Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors

Last update: Nov 27, 2022

Related tags

Overview

PSML

paper: Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors

PSML_IONE,PSML_ABNE,PSML_DEEPLINK,PSML_SNNA:

numpy==1.14<br>
networkx==2.0<br>
scipy==0.19.1<br>
tensorflow>=1.12.1<br>
gensim==3.0.1<br>
scikit-learn==0.19.0<br>

PSML_DALUAP,PSML_MGCN:

python >= 3.6<br>
pytorch >= 0.4<br>
numpy  1.18.0<br>
tqdm<br>
networkx >2.0<br>

support data comes from :https://github.com/ChuXiaokai/CrossMNA
query data comes from :https://github.com/ColaLL/IONE
, https://github.com/ColaLL/AcrossNetworkEmbeddingDiversity

For PSML_IONE

   first run PSML_IONE.py
   second run Four.py
   getPrecision--should run emd_to_ione_emd.py and emd_to_ione_emd_t.py

For PSML_ABNE

   first run PSML_ABNE.py
   second run Four.py
   getPrecision--should run emd_to_ione_emd.py and emd_to_ione_emd_t.py

For PSML_SNNA

   use deepwalk or line get pre_data
   run PSML_SNNA.py

For PSML_DeepLink

   run embedding.py to use word2vec get pre_data
   run PSML_Deeplink.py

For PSML_MGCN

   run PSML_MGCN.py

For PSML_DALUAP

   run PSML_DALUAP.py

NOTE:

Method of adding pseudo node, Take two pseudo anchors, which are connected to each other, such as subnetwork file:

        node      node
         1          2
         3(anchor)  4

You need change it to:

        node      node
         1          2
         3(anchor)  4
         3          5(pse)
         3          6(pse)
         5(pse)     3
         6(pse)     3
         5(pse)     6(pse)
         6(pse)     5(pse)

Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors

Related tags

Overview

PSML

paper: Towards Improving Embedding Based Models of Social Network Alignment via Pseudo Anchors

For PSML_IONE

For PSML_ABNE

For PSML_SNNA

For PSML_DeepLink

For PSML_MGCN

For PSML_DALUAP

NOTE:

Owner

PyBrain - Another Python Machine Learning Library.

This a classic fintech problem that introduces real life difficulties such as data imbalance. Check out the notebook to find out more!

Simple and Robust Loss Design for Multi-Label Learning with Missing Labels

Complete system for facial identity system. Include one-shot model, database operation, features visualization, monitoring

A minimal solution to hand motion capture from a single color camera at over 100fps. Easy to use, plug to run.

Code for "Discovering Non-monotonic Autoregressive Orderings with Variational Inference" (paper and code updated from ICLR 2021)

MEDS: Enhancing Memory Error Detection for Large-Scale Applications

The hippynn python package - a modular library for atomistic machine learning with pytorch.

Identifying a Training-Set Attack’s Target Using Renormalized Influence Estimation

FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation.

π-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis

Codes to calculate solar-sensor zenith and azimuth angles directly from hyperspectral images collected by UAV. Works only for UAVs that have high resolution GNSS/IMU unit.

The AWS Certified SysOps Administrator

An educational tool to introduce AI planning concepts using mobile manipulator robots.

Code for "On Memorization in Probabilistic Deep Generative Models"

PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World [ACL 2021]

Video Frame Interpolation with Transformer (CVPR2022)

Deep Surface Reconstruction from Point Clouds with Visibility Information

Code release of paper "Deep Multi-View Stereo gone wild"

A pytorch &keras implementation and demo of Fastformer.