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
https://github.com/Tianqi-py/MLGNC.

图神经网络在节点分类任务中取得了最先进的结果。本文聚焦于多标签节点分类，通过收集和发布了三个真实的生物数据集，并开发了一个可调参数的多标签图生成器。进一步提出了适用于多标签分类的同质性和跨类邻域相似性的定义，并以 $9$ 个收集的多标签数据集为基础进行了研究。最后，通过对 $8$ 个方法在九个数据集上进行大规模对比研究，评估了目前在多标签节点分类方面的进展。代码已在 https://github.com/Tianqi-py/MLGNC 上发布。

评估图神经网络进展的数据导向方法

A data-centric approach for assessing progress of Graph Neural Networks

Graph Neural Networks (GNNs) achieve state-of-the-art performance on
graph-structured data across numerous domains. Their underlying ability to
represent nodes as summaries of their vicinities has proven effective for
homophilous graphs in particular, in which same-type nodes tend to connect. On
heterophilous graphs, in which different-type nodes are likely connected, GNNs
perform less consistently, as neighborhood information might be less
representative or even misleading. On the other hand, GNN performance is not
inferior on all heterophilous graphs, and there is a lack of understanding of
what other graph properties affect GNN performance.
In this work, we highlight the limitations of the widely used homophily ratio
and the recent Cross-Class Neighborhood Similarity (CCNS) metric in estimating
GNN performance. To overcome these limitations, we introduce 2-hop Neighbor
Class Similarity (2NCS), a new quantitative graph structural property that
correlates with GNN performance more strongly and consistently than alternative
metrics. 2NCS considers two-hop neighborhoods as a theoretically derived
consequence of the two-step label propagation process governing GCN's
training-inference process. Experiments on one synthetic and eight real-world
graph datasets confirm consistent improvements over existing metrics in
estimating the accuracy of GCN- and GAT-based architectures on the node
classification task.

通过介绍 2NCS 方法，本文挖掘了同质网络比率和 Cross-Class 邻域相似性 (CCNS) 等指标的局限性，并在一个合成和 8 个真实图数据集上进行实验，结果表明 2NCS 可以更准确和一致地评估基于 GCN 和 GAT 的体系结构在节点分类任务上的准确性。