Timezone: »

PRUNE: Preserving Proximity and Global Ranking for Network Embedding
Yi-An Lai · Chin-Chi Hsu · Wen Hao Chen · Mi-Yen Yeh · Shou-De Lin

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #14

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.

Author Information

Yi-An Lai (National Taiwan University)
Chin-Chi Hsu (Academia Sinica)
Wen Hao Chen (National Taiwan University)
Mi-Yen Yeh (Academia Sinica)
Shou-De Lin (National Taiwan University)

More from the Same Authors