Ensemble Node Embeddings using Tensor Decomposition: A Case-Study on DeepWalk

Jia Chen, Evangelos E. Papalexakis
2020 2020 International Conference on Data Mining Workshops (ICDMW)  
Node embeddings have been attracting increasing attention during the past years. In this context, we propose a new ensemble node embedding approach, called TENSEMBLE2VEC, by first generating multiple embeddings using the existing techniques and taking them as multiview data input of the state-of-art tensor decomposition model namely PARAFAC2 to learn the shared lower-dimensional representations of the nodes. Contrary to other embedding methods, our TENSEMBLE2VEC takes advantage of the
more » ... ary information from different methods or the same method with different hyper-parameters, which bypasses the challenge of choosing models. Extensive tests using real-world data validates the efficiency of the proposed method.
doi:10.1109/icdmw51313.2020.00080 fatcat:zkxi54u26raapc5ydnxws6ibfi