Mixture of Message Passing Experts with Routing Entropy Regularization for Node Classification
This work addresses a significant problem in graph-based learning tasks, particularly for researchers and practitioners dealing with heterophilous graph structures, by providing a unified and principled approach for node classification.
The authors tackled the limitation of graph neural networks (GNNs) in handling heterophilous structures, and their proposed framework GNNMoE achieved state-of-the-art node classification results on twelve benchmark datasets. GNNMoE consistently outperformed existing methods, demonstrating its effectiveness in adaptive representation learning.
Graph neural networks (GNNs) have achieved significant progress in graph-based learning tasks, yet their performance often deteriorates when facing heterophilous structures where connected nodes differ substantially in features and labels. To address this limitation, we propose GNNMoE, a novel entropy-driven mixture of message-passing experts framework that enables node-level adaptive representation learning. GNNMoE decomposes message passing into propagation and transformation operations and integrates them through multiple expert networks guided by a hybrid routing mechanism. And a routing entropy regularization dynamically adjusts soft weighting and soft top-$k$ routing, allowing GNNMoE to flexibly adapt to diverse neighborhood contexts. Extensive experiments on twelve benchmark datasets demonstrate that GNNMoE consistently outperforms SOTA node classification methods, while maintaining scalability and interpretability. This work provides a unified and principled approach for achieving fine-grained, personalized node representation learning.