计算机科学
图形
人工神经网络
采样(信号处理)
人工智能
理论计算机科学
电信
探测器
作者
Wei Duan,Jie Lü,Yu Guang Wang,Junyu Xuan
出处
期刊:Cornell University - arXiv
日期:2024-03-18
被引量:10
标识
DOI:10.48550/arxiv.2403.11408
摘要
Graph neural networks (GNNs) are a powerful solution for various structure learning applications due to their strong representation capabilities for graph data. However, traditional GNNs, relying on message-passing mechanisms that gather information exclusively from first-order neighbours (known as positive samples), can lead to issues such as over-smoothing and over-squashing. To mitigate these issues, we propose a layer-diverse negative sampling method for message-passing propagation. This method employs a sampling matrix within a determinantal point process, which transforms the candidate set into a space and selectively samples from this space to generate negative samples. To further enhance the diversity of the negative samples during each forward pass, we develop a space-squeezing method to achieve layer-wise diversity in multi-layer GNNs. Experiments on various real-world graph datasets demonstrate the effectiveness of our approach in improving the diversity of negative samples and overall learning performance. Moreover, adding negative samples dynamically changes the graph's topology, thus with the strong potential to improve the expressiveness of GNNs and reduce the risk of over-squashing.
科研通智能强力驱动
Strongly Powered by AbleSci AI