Skip to yearly menu bar Skip to main content


Poster

PRUNE: Preserving Proximity and Global Ranking for Network Embedding

Yi-An Lai · Chin-Chi Hsu · Wen Hao Chen · Mi-Yen Yeh · Shou-De Lin

Pacific Ballroom #14

Keywords: [ Representation Learning ] [ Embedding Approaches ]


Abstract:

We investigate an unsupervised generative approach for network embedding. A multi-task Siamese neural network structure is formulated to connect embedding vectors and our objective to preserve the global node ranking and local proximity of nodes. We provide deeper analysis to connect the proposed proximity objective to link prediction and community detection in the network. We show our model can satisfy the following design properties: scalability, asymmetry, unity and simplicity. Experiment results not only verify the above design properties but also demonstrate the superior performance in learning-to-rank, classification, regression, and link prediction tasks.

Live content is unavailable. Log in and register to view live content