Mitigating Oversmoothing Through Reverse Process of GNNs for Heterophilic Graphs
This addresses the challenge of classifying nodes in heterophilic graphs, where adjacent nodes have different labels, offering an incremental improvement to existing GNN variants.
The paper tackles the problem of oversmoothing in Graph Neural Networks (GNNs) by proposing a reverse process of message passing, which improves prediction performance on heterophilic graphs, with experiments showing significant gains and mitigation of oversmoothing over hundreds of layers.
Graph Neural Network (GNN) resembles the diffusion process, leading to the over-smoothing of learned representations when stacking many layers. Hence, the reverse process of message passing can produce the distinguishable node representations by inverting the forward message propagation. The distinguishable representations can help us to better classify neighboring nodes with different labels, such as in heterophilic graphs. In this work, we apply the design principle of the reverse process to the three variants of the GNNs. Through the experiments on heterophilic graph data, where adjacent nodes need to have different representations for successful classification, we show that the reverse process significantly improves the prediction performance in many cases. Additional analysis reveals that the reverse mechanism can mitigate the over-smoothing over hundreds of layers. Our code is available at https://github.com/ml-postech/reverse-gnn.