论文标题
开放图基准上的图形属性预测：图形神经体系结构搜索的获胜解决方案
Graph Property Prediction on Open Graph Benchmark: A Winning Solution by Graph Neural Architecture Search
论文作者
论文摘要
针对OGB图分类任务中的两个分子图数据集和一个蛋白质关联子图数据集，我们通过引入PAS（池架构搜索）设计了一个图形神经网络框架，以用于图形分类任务。同时，我们根据GNN拓扑设计方法F2GNN改进它，以进一步设计功能选择和融合策略，以便进一步提高模型在Graph Propertion Prediction Task中的性能，同时克服深度GNN训练的过度平滑问题。最后，在这三个数据集上实现了性能突破，这比具有固定聚合功能的其他方法要好得多。事实证明，NAS方法具有多个任务的高概括能力以及我们在处理图形属性预测任务方面的优势。
Aiming at two molecular graph datasets and one protein association subgraph dataset in OGB graph classification task, we design a graph neural network framework for graph classification task by introducing PAS(Pooling Architecture Search). At the same time, we improve it based on the GNN topology design method F2GNN to further design the feature selection and fusion strategies, so as to further improve the performance of the model in the graph property prediction task while overcoming the over smoothing problem of deep GNN training. Finally, a performance breakthrough is achieved on these three datasets, which is significantly better than other methods with fixed aggregate function. It is proved that the NAS method has high generalization ability for multiple tasks and the advantage of our method in processing graph property prediction tasks.
