Geometric Deep Learning bachelor thesis project and notes
-
Updated
Mar 3, 2020 - Jupyter Notebook
Geometric Deep Learning bachelor thesis project and notes
Implemented Machine Learning Algorithms in Hyperbolic Geometry (MDS, K-Means, Support vector machines, etc.)
About utilizing Hyperbolic space on NLP tasks.
Implementation of ICLR 21 paper: Probing BERT in Hyperbolic Spaces
Knowledge Association with Hyperbolic Knowledge Graph Embeddings, EMNLP 2020
Conformal Geometry Stonybrook 2020 final project
C++ implementation of TreeRep algorithm from Sonathalia & Gilbert "Tree! I am no Tree! I am a Low Dimensional Hyperbolic Embedding"
Code for the paper Joint Learning of Hyperbolic Label Embeddings for Hierarchical Multi-label Classification (EACL '21)
Hyperbolic Busemann Learning with Ideal Prototypes, NeurIPS2021
Learning joint Euclidean and hyperbolic graph representations. Codes for "Joint hyperbolic and Euclidean geometry contrastive graph neural networks" published in Information Sciences
Let’s train various models to embed Cayley graphs to hyperbolic plane and then study, how much can we say about groups from these embeddings. At the same time, let’s study models generalization ability, by changing their hyperparameters.
Facilitating learning, using, and designing graph processing pipelines/models systematically.
Hyperbolic Image Segmentation, CVPR 2022
The repository for Hyperbolic Representation Learning for Computer Vision, ECCV 2022
[EMNLP'21 Findings] HyperExpan: Taxonomy Expansion with Hyperbolic Representation Learning
Source code for HAKG: Hierarchy-Aware Knowledge Gated Network for Recommendation. SIGIR 2022.
Code for "Rethinking the compositionality of point clouds through regularization in the hyperbolic space" (NeurIPS 2022)
Code for CVPR-W 2020 paper "Hierarchical Image Classification using Entailment Cone Embeddings" https://arxiv.org/abs/2004.03459
Improved Embedded Topic Models in Hyperbolic Space
Code for the paper Learning the Predictability of the Future (CVPR 2021)
Add a description, image, and links to the hyperbolic-embeddings topic page so that developers can more easily learn about it.
To associate your repository with the hyperbolic-embeddings topic, visit your repo's landing page and select "manage topics."