不依赖同质性假设，自适应调整图卷积强度以提升节点表征质量
Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption
- 基于节点特征聚类生成类别代理，动态调节图卷积使用程度
- 在14个基准数据集上实现领先性能，覆盖高低同质性图
- 适用于无标签场景，尤其适合异质性较强的复杂网络
无监督节点表征学习旨在不依赖节点标签的情况下获得有意义的节点嵌入。通常采用图卷积聚合邻域信息来编码节点特征与图结构。然而，在非同质性图中，过度依赖图卷积可能导致特征或拓扑差异较大的节点产生过于相似的嵌入。尽管监督学习中已探索调整图卷积使用程度，但无监督场景仍较少涉及。为此，我们提出FUEL，通过增强嵌入空间中的类内相似性和类间可分性，自适应学习合适的图卷积使用度。由于类别未知，FUEL利用节点特征识别节点簇，并将其作为类别的代理。在15种基线方法和14个基准数据集上的大量实验表明，FUEL在下游任务中表现优异，跨不同同质性水平的图均达到当前最优性能。
原文摘要 · Abstract (English)
Unsupervised node representation learning aims to obtain meaningful node embeddings without relying on node labels. To achieve this, graph convolution, which aggregates information from neighboring nodes, is commonly employed to encode node features and graph topology. However, excessive reliance on graph convolution can be suboptimal-especially in non-homophilic graphs-since it may yield unduly similar embeddings for nodes that differ in their features or topological properties. As a result, adjusting the degree of graph convolution usage has been actively explored in supervised learning settings, whereas such approaches remain underexplored in unsupervised scenarios. To tackle this, we propose FUEL, which adaptively learns the adequate degree of graph convolution usage by aiming to enhance intra-class similarity and inter-class separability in the embedding space. Since classes are unknown, FUEL leverages node features to identify node clusters and treats these clusters as proxies for classes. Through extensive experiments using 15 baseline methods and 14 benchmark datasets, we demonstrate the effectiveness of FUEL in downstream tasks, achieving state-of-the-art performance across graphs with diverse levels of homophily.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。