针对节点模式差异，用专家混合模型提升分类准确率
Mixture of Experts for Node Classification
- 按节点特征动态选择不同预测模型
- 在多个真实图数据集上显著优于单一模型
- 适合处理异质性高的复杂网络节点分类
现实世界图中的节点在度分布、同质性等方面呈现多样化模式，但现有节点分类器通常无法捕捉多种模式，导致性能不佳。本文发现不同节点预测器擅长处理特定模式的节点，统一使用单一模型会带来次优结果。为此，提出MoE-NP框架，结合多个节点预测器并根据节点特征智能选择最适模型。在多个真实数据集上的实验表明，该方法显著提升了分类性能。
原文摘要 · Abstract (English)
Nodes in the real-world graphs exhibit diverse patterns in numerous aspects, such as degree and homophily. However, most existent node predictors fail to capture a wide range of node patterns or to make predictions based on distinct node patterns, resulting in unsatisfactory classification performance. In this paper, we reveal that different node predictors are good at handling nodes with specific patterns and only apply one node predictor uniformly could lead to suboptimal result. To mitigate this gap, we propose a mixture of experts framework, MoE-NP, for node classification. Specifically, MoE-NP combines a mixture of node predictors and strategically selects models based on node patterns. Experimental results from a range of real-world datasets demonstrate significant performance improvements from MoE-NP.
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。