Graph Feature Gating Networks
This work addresses a potential limitation in GNNs for graph representation learning, though it appears incremental as it builds on existing message-passing schemes.
The paper tackled the problem of treating all feature dimensions equally in graph neural networks (GNNs) by proposing a graph feature gating network (GFGN) that allows heterogeneous contributions from different dimensions, resulting in demonstrated effectiveness and robustness across various real-world datasets.
Graph neural networks (GNNs) have received tremendous attention due to their power in learning effective representations for graphs. Most GNNs follow a message-passing scheme where the node representations are updated by aggregating and transforming the information from the neighborhood. Meanwhile, they adopt the same strategy in aggregating the information from different feature dimensions. However, suggested by social dimension theory and spectral embedding, there are potential benefits to treat the dimensions differently during the aggregation process. In this work, we investigate to enable heterogeneous contributions of feature dimensions in GNNs. In particular, we propose a general graph feature gating network (GFGN) based on the graph signal denoising problem and then correspondingly introduce three graph filters under GFGN to allow different levels of contributions from feature dimensions. Extensive experiments on various real-world datasets demonstrate the effectiveness and robustness of the proposed frameworks.