Skip to content

BUPT-GAMMA/hyperbolic_hhne

main
Switch branches/tags

Name already in use

A tag already exists with the provided branch name. Many Git commands accept both tag and branch names, so creating this branch may cause unexpected behavior. Are you sure you want to create this branch?
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
 
 
 
 
 
 

HHNE

Source code for AAAI-2019 paper "Hyperbolic Heterogeneous Information Network Embedding"

The HHNE code is built upon Mikolov et al.'s word2vec.c from https://code.google.com/archive/p/word2vec/

Compile

  1. cmd "make" in folder HHNE/code/
  2. run "hhne" in folder HHNE/code/

Usage

./hhne [options]

The Options follow Mikolov et al.'s word2vec Options for training:

-train <file>
	Use text data from <file> to train the model
-output <file>
	Use <file> to save the resulting word vectors / word clusters
-size <int>
	Set size of word vectors; default is 100
-window <int>
	Set max skip length between words; default is 5
-sample <float>
	Set threshold for occurrence of words. Those that appear with higher frequency in the training data
	will be randomly down-sampled; default is 1e-3, useful range is (0, 1e-5)
-negative <int>
	Number of negative examples; default is 5, common values are 3 - 10 (0 = not used)
-threads <int>
	Use <int> threads (default 12)
-iter <int>
	Run more training iterations (default 5)
-min-count <int>
	This will discard words that appear less than <int> times; default is 5
-alpha <float>
	Set the starting learning rate; default is 0.025 for skip-gram
-debug <int>
	Set the debug mode (default = 2 = more info during training)
-save-vocab <file>
	The vocabulary will be saved to <file>
-read-vocab <file>
	The vocabulary will be read from <file>, not constructed from the training data

Examples:

./hhne -train random_walks.txt -output hhne.embeddings -size 2 -window 5 -negative 10 -threads 32 -iter 5 -alpha 0.025

Input:

The walks generated by meta-path guided random walks, each of which consists of different types of nodes.

Output:

The file for each node in text format (e.g., hhne.embeddings.txt)

HHNE bibtex information

@article{zhang2021embedding,
 title={Embedding Heterogeneous Information Network in Hyperbolic Spaces},
 author={Zhang, Yiding and Wang, Xiao and Liu, Nian and Shi, Chuan},
 journal={ACM Transactions on Knowledge Discovery from Data (TKDD)},
 volume={16},
 number={2},
 pages={1--23},
 year={2021},
 publisher={ACM New York, NY}
}

@inproceedings{HHNE:AAAI19,
 title={Hyperbolic Heterogeneous Information Network Embedding},
 author = {Wang, Xiao and Zhang, Yiding and Shi, Chuan},
 booktitle = {AAAI},
 year = {2019},
} 

About

About Source code for AAAI 2019 paper "Hyperbolic Heterogeneous Information Network Embedding"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published