Project report in the course DD2434 at KTH HT20
Instructions Paper:
Megha Khosla, Vinay Setty, and Avishek Anand. "A Comparative Study for Unsupervised Network Representation Learning." IEEE Transactions on Knowledge and Data Engineering (2019)
Tasks:
-
Implement the following methods discussed in the paper: DeepWalk, Node2vec, Line-1, NetMF, and GraphSage. Use of standard ML and DL languages is allowed.
-
Collect all the datasets presented in the paper. Search for a few additional datasets, if possible from different domains. Try to include new datasets that are at least as large as the ones in the original paper.
-
Evaluate the different methods on the data you collected with respect to the tasks of link prediction and node classification.
-
Discuss whether the results of the paper are reproducible in your experiments and whether they generalize to the new datasets you tested.
-
Discuss the original paper in terms of approach, methodology, and conclusions.
-
Summarize the most interesting things that you learned in this project.