Learning Low-Dimensional Embeddings for Nodes in Graph-Structured Data

Home

Discover

Bookmarks

Keep Up With Top Trending Papers In CS / AI / ML ...

Source arXiv

Machine Learning

Computation and Language

Stats Machine Learning

Learning Low-Dimensional Embeddings for Nodes in Graph-Structured Data

A Capsule Network-based Model for Learning Node Embeddings

We propose caps2ne, a new unsupervised embedding model leveraging a network of two capsule layers.

Caps2ne induces a routing process to aggregate feature vectors of contextneighbors of a given target node at the first capsule layer, then feed these features into the second capsule layer to infer a plausible embedding for the target node.

Experimental results show that our proposed caps2ne obtains state-of-the-art performances on benchmark datasets for the node classification task.

Authors

Dai Quoc Nguyen, Tu Dinh Nguyen, Dat Quoc Nguyen, Dinh Phung

◐ Recommended Members

◐ Latest Activity