Skip to main content

Exploring Machine Learning Dataset with Knowledge Graph

Primary supervisor

Chunyang Chen

In recent days, Deep Learning projects have achieved significant progress in many domains, such as Computer Vision (CV), Natural Language Processing (NLP), Speech Recognition, etc. Therefore, numerous new deep learning, machine learning models are introduced each year. To collect all the emerged data, PeperwithCode was introduced. It is a website that aims to create a free and open resource with Machine Learning papers, code, datasets, methods, and evaluation tables.

With over 200k papers recorded, we hope to work with a student to build up a knowledge graph based on the whole dataset. Then, based on the dataset, we can apply Neural Network Models for knowledge graphs to it for some further research, for example, explore and find the existing relations between each node, or predict the hidden links between technique nodes. We could further use visualizations to illustrate the connections of each paper/method to help users better understand the bigger picture.

 

Paper with Code:

https://paperswithcode.com/

 

KnowledgeGraph

A Survey on Knowledge Graphs: Representation, Acquisition, and Applications

https://arxiv.org/abs/2002.00388

Student cohort

Double Semester