node2vec is a framework for learning graph embeddings for nodes in graphs. Node2vec maximizes a likelihood objective over mappings which preserve neighbourhood distances in higher dimensional spaces. From an algorithm design perspective, node2vec exploits the freedom to define neighbourhoods for nodes and provide an explanation for the effect of the choice of neighborhood on the learned representations. For each node, node2vec simulates biased random walks based on an efficient network-aware search strategy and the nodes appearing in the random walk define neighbourhoods. The search strategy accounts for the relative influence nodes exert in a network. It also generalizes prior work alluding to naive search strategies by providing flexibility in exploring neighborhoods.
相关学科: DeepWalkNetwork EmbeddingGraph EmbeddingGraphSAGELink PredictionNode ClassificationGraph Representation LearningStruc2vecRepresentation LearningGraph Sampling









Hongfang Liu

139850 被引用,2666 篇论文

Kevin Murphy

83646 被引用,800 篇论文

Jure Leskovec

68322 被引用,500 篇论文

Christos Faloutsos

63796 被引用,819 篇论文

Dawn Song

47685 被引用,470 篇论文

Nitesh V. Chawla

32376 被引用,407 篇论文

Tat-Seng Chua

30731 被引用,750 篇论文

Michael Backes

21671 被引用,909 篇论文

Yong Yu

21402 被引用,545 篇论文

Peter N. Robinson

21212 被引用,416 篇论文