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 → thunlp → TADW

thunlp / TADW

Licence: MIT License
Network Representation Learning with Rich Text Information (IJCAI 2015)

Programming Languages

matlab
3953 projects
c
50402 projects - #5 most used programming language

Labels

network-embedding

Projects that are alternatives of or similar to TADW

CIKM18-LCVA
Code for CIKM'18 paper, Linked Causal Variational Autoencoder for Inferring Paired Spillover Effects.
Stars: ✭ 13 (-69.05%)
Mutual labels:  network-embedding
FSCNMF
An implementation of "Fusing Structure and Content via Non-negative Matrix Factorization for Embedding Information Networks".
Stars: ✭ 16 (-61.9%)
Mutual labels:  network-embedding
HEER
Easing Embedding Learning by Comprehensive Transcription of Heterogeneous Information Networks(KDD'18)
Stars: ✭ 60 (+42.86%)
Mutual labels:  network-embedding
RHINE
Source code for AAAI 2019 paper "Relation Structure-Aware Heterogeneous Information Network Embedding"
Stars: ✭ 49 (+16.67%)
Mutual labels:  network-embedding
Friends-Recommender-In-Social-Network
Friends Recommendation and Link Prediction in Social Netowork
Stars: ✭ 33 (-21.43%)
Mutual labels:  network-embedding
ethereum-privacy
Profiling and Deanonymizing Ethereum Users
Stars: ✭ 37 (-11.9%)
Mutual labels:  network-embedding
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 (-19.05%)
Mutual labels:  network-embedding
TriDNR
Tri-Party Deep Network Representation, IJCAI-16
Stars: ✭ 72 (+71.43%)
Mutual labels:  network-embedding
resolutions-2019
A list of data mining and machine learning papers that I implemented in 2019.
Stars: ✭ 19 (-54.76%)
Mutual labels:  network-embedding
REGAL
Representation learning-based graph alignment based on implicit matrix factorization and structural embeddings
Stars: ✭ 78 (+85.71%)
Mutual labels:  network-embedding
TransNet
Source code and datasets of IJCAI2017 paper "TransNet: Translation-Based Network Representation Learning for Social Relation Extraction".
Stars: ✭ 103 (+145.24%)
Mutual labels:  network-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 (-7.14%)
Mutual labels:  network-embedding
MixGCF
MixGCF: An Improved Training Method for Graph Neural Network-based Recommender Systems, KDD2021
Stars: ✭ 73 (+73.81%)
Mutual labels:  network-embedding
GNE
This repository contains the tensorflow implementation of "GNE: A deep learning framework for gene network inference by aggregating biological information"
Stars: ✭ 27 (-35.71%)
Mutual labels:  network-embedding
Euler
A distributed graph deep learning framework.
Stars: ✭ 2,701 (+6330.95%)
Mutual labels:  network-embedding
Nrlpapers
Must-read papers on network representation learning (NRL) / network embedding (NE)
Stars: ✭ 2,503 (+5859.52%)
Mutual labels:  network-embedding
Awesome Network Embedding
A curated list of network embedding techniques.
Stars: ✭ 2,379 (+5564.29%)
Mutual labels:  network-embedding
Openne
An Open-Source Package for Network Embedding (NE)
Stars: ✭ 1,527 (+3535.71%)
Mutual labels:  network-embedding
Awesome Graph Classification
A collection of important graph embedding, classification and representation learning papers with implementations.
Stars: ✭ 4,309 (+10159.52%)
Mutual labels:  network-embedding
NetEmb-Datasets
A collection of real-world networks/graphs for Network Embedding
Stars: ✭ 18 (-57.14%)
Mutual labels:  network-embedding

TADW

This is the lab code for paper "Network Representation Learning with Rich Text Information". (To be appeared at IJCAI2015)

The code requires a 64-bit linux machine with MATLAB installed.

The main program is TADW.m. More details about parameters can be found in the comments.

Dataset Description

Cora contains 2, 708 machine learning papers from seven classes and 5, 429 links between them. The links are citation relationships between the documents. Each document is described by a binary vector of 1, 433 dimensions indicating the presence of the corresponding word.

Citeseer contains 3, 312 publications from six classes and 4, 732 links between them. Similar to Cora, the links are citation relationships between the documents and each paper is described by a binary vector of 3, 703 dimensions.

Wiki contains 2, 405 documents from 19 classes and 17, 981 links between them. The TFIDF matrix of this dataset has 4, 973 columns.

graph.txt: Each line contains two paper Ids which indicates the citation relationship between them. ID begins from 0.

group.txt: Each line contains two numbers: Paper Id and Group Id. For Cora and Citeseer, group Id begins from 0; For Wiki, group Id begins from 1.

feature.txt for Cora and Citeseer: This is the Paper-Word relationship matrix. Each line contains a binary vector of 1, 433 dimensions indicating the presence of the corresponding word.

tfidf.txt for Wiki: This is the TFIDF matrix of Wiki dataset. 4, 973 columns correspond to 4, 973 different words.

#About the mex file The source code of train.mexa64 comes from LibLinear which can be found at http://www.csie.ntu.edu.tw/~cjlin/liblinear/. train_ml.mexa64 comes from the work "Inductive matrix completion for predicting gene-disease associations" which can be found at http://bigdata.ices.utexas.edu/project/gene-disease/. The authors provide only mex file on the site and I don't have the source code either.

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].