了三元对比损失函数,以最大限度地提高交叉视图的一致性,并捕获不变的语义特征.
主要成果:
- 在五个现实世界超图数据集中,OFSH在超边缘预测准确度方面取得了显著的改进.
- 拟议的方法在接收器操作特征曲线 (AUROC) 下的面积和平均精度 (AP) 方面优于现有的最先进的方法.
结论:
- OFSH有效地解决了超边缘预测的关键挑战,包括节点异质性,超边缘顺序效应和数据稀疏性.
- 该框架为揭示复杂系统中高阶关系提供了强大而准确的解决方案,推进了网络科学领域.
相关概念视频
01:07End Point Prediction: Gran Plot
1.1K
A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
For potentiometric titration, the Gran plot is created by plotting...
1.1K
01:29Aggregates Classification
963
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
963