Skip to content

Latest commit

 

History

History
26 lines (18 loc) · 1.27 KB

File metadata and controls

26 lines (18 loc) · 1.27 KB

Dynamic-Social-Network-Alignment-based-on-Heuristic-Algorithm

Codes for Dynamic Social Network Alignment based on Heuristic Algorithm. With the permission of sharing anonymous twitter_foursquare data from Prof.Jiawei Zhang, we share the anonymous data and code of IONE here. Note that the data and code only can be used for research purposes.

AcrossNetworkEmbeddingData

foursquare: following.number: the relation file, "1 2" means user 1 is the follower of user 2. embeddings directory for storing the embedding generated by ABNE model.

twitter: the same as the foursquare fold

twitter_foursquare_groundtruth:

groundtruth.x.foldtrain.train.number, the traning anchors, which are the 0.x of all the anchors.

groundtruth.x.foldtrain.test.number, the testing anchors, which are the 1-0.x of all the anchors.

Note that users only appear in the "groundtruth.number" file are the training anchors (even there are some uses have same ids, they are not anchors)

Model Running

First run the IONE.java to get the initial embeddings for two networks,then run Attention.java and supervisedAnchorLearning.java to get two wieghts for each nodes. Finally,run HDyNA.java to get the final embeddings.

Feel free to contact me (254579678@qq.com) when you have any problems about the paper or the code.