一种评估图神经网络进展的以数据为中心的方法
A data-centric approach for assessing progress of Graph Neural Networks
AI总结:
针对多标签节点分类研究数据集稀缺、传统同异质性概念不适用的问题,该研究发布3个真实生物数据集与可调多标签图生成器,定义适配的同质性与跨类邻域相似度,并通过8种方法在9个数据集上的大规模对比评估GNN在该任务的进展。
摘要:
图神经网络(GNNs)已在节点分类任务中取得了当前最优(state-of-the-art)结果。然而,大多数改进集中在多类分类上,对每个节点可能具有多个标签的场景关注较少。研究多标签节点分类的首要挑战是公开可用数据集的稀缺。为解决这一问题,我们收集并发布了三个真实世界生物数据集,并开发了一个具有可调属性的多标签图生成器。我们还认为,传统的同质性(homophily)和异质性(heterophily)概念不能很好地适用于多标签场景。因此,我们为多标签分类定义了同质性和跨类邻域相似度(Cross-Class Neighborhood Similarity),并对9个收集到的多标签数据集展开了研究。最后,我们在9个数据集上对8种方法开展了大规模对比研究,以评估当前多标签节点分类的进展。我们在https://github.com/Tianqi-py/MLGNC 发布了代码。
英文摘要:
Graph Neural Networks (GNNs) have achieved state-of-the-art results in node classification tasks. However, most improvements are in multi-class classification, with less focus on the cases where each node could have multiple labels. The first challenge in studying multi-label node classification is the scarcity of publicly available datasets. To address this, we collected and released three real-world biological datasets and developed a multi-label graph generator with tunable properties. We also argue that traditional notions of homophily and heterophily do not apply well to multi-label scenarios. Therefore, we define homophily and Cross-Class Neighborhood Similarity for multi-label classification and investigate $9$ collected multi-label datasets. Lastly, we conducted a large-scale comparative study with $8$ methods across nine datasets to evaluate current progress in multi-label node classification. We release our code at \url{https://github.com/Tianqi-py/MLGNC}.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。