GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → RoyZhengGao → edge2vec

RoyZhengGao / edge2vec

Licence: BSD-3-Clause license
Learning node representation using edge semantics

Programming Languages

python
139335 projects - #7 most used programming language

Labels

embedding-modelsgraph-embedding

Projects that are alternatives of or similar to edge2vec

TriDNR
Tri-Party Deep Network Representation, IJCAI-16
Stars: ✭ 72 (+60%)
Mutual labels:  graph-embedding
Awesome Graph Classification
A collection of important graph embedding, classification and representation learning papers with implementations.
Stars: ✭ 4,309 (+9475.56%)
Mutual labels:  graph-embedding
Awesome Embedding Models
A curated list of awesome embedding models tutorials, projects and communities.
Stars: ✭ 1,486 (+3202.22%)
Mutual labels:  embedding-models
walklets
A lightweight implementation of Walklets from "Don't Walk Skip! Online Learning of Multi-scale Network Embeddings" (ASONAM 2017).
Stars: ✭ 94 (+108.89%)
Mutual labels:  graph-embedding
AutoSF
Y. Zhang, Q. Yao, J. Kwok. Bilinear Scoring Function Search for Knowledge Graph Learning. TPAMI 2022
Stars: ✭ 51 (+13.33%)
Mutual labels:  graph-embedding
Alink
Alink is the Machine Learning algorithm platform based on Flink, developed by the PAI team of Alibaba computing platform.
Stars: ✭ 2,936 (+6424.44%)
Mutual labels:  graph-embedding
OpenANE
OpenANE: the first Open source framework specialized in Attributed Network Embedding. The related paper was accepted by Neurocomputing. https://doi.org/10.1016/j.neucom.2020.05.080
Stars: ✭ 39 (-13.33%)
Mutual labels:  graph-embedding
multi-label-text-classification
Mutli-label text classification using ConvNet and graph embedding (Tensorflow implementation)
Stars: ✭ 44 (-2.22%)
Mutual labels:  graph-embedding
GOSH
An ultra-fast, GPU-based large graph embedding algorithm utilizing a novel coarsening algorithm requiring not more than a single GPU.
Stars: ✭ 12 (-73.33%)
Mutual labels:  graph-embedding
ncc
Neural Code Comprehension: A Learnable Representation of Code Semantics
Stars: ✭ 162 (+260%)
Mutual labels:  embedding-models
RolX
An alternative implementation of Recursive Feature and Role Extraction (KDD11 & KDD12)
Stars: ✭ 52 (+15.56%)
Mutual labels:  graph-embedding
FSCNMF
An implementation of "Fusing Structure and Content via Non-negative Matrix Factorization for Embedding Information Networks".
Stars: ✭ 16 (-64.44%)
Mutual labels:  graph-embedding
VCML
PyTorch implementation of paper "Visual Concept-Metaconcept Learner", NeruIPS 2019
Stars: ✭ 45 (+0%)
Mutual labels:  embedding-models
FEATHER
The reference implementation of FEATHER from the CIKM '20 paper "Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models".
Stars: ✭ 34 (-24.44%)
Mutual labels:  graph-embedding
Awesome Sentence Embedding
A curated list of pretrained sentence and word embedding models
Stars: ✭ 1,973 (+4284.44%)
Mutual labels:  embedding-models
resolutions-2019
A list of data mining and machine learning papers that I implemented in 2019.
Stars: ✭ 19 (-57.78%)
Mutual labels:  graph-embedding
Euler
A distributed graph deep learning framework.
Stars: ✭ 2,701 (+5902.22%)
Mutual labels:  graph-embedding
dgcnn
Clean & Documented TF2 implementation of "An end-to-end deep learning architecture for graph classification" (M. Zhang et al., 2018).
Stars: ✭ 21 (-53.33%)
Mutual labels:  graph-embedding
GE-FSG
Graph Embedding via Frequent Subgraphs
Stars: ✭ 39 (-13.33%)
Mutual labels:  graph-embedding
STransE
STransE: a novel embedding model of entities and relationships in knowledge bases (NAACL 2016)
Stars: ✭ 50 (+11.11%)
Mutual labels:  embedding-models
View All Similar Projects ➔

edge2evc

The open source code for our paper "edge2vec: Learning Node Representation Using Edge Semantics".

How to use the code

Dataset

The dataset we offer for test is data.csv. The data contains four columns, which refer to Source ID, Target ID, Edge Type, Edge ID. And columns are seperated by space ' '.

For unweighted graph, please see unweighted_graph.txt. The four columns are Source ID, Target ID, Edge Type, Edge ID. And columns are seperated by space ' '. For weighted graph, please see weighted_graph.txt. The five columns are Source ID, Target ID, Edge Type, Edge Weight, Edge ID. And columns are seperated by space ' '.

Run the code

There are two steps for running the code. First, to calculate transition matrix in heterogeneous networks. run transition.py from bash:

$ transition.py --input data.csv --output matrix.txt --type_size 3 --em_iteration 5 --e_step 3 --walk-length 3 --num-walks 2

The output is matrix.txt which stores edge transition matrix. Second, run edge2vec.py to the node embeddings via biased random walk. To use it from bash:

$ edge2vec.py --input data.csv --matrix matrix.txt --output vector.txt --dimensions 128 --walk-length 3 --num-walks 2 --p 1 --q 1

The output is the node embedding file vector.txt. Data repository for medical dataset in the link: http://ella.ils.indiana.edu/~gao27/data_repo/edge2vec%20vector.zip or https://figshare.com/articles/edge2vec_vector_zip/8097539 (It is a re-computed version so the evaluation output may be a little bit different with the paper reported results.)

Citations

if you use the code, please cite:

  • Gao, Zheng, Gang Fu, Chunping Ouyang, Satoshi Tsutsui, Xiaozhong Liu, Jeremy Yang, Christopher Gessner et al. "edge2vec: Representation learning using edge semantics for biomedical knowledge discovery." BMC bioinformatics 20, no. 1 (2019): 306.

License

The code is released under BSD 3-Clause License.

Contributor

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].