Hierarchical Taxonomy Aware Network Embedding
Uploaded by: Ayan Kumar Bhowmick
Upload date: 2018-11-06 10:46:26
Edited at: 2018-11-07 10:30:05
Edited by: Maximimi


The idea of using a hierarchical clustering of nodes in order to guide network embedding is very nice! ### Related work: Hierarchical clustering for network embedding has also been used in the two following papers: - [HARP: Hierarchical Representation Learning for Networks](https://papers-gamma.link/paper/109) - [MILE: A Multi-Level Framework for Scalable Graph Embedding](https://papers-gamma.link/paper/104) ### Scalability: The largest graph used in the experiments has only 334k edges and the running time on that network is not reported. In figure 7, the method takes 2 minutes on a BA network of less than 10k nodes and 150k edges. It would have been nice to report the running time on a graph of 1G edges in order to evaluate the scalability in a better way. ### Reproducibility: The implementation does not seem to be publically available and as the proposed method is complicated, the results are hard to reproduce. ### Table 3: It is interesting that the dot-product approach leads to the best results for link prediction in comparison with the 4 strategies used in node2vec. Usualy, Hadamard leads to the best results.
Maximimi at 2018-11-07 10:29:14
Edited by Maximimi at 2018-11-07 10:42:33
Comments to a comment: 1. Code is available at https://github.com/JianxinMa/jianxinma.github.io/blob/master/assets/nethiex-linux.zip at the moment. It will probably be put on http://nrl.thumedialab.com/ later. Yeah the implementation is quite complicated. Still, a lot simpler than the variational inference for the nested chinese restaurant process (which I can't find any implementation). 2. Scalability shouldn't be a problem in theory (the time complexity is linear per iteration in theory). But the released code is not really optimized (not even multi-threaded or distributed). 3. It's possible for Hadamard to be worse than dot product, as it requires training a classifier and can over-fit if not tuned carefully or trained on a small sample.

You comment anonymously! You will not be able to edit/delete the comment.

Please consider to register or login.

Use $\LaTeX$ to type formulæ and markdown to format text.
When you post something to which you hold the copyright you authorise us to do distribute this data across the scientific community. You can post public domain content. All user-generated content will be freely available online. Please see this page to learn more about Papersγ's terms of use and privacy policy.