Mehak Khan's starred repositories
PyTorch-BigGraph
Generate embeddings from large-scale graph-structured data.
HIN-Datasets-for-Recommendation-and-Network-Embedding
Heterogeneous Information Network Datasets for Recommendation and Network Embedding
stable-diffusion-tensorflow
TensorFlow/Keras port of Stable Diffusion
GraphEmbeddingRecommendationSystem
Python based Graph Propagation algorithm, DeepWalk to evaluate and compare preference propagation algorithms in heterogeneous information networks from user item relation ship.
Recommendation-systems
Recommendation Systems This is a workshop on using Machine Learning and Deep Learning Techniques to build Recommendation Systesm Theory: ML & DL Formulation, Prediction vs. Ranking, Similiarity, Biased vs. Unbiased Paradigms: Content-based, Collaborative filtering, Knowledge-based, Hybrid and Ensembles Data: Tabular, Images, Text (Sequences) Models: (Deep) Matrix Factorisation, Auto-Encoders, Wide & Deep, Rank-Learning, Sequence Modelling Methods: Explicit vs. implicit feedback, User-Item matrix, Embeddings, Convolution, Recurrent, Domain Signals: location, time, context, social, Process: Setup, Encode & Embed, Design, Train & Select, Serve & Scale, Measure, Test & Improve Tools: python-data-stack: numpy, pandas, scikit-learn, keras, spacy, implicit, lightfm Notes & Slides Basics: Deep Learning AI Conference 2019: WhiteBoard Notes | In-Class Notebooks Notebooks Movies - Movielens 01-Acquire 02-Augment 03-Refine 04-Transform 05-Evaluation 06-Model-Baseline 07-Feature-extractor 08-Model-Matrix-Factorization 09-Model-Matrix-Factorization-with-Bias 10-Model-MF-NNMF 11-Model-Deep-Matrix-Factorization 12-Model-Neural-Collaborative-Filtering 13-Model-Implicit-Matrix-Factorization 14-Features-Image 15-Features-NLP Ecommerce - YooChoose 01-Data-Preparation 02-Models News - Hackernews Product - Groceries Python Libraries Deep Recommender Libraries Tensorrec - Built on Tensorflow Spotlight - Built on PyTorch TFranking - Built on TensorFlow (Learning to Rank) Matrix Factorisation Based Libraries Implicit - Implicit Matrix Factorisation QMF - Implicit Matrix Factorisation Lightfm - For Hybrid Recommedations Surprise - Scikit-learn type api for traditional alogrithms Similarity Search Libraries Annoy - Approximate Nearest Neighbour NMSLib - kNN methods FAISS - Similarity search and clustering Learning Resources Reference Slides Deep Learning in RecSys by Balázs Hidasi Lessons from Industry RecSys by Xavier Amatriain Architecting Recommendation Systems by James Kirk Recommendation Systems Overview by Raimon and Basilico Benchmarks MovieLens Benchmarks for Traditional Setup Microsoft Tutorial on Recommendation System at KDD 2019 Algorithms & Approaches Collaborative Filtering for Implicit Feedback Datasets Bayesian Personalised Ranking for Implicit Data Logistic Matrix Factorisation Neural Network Matrix Factorisation Neural Collaborative Filtering Variational Autoencoders for Collaborative Filtering Evaluations Evaluating Recommendation Systems
GCN.PyTorch
Graph Convolutional Networks for Text Classification.
Influence-maximization
The project is trying to find the most influential group of nodes in a huge social network.(SUSTech AI lab3)
NODE-SELECT
NODE-SELECT: A Graph Neural Network Based On A Selective Propagation Technique
Betweenness_Centrality
Betweenness Centrality is a metric that measures the importance of each node in a graph/network by giving it a numerical value. The nodes with the highest values of Betweenness Centrality will be the most important nodes in the graph.
Detection-of-Most-Influential-Nodes-in-a-Social-Network
This repository contains a novel model for the detection of most influential nodes in a social network graph
Node2Vec_DBLP_citation_graph
Aim is to convert nodes and node attributes of the DBLP Citation graph to analyze graph specific trends. This objective entailed two tasks, recreating a search algorithm for sampling the neighborhood as per the Node2Vec algorithm and extract feature embeddings using the Word2Vec skip-gram architecture. The nodes (papers)are represented into a fixed size multi-space dimension that is capable of capturing closeness of two papers based on a mentioned metric. The final classification of groups is based on the feature embeddings, performed by the spectral clustering algorithm. The sense-making converts to a search based optimization problem as we built our model to maximize the probability of each node belonging to a neighborhood found depending on the likelihood of revisiting a node and of out-ward exploration.
centrality-multitask
Code for the Paper "Multitask Learning on Graph Neural Networks: Learning Multiple Graph Centrality Measures with a Unified Network" published at ICANN2019