Name: Hussein Abdallah
Type: User
Company: Computer Science PhD Candidate
Bio: PhD candidate/TA at Concordia University @CoDS-GCS , Interested in ML applications for large Scale KGs, Sampling for Graph neural networks,RAG-KG
Twitter: Hussein_Abdala1
Location: Montreal,Canada
Hussein Abdallah's Projects
ai4db and db4ai work
Example notebooks that show how to apply machine learning, deep learning and reinforcement learning in Amazon SageMaker
Pre-trained Transformers for the Arabic Language Understanding and Generation (Arabic BERT, Arabic GPT2, Arabic Electra)
AraVec is a pre-trained distributed word representation (word embedding) open source project which aims to provide the Arabic NLP research community with free to use and powerful word embedding models.
Official implementation of A* Networks
Y. Zhang, Q. Yao, J. Kwok. Bilinear Scoring Function Search for Knowledge Graph Learning. TPAMI 2022
A list of awesome GNN systems.
A collection of AWESOME things about Graph-Related LLMs.
A curated list of papers and resources based on "Large Language Models on Graphs: A Comprehensive Survey".
A collection of resources on the topic of Complex Logical Query Answering
A curated list of references for MLOps
A topic-centric list of HQ open datasets.
Base64Image Plugin for CKEditor 4 - Adds images from local client as base64 string into the source without server side processing. You can also add external image urls into the source.
A quick way to benchmark your CUDA compiler on a Linux environment
Repository for benchmarking graph neural networks
Implementation of breadth first search on GPU with CUDA Driver API.
Generating Movie Recommendations from 1 million user ratings data, using Hadoop map-reduce and Spark on AWS cloud clusters
A Knowledge Graph for Relational Learning On Biological Data
Some examples on how to use bpmn-js
A Firefox extension to download YouTube videos in bulk: (old Website)
Code for TNNLS paper: "Comprehensive Graph Gradual Pruning for Sparse Training in Graph Neural Networks"
ChatGPT PROMPTs Splitter. Tool for safely process chunks of up to 15,000 characters per request
Model benchmark on CIFAR10 dataset in PyTorch.
Cloud IaaS Schema
This project aims at creating an RDF schema given a list of column headers of a tabular dataset. It first transforms the given header list into meaningful vectors, then it applies a distance-based Clustering algorithm such that it maximizes the similarity among headers inside one cluster. The user has the facility to move items from one cluster to another and merge among some clusters. The system can suggest cluster names based on the commonality among its members. If no common word found, it will produce Unknown. Afterwards, the user can rename the automatically generated names. Finally, it can expose the resultant clusters in an RDF format.
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit
CogDL: A Comprehensive Library for Graph Deep Learning (WWW 2023)
:mortar_board: Path to a free self-taught education in Computer Science!