Source code for EvalNE, a Python library for evaluating Network Embedding methods.
Release date: 20 Apr 2020
Main improvements since v0.2.2 release:
all_baselines
has been added. Generates a 5-dim edge embedding by combining the existing heuristics [CN, JC, AA, PA, RAI].A complete Release Log is available on the EvalNE Read The Docs page here.
Release date: 14 Mar 2019
WRITE_WEIGHTS_OTHER
in conf files which allows the user to specify if the input train network to the NE methods should have weights or not. If True but the original input network is unweighted, weights of 1 are given to each edge. This feature is useful for e.g. the original code of LINE which requires edges to have weights (all 1 if the graph is unweighted).WRITE_DIR_OTHER
in conf files which allows the user to specify if the input train network to the NE methods should be specified with both directions of edges or a single one.SEED
in the conf file which sets a general random seed for the experiment. If None the system time is used.simple-example.py
now checks if OpenNE is installed, if not it runs only the LP heuristics.setup.py
update. Ready for making EvalNE pip installable.Release date: 4 Feb 2019
This second version of EvalNE contains major improves and allows for the evaluation of node embeddings, edge embeddings and end to end prediction methods directly from the configuration file. The detailed changes are presented below:
Initial release of EvalNE.