提出无监督方法AMLP，让MLP自适应图消息聚合，提升异质图性能。
Aggregation-aware MLP: An Unsupervised Approach for Graph Message-passing
- 用图重建实现高阶聚类，让MLP感知不同异质程度
- 在节点分类与聚类任务上优于传统聚合方式
- 无需标签数据，适合真实场景中标签稀缺的图学习
图神经网络（GNN）凭借消息传递机制成为图表示学习的主流方法，但其通常采用固定聚合函数（如均值、最大值或求和），缺乏选择依据。这种僵化设计在异质性图中表现不佳，且现有改进方法多依赖标注数据，而真实任务中标签常稀缺。本文提出无监督新框架「聚合感知多层感知机」（AMLP），将设计聚合函数的思路转向使MLP自适应于聚合过程。该方法包含两个关键步骤：首先通过图重建实现高阶分组效应；其次使用单层网络编码不同异质程度，增强模型表达能力与适用性。在节点聚类与分类任务上的大量实验表明，AMLP表现优异，展现出在多样图学习场景中的潜力。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have become a dominant approach to learning graph representations, primarily because of their message-passing mechanisms. However, GNNs typically adopt a fixed aggregator function such as Mean, Max, or Sum without principled reasoning behind the selection. This rigidity, especially in the presence of heterophily, often leads to poor, problem dependent performance. Although some attempts address this by designing more sophisticated aggregation functions, these methods tend to rely heavily on labeled data, which is often scarce in real-world tasks. In this work, we propose a novel unsupervised framework, "Aggregation-aware Multilayer Perceptron" (AMLP), which shifts the paradigm from directly crafting aggregation functions to making MLP adaptive to aggregation. Our lightweight approach consists of two key steps: First, we utilize a graph reconstruction method that facilitates high-order grouping effects, and second, we employ a single-layer network to encode varying degrees of heterophily, thereby improving the capacity and applicability of the model. Extensive experiments on node clustering and classification demonstrate the superior performance of AMLP, highlighting its potential for diverse graph learning scenarios.
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。