ProbWalk: A random walk approach in weighted graph embedding

Abstract

Abstract There are many weighted graphs in the real-world networks, such as social networks, communication networks, citation networks, etc. Along with successful application of deep learning in graph embedding, we study how to embed weight graph, because weights on the edges also play an important role in the graph. We propose a novel algorithm called ProbWalk, which take advantage of edge weights and convert the weights into transition probabilities. Our proposed method specifies the strategy of sampling the surrounding vertices by weights and generate the random walk for graph embedding according to transition probability. We evaluate our methods on tasks including multi-label classification and link prediction. Experimental results show that our method performs better than competed method on several weighted graph datasets.