arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1905.04682cs.LGstat.ML
收藏

关于图分类网络、数据集和基线

On Graph Classification Networks, Datasets and Baselines

University of Cambridge(剑桥大学)

Enxhell Luzhnica, Ben Day, Pietro Liò

摘要:

图分类受到了非欧几里得机器学习社区的极大关注。图粗化的最新进展使更深层网络的训练成为可能,并在许多基准任务中产生了新的最先进的结果。我们研究这些架构如何训练,并发现性能是高度敏感的初始化,并强烈依赖于跳跃知识结构。然后,我们表明,尽管这些模型非常复杂,但最简单的模型-结构盲MLP,单层GCN和固定重量GCN -可以实现具有竞争力的性能,并建议将这些模型作为未来的基线。

英文摘要:

Graph classification receives a great deal of attention from the non-Euclidean machine learning community. Recent advances in graph coarsening have enabled the training of deeper networks and produced new state-of-the-art results in many benchmark tasks. We examine how these architectures train and find that performance is highly-sensitive to initialisation and depends strongly on jumping-knowledge structures. We then show that, despite the great complexity of these models, competitive performance is achieved by the simplest of models -- structure-blind MLP, single-layer GCN and fixed-weight GCN -- and propose these be included as baselines in future.

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。

↑