Simplifying Graph Convolutional Networks with Redundancy-Free Neighbors
This addresses a critical bottleneck in deep graph learning for researchers and practitioners, offering a novel perspective rather than incremental improvements.
The paper tackles the over-smoothing problem in Graph Convolutional Networks (GCNs) by identifying over-aggregation from redundant neighbor information as its fundamental cause, proposing a redundancy-free approach to simplify GCNs.
In recent years, Graph Convolutional Networks (GCNs) have gained popularity for their exceptional ability to process graph-structured data. Existing GCN-based approaches typically employ a shallow model architecture due to the over-smoothing phenomenon. Current approaches to mitigating over-smoothing primarily involve adding supplementary components to GCN architectures, such as residual connections and random edge-dropping strategies. However, these improvements toward deep GCNs have achieved only limited success. In this work, we analyze the intrinsic message passing mechanism of GCNs and identify a critical issue: messages originating from high-order neighbors must traverse through low-order neighbors to reach the target node. This repeated reliance on low-order neighbors leads to redundant information aggregation, a phenomenon we term over-aggregation. Our analysis demonstrates that over-aggregation not only introduces significant redundancy but also serves as the fundamental cause of over-smoothing in GCNs.