TatsuyaShirakawa / Poincare Embedding
Licence: mit
Poincaré Embedding (unofficial)
Stars: ✭ 218
Projects that are alternatives of or similar to Poincare Embedding
Multi object datasets
Multi-object image datasets with ground-truth segmentation masks and generative factors.
Stars: ✭ 121 (-44.5%)
Mutual labels: representation-learning
Deformable Kernels
Deforming kernels to adapt towards object deformation. In ICLR 2020.
Stars: ✭ 166 (-23.85%)
Mutual labels: representation-learning
Variational Ladder Autoencoder
Implementation of VLAE
Stars: ✭ 196 (-10.09%)
Mutual labels: representation-learning
Srl Zoo
State Representation Learning (SRL) zoo with PyTorch - Part of S-RL Toolbox
Stars: ✭ 125 (-42.66%)
Mutual labels: representation-learning
Autoregressive Predictive Coding
Autoregressive Predictive Coding: An unsupervised autoregressive model for speech representation learning
Stars: ✭ 138 (-36.7%)
Mutual labels: representation-learning
Stylealign
[ICCV 2019]Aggregation via Separation: Boosting Facial Landmark Detector with Semi-Supervised Style Transition
Stars: ✭ 172 (-21.1%)
Mutual labels: representation-learning
Sigver wiwd
Learned representation for Offline Handwritten Signature Verification. Models and code to extract features from signature images.
Stars: ✭ 112 (-48.62%)
Mutual labels: representation-learning
Pytorch Byol
PyTorch implementation of Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
Stars: ✭ 213 (-2.29%)
Mutual labels: representation-learning
Attribute Aware Attention
[ACM MM 2018] Attribute-Aware Attention Model for Fine-grained Representation Learning
Stars: ✭ 143 (-34.4%)
Mutual labels: representation-learning
Vae vampprior
Code for the paper "VAE with a VampPrior", J.M. Tomczak & M. Welling
Stars: ✭ 173 (-20.64%)
Mutual labels: representation-learning
Hyte
EMNLP 2018: HyTE: Hyperplane-based Temporally aware Knowledge Graph Embedding
Stars: ✭ 130 (-40.37%)
Mutual labels: representation-learning
Kate
Code & data accompanying the KDD 2017 paper "KATE: K-Competitive Autoencoder for Text"
Stars: ✭ 135 (-38.07%)
Mutual labels: representation-learning
Jodie
A PyTorch implementation of ACM SIGKDD 2019 paper "Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks"
Stars: ✭ 172 (-21.1%)
Mutual labels: representation-learning
Pcl
PyTorch code for "Prototypical Contrastive Learning of Unsupervised Representations"
Stars: ✭ 124 (-43.12%)
Mutual labels: representation-learning
Semantic Embeddings
Hierarchy-based Image Embeddