BiNE: Bipartite Network Embedding

Related tags

Text Data & NLPBiNE
Overview

BiNE: Bipartite Network Embedding

This repository contains the demo code of the paper:

BiNE: Bipartite Network Embedding. Ming Gao, Leihui Chen, Xiangnan He & Aoying Zhou

which has been accepted by SIGIR2018.

Note: Any problems, you can contact me at [email protected]. Through email, you will get my rapid response.

Environment settings

  • python==2.7.11
  • numpy==1.13.3
  • sklearn==0.17.1
  • networkx==1.11
  • datasketch==1.2.5
  • scipy==0.17.0
  • six==1.10.0

Basic Usage

Main Parameters:

Input graph path. Defult is '../data/rating_train.dat' (--train-data)
Test dataset path. Default is '../data/rating_test.dat' (--test-data)
Name of model. Default is 'default' (--model-name)
Number of dimensions. Default is 128 (--d)
Number of negative samples. Default is 4 (--ns)
Size of window. Default is 5 (--ws)
Trade-off parameter $\alpha$. Default is 0.01 (--alpha)
Trade-off parameter $\beta$. Default is 0.01 (--beta)
Trade-off parameter $\gamma$. Default is 0.1 (--gamma)
Learning rate $\lambda$. Default is 0.01 (--lam)
Maximal iterations. Default is 50 (--max-iters)
Maximal walks per vertex. Default is 32 (--maxT)
Minimal walks per vertex. Default is 1 (--minT)
Walk stopping probability. Default is 0.15 (--p)
Calculate the recommendation metrics. Default is 0 (--rec)
Calculate the link prediction. Default is 0 (--lip)
File of training data for LR. Default is '../data/wiki/case_train.dat' (--case-train)
File of testing data for LR. Default is '../data/wiki/case_test.dat' (--case-test)
File of embedding vectors of U. Default is '../data/vectors_u.dat' (--vectors-u)
File of embedding vectors of V. Default is '../data/vectors_v.dat' (--vectors-v)
For large bipartite, 1 do not generate homogeneous graph file; 2 do not generate homogeneous graph. Default is 0 (--large)
Mertics of centrality. Default is 'hits', options: 'hits' and 'degree_centrality' (--mode)

Usage

We provide two processed dataset:

  • DBLP (for recommendation). It contains:

    • A training dataset ./data/dblp/rating_train.dat
    • A testing dataset ./data/dblp/rating_test.dat

  • Wikipedia (for link prediction). It contains:

    • A training dataset ./data/wiki/rating_train.dat
    • A testing dataset ./data/wiki/rating_test.dat

  • Each line is a instance: userID (begin with 'u')\titemID (begin with 'i') \t weight\n

    For example: u0\ti0\t1

Please run the './model/train.py'

cd model
python train.py --train-data ../data/dblp/rating_train.dat --test-data ../data/dblp/rating_test.dat --lam 0.025 --max-iter 100 --model-name dblp --rec 1 --large 2 --vectors-u ../data/dblp/vectors_u.dat --vectors-v ../data/dblp/vectors_v.dat

The embedding vectors of nodes are saved in file '/model-name/vectors_u.dat' and '/model-name/vectors_v.dat', respectively.

Example

Recommendation

Run

cd model
python train.py --train-data ../data/dblp/rating_train.dat --test-data ../data/dblp/rating_test.dat --lam 0.025 --max-iter 100 --model-name dblp --rec 1 --large 2 --vectors-u ../data/dblp/vectors_u.dat --vectors-v ../data/dblp/vectors_v.dat

Output (training process)

======== experiment settings =========
alpha : 0.0100, beta : 0.0100, gamma : 0.1000, lam : 0.0250, p : 0.1500, ws : 5, ns : 4, maxT :  32, minT : 1, max_iter : 100
========== processing data ===========
constructing graph....
number of nodes: 6001
walking...
walking...ok
number of nodes: 1177
walking...
walking...ok
getting context and negative samples....
negative samples is ok.....
context...
context...ok
context...
context...ok
============== training ==============
[*************************************************************************************************** ]100.00%

Output (testing process)

============== testing ===============
recommendation metrics: F1 : 0.1132, MAP : 0.2041, MRR : 0.3331, NDCG : 0.2609

Link Prediction

Run

cd model
python train.py --train-data ../data/wiki/rating_train.dat --test-data ../data/wiki/rating_test.dat --lam 0.01 --max-iter 100 --model-name wiki --lip 1 --large 2 --gamma 1 --vectors-u ../data/wiki/vectors_u.dat --vectors-v ../data/wiki/vectors_v.dat --case-train ../data/wiki/case_train.dat --case-test ../data/wiki/case_test.dat

Output (training process)

======== experiment settings =========
alpha : 0.0100, beta : 0.0100, gamma : 1.0000, lam : 0.0100, p : 0.1500, ws : 5, ns : 4, maxT :  32, minT : 1, max_iter : 100, d : 128
========== processing data ===========
constructing graph....
number of nodes: 15000
walking...
walking...ok
number of nodes: 2529
walking...
walking...ok
getting context and negative samples....
negative samples is ok.....
context...
context...ok
context...
context...ok
============== training ==============
[*************************************************************************************************** ]100.00%

Output (testing process)

============== testing ===============
link prediction metrics: AUC_ROC : 0.9468, AUC_PR : 0.9614
Owner
leihuichen
student
leihuichen
GitHub Repository
CCF BDCI BERT系统调优赛题baseline（Pytorch版本）

CCF BDCI BERT系统调优赛题baseline（Pytorch版本） 此版本基于Pytorch后端的huggingface进行实现。由于此实现使用了Oneflow的dataloader作为数据读入的方式，因此也需要安装Oneflow。其它框架的数据读取可以参考OneflowDataloade

Ziqi Zhou 9 Oct 13, 2022
To create a deep learning model which can explain the content of an image in the form of speech through caption generation with attention mechanism on Flickr8K dataset.

