Home Hot keywords

Search Modes

全部

搜索结果

作者:G Nikolentzos2017被引用次数:134 — These algorithms represent each graph as a set of vectors corresponding to the embeddings of its vertices. The similarity between two graphs is then determined ...
This paper presents a graph kernel based on the Pyramid Match kernel that finds an approximate correspondence between the sets of vectors of the two graphs ...
2017年2月28日 — These algorithms represent each graph as a set of vectors corresponding to the embeddings of its vertices. The similarity between two graphs is ...
作者:G Nikolentzos2017被引用次数:134 — Graph kernels have emerged as a powerful tool for graph comparison. Most existing graph kernels focus on local properties of graphs and ...

2017年2月4日 — These algorithms represent each graph as a set of vectors corresponding to the embeddings of its vertices. The similarity between two graphs ...
作者:H Xiu2020被引用次数:1 — Graph matching network. (GMN) [23] adopts an attention layer to match the nodes in two graphs in embedding learning and computes the GED using ...
作者:Y Bai2018被引用次数:102 — supplement the graph-level embeddings with fine-grained node- ... network embedding, neural networks, graph similarity computa-.
作者:G Ma2021被引用次数:11 — 2019a), and the deep graph matching networks proposed for binary function ... which apply graph embedding techniques to obtain node-level or ...
作者:F Béres2019被引用次数:14 — Online learning of second order node similarity. Our next online algorithm optimizes the embedding to match the neighborhood similarity of the ...
作者:Y Bai被引用次数:17 — To reflect the difference in graph sizes in the similarity matrix, we pad |N1 − N2| rows of zeros to the node embedding matrix of the smaller of the two graphs ...
14 页·1 MB

Page Navigation

google search trends