HyperAggregation：通过超网络在图边上进行聚合
HyperAggregation: Aggregating over Graph Edges with Hypernetworks
AI总结：
本文提出基于超网络的图聚合函数HyperAggregation，动态生成邻域权重，在多种任务和数据集上验证了其有效性，并在异质性数据集上达到新最优。
摘要：
HyperAggregation是一种基于超网络的图神经网络聚合函数。它利用一个超网络动态生成与当前邻域大小相匹配的权重，然后用这些权重对该邻域进行聚合。这种使用生成权重的聚合方式类似于MLP-Mixer在可变大小的顶点邻域上进行的通道混合。我们在两个模型中展示了HyperAggregation：GraphHyperMixer是一个基于MLP-Mixer的模型，而GraphHyperConv则源自GCN，但采用了基于超网络的聚合函数。我们在顶点分类、图分类和图回归任务上对多种基准数据集进行了实验。结果表明，HyperAggregation可以有效地用于同质性和异质性数据集，在归纳式和转导式设置中均表现良好。GraphHyperConv的性能优于GraphHyperMixer，尤其在转导式设置中表现突出。在异质性数据集Roman-Empire上，它达到了新的最先进水平。在图级任务中，我们的模型与规模相近的模型表现相当。消融研究探讨了模型对各种超参数选择的鲁棒性。HyperAggregation的实现以及复现所有实验的代码可在https://github.com/Foisunt/HyperAggregation 获取。
英文摘要：
HyperAggregation is a hypernetwork-based aggregation function for Graph Neural Networks. It uses a hypernetwork to dynamically generate weights in the size of the current neighborhood, which are then used to aggregate this neighborhood. This aggregation with the generated weights is done like an MLP-Mixer channel mixing over variable-sized vertex neighborhoods. We demonstrate HyperAggregation in two models, GraphHyperMixer is a model based on MLP-Mixer while GraphHyperConv is derived from a GCN but with a hypernetwork-based aggregation function. We perform experiments on diverse benchmark datasets for the vertex classification, graph classification, and graph regression tasks. The results show that HyperAggregation can be effectively used for homophilic and heterophilic datasets in both inductive and transductive settings. GraphHyperConv performs better than GraphHyperMixer and is especially strong in the transductive setting. On the heterophilic dataset Roman-Empire it reaches a new state of the art. On the graph-level tasks our models perform in line with similarly sized models. Ablation studies investigate the robustness against various hyperparameter choices. The implementation of HyperAggregation as well code to reproduce all experiments is available under https://github.com/Foisunt/HyperAggregation .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
