arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.09430cs.LGstat.ML
收藏

用于图学习的Wasserstein嵌入

Wasserstein Embedding for Graph Learning

HRL Laboratories, LLC.(HRL有限责任公司);University of Virginia(弗吉尼亚大学)

Soheil Kolouri, Navid Naderializadeh, Gustavo K. Rohde, Heiko Hoffmann

摘要:

我们提出了Wasserstein Embedding for Graph Learning(WEGL),这是一种用于将整个图嵌入到向量空间中的新型快速框架,其中各种机器学习模型适用于图级预测任务。我们利用新的见解定义图之间的相似性作为其节点嵌入分布之间的相似性的函数。具体来说,我们使用Wasserstein距离来衡量不同图的节点嵌入之间的差异。与以前的工作不同,我们避免了两两计算图之间的距离,并减少了计算复杂性从二次到线性的图的数量。WEGL计算从参考分布到每个节点嵌入的Monge映射,并基于这些映射创建图的固定大小的向量表示。我们在各种基准图属性预测任务上评估了我们的新图嵌入方法,显示了最先进的分类性能,同时具有卓越的计算效率。该代码可在https://github.com/navid-naderi/WEGL上获得。

英文摘要:

We present Wasserstein Embedding for Graph Learning (WEGL), a novel and fast framework for embedding entire graphs in a vector space, in which various machine learning models are applicable for graph-level prediction tasks. We leverage new insights on defining similarity between graphs as a function of the similarity between their node embedding distributions. Specifically, we use the Wasserstein distance to measure the dissimilarity between node embeddings of different graphs. Unlike prior work, we avoid pairwise calculation of distances between graphs and reduce the computational complexity from quadratic to linear in the number of graphs. WEGL calculates Monge maps from a reference distribution to each node embedding and, based on these maps, creates a fixed-sized vector representation of the graph. We evaluate our new graph embedding approach on various benchmark graph-property prediction tasks, showing state-of-the-art classification performance while having superior computational efficiency. The code is available at https://github.com/navid-naderi/WEGL.

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。

↑