用语言模型提升异质图的消息传递效果，兼顾性能与效率
Language Models as Messengers: Enhancing Message Passing in Heterophilic Graph Learning
- 用语言模型从节点文本中建模语义关系，生成更优消息
- 在异质图上超越现有方法，在同质图上也保持稳定表现
- 通过启发式筛选关键消息对，降低计算开销，适合实际应用
图神经网络（GNN）已成为图表示学习的标准范式，但其消息传递机制隐含假设：消息可由源节点嵌入表示，这一假设在异质图中失效。现有方法通过图结构优化或邻居聚合调整来应对异质性，却常忽视节点文本的语义潜力，依赖次优的消息表示，且在同质图上性能下降。为此，我们提出 LEMP4HG，一种基于语言模型（LM）的异质图消息传递新方法。针对带文本属性的图（TAG），利用语言模型显式建模节点对之间的语义关系，合成语义感知的消息进行传播。为保障实际效率，进一步引入受定制启发式 MVRD 指导的主动学习策略，仅对最受影响的节点对增强消息。大量实验表明，LEMP4HG 在异质图上持续优于当前最优方法，同时在同质图上保持鲁棒性能，且计算开销可控。
原文摘要 · Abstract (English)
Graph neural networks (GNNs) have become a standard paradigm for graph representation learning, yet their message passing mechanism implicitly assumes that messages can be represented by source node embeddings, an assumption that fails in heterophilic graphs. While existing methods attempt to address heterophily through graph structure refinement or adaptation of neighbor aggregation, they often overlook the semantic potential of node text, relying on suboptimal message representation for propagation and compromise performance on homophilic graphs. To address these limitations, we propose LEMP4HG, a novel language model (LM)-enhanced message passing approach for heterophilic graph learning. Specifically, for text-attributed graphs (TAG), we leverage a LM to explicitly model inter-node semantic relationships from paired node texts, synthesizing semantically informed messages for propagation. To ensure practical efficiency, we further introduce an active learning-inspired strategy guided by a tailored heuristic, MVRD, which selectively enhances messages for node pairs most affected by message passing. Extensive experiments demonstrate that LEMP4HG consistently outperforms state-of-the-art methods on heterophilic graphs while maintaining robust performance on homophilic graphs under a practical computational budget.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。