To create a deep learning model which can explain the content of an image in the form of speech through caption generation with attention mechanism on Flickr8K dataset.

Ragesh Hajela 0 Feb 08, 2022
Study German declensions (dER nettE Mann, ein nettER Mann, mit dEM nettEN Mann, ohne dEN nettEN Mann ...) Generate as many exercises as you want using the incredible power of SPACY!

Study German declensions (dER nettE Mann, ein nettER Mann, mit dEM nettEN Mann, ohne dEN nettEN Mann ...) Generate as many exercises as you want using the incredible power of SPACY!

Hans Alemão 4 Jul 20, 2022
A method for cleaning and classifying text using transformers.

NLP Translation and Classification The repository contains a method for classifying and cleaning text using NLP transformers. Overview The input data

Ray Chamidullin 0 Nov 15, 2022
A PyTorch implementation of the Transformer model in "Attention is All You Need".

Attention is all you need: A Pytorch Implementation This is a PyTorch implementation of the Transformer model in "Attention is All You Need" (Ashish V

Yu-Hsiang Huang 7.1k Jan 05, 2023
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.

Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization, language mod

20.5k Jan 08, 2023
A cross platform OCR Library based on PaddleOCR & OnnxRuntime

A cross platform OCR Library based on PaddleOCR & OnnxRuntime

RapidOCR Team 767 Jan 09, 2023
Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

Kashgari Overview | Performance | Installation | Documentation | Contributing 🎉 🎉 🎉 We released the 2.0.0 version with TF2 Support. 🎉 🎉 🎉 If you

Eliyar Eziz 2.3k Dec 29, 2022
Word2Wave: a framework for generating short audio samples from a text prompt using WaveGAN and COALA.

Word2Wave is a simple method for text-controlled GAN audio generation. You can either follow the setup instructions below and use the source code and CLI provided in this repo or you can have a play

Ilaria Manco 91 Dec 23, 2022
Pre-training with Extracted Gap-sentences for Abstractive SUmmarization Sequence-to-sequence models

PEGASUS library Pre-training with Extracted Gap-sentences for Abstractive SUmmarization Sequence-to-sequence models, or PEGASUS, uses self-supervised

Google Research 1.4k Dec 22, 2022
Galois is an auto code completer for code editors (or any text editor) based on OpenAI GPT-2.

Galois is an auto code completer for code editors (or any text editor) based on OpenAI GPT-2. It is trained (finetuned) on a curated list of approximately 45K Python (~470MB) files gathered from the

Galois Autocompleter 91 Sep 23, 2022
Voilà turns Jupyter notebooks into standalone web applications

Rendering of live Jupyter notebooks with interactive widgets. Introduction Voilà turns Jupyter notebooks into standalone web applications. Unlike the

Voilà Dashboards 4.5k Jan 03, 2023
Generate text line images for training deep learning OCR model (e.g. CRNN)

Generate text line images for training deep learning OCR model (e.g. CRNN)

532 Jan 06, 2023
Topic Modelling for Humans

gensim – Topic Modelling in Python Gensim is a Python library for topic modelling, document indexing and similarity retrieval with large corpora. Targ

RARE Technologies 13.8k Jan 02, 2023
Python bot created with Selenium that can guess the daily Wordle word correct 96.8% of the time.

Wordle_Bot Python bot created with Selenium that can guess the daily Wordle word correct 96.8% of the time. It will log onto the wordle website and en

Lucas Polidori 15 Dec 11, 2022
Fastseq 基于ONNXRUNTIME的文本生成加速框架

Fastseq 基于ONNXRUNTIME的文本生成加速框架

Jun Gao 9 Nov 09, 2021
A Semi-Intelligent ChatBot filled with statistical and economical data for the Premier League.

MONEYBALL - ChatBot Module: 4006CEM, Class: B, Group: 5 Contributors: Jonas Djondo Roshan Kc Cole Samson Daniel Rodrigues Ihteshaam Naseer Kind remind

Jonas Djondo 1 Nov 18, 2021
Package for controllable summarization

summarizers summarizers is package for controllable summarization based CTRLsum. currently, we only supports English. It doesn't work in other languag

Hyunwoong Ko 72 Dec 07, 2022
Natural Language Processing

NLP Natural Language Processing apps Multilingual_NLP.py start #This script is demonstartion of Mul

Ritesh Sharma 1 Oct 31, 2021
This repository contains the code for "Generating Datasets with Pretrained Language Models".

Datasets from Instructions (DINO 🦕 ) This repository contains the code for Generating Datasets with Pretrained Language Models. The paper introduces

Timo Schick 154 Jan 01, 2023