Deep Graph Neural Networks struggle with oversmoothing. This paper introduces a novel, physics-inspired GNN model designed to mitigate this issue. Our approach integrates with existing GNN architectures, introducing an entropy-aware message passing term. This term performs gradient ascent on the entropy during node aggregation, thereby preserving a certain degree of entropy in the embeddings. We conduct a comparative analysis of our model against state-of-the-art GNNs across various common datasets.

翻译：深度图神经网络面临过平滑问题。本文提出了一种新颖的、受物理学启发的图神经网络模型，旨在缓解这一问题。我们的方法可与现有图神经网络架构集成，引入一个熵感知的消息传递项。该术语在节点聚合过程中对熵进行梯度上升，从而在嵌入中保留一定程度的熵。我们针对多种常见数据集，将我们的模型与最先进的图神经网络进行了对比分析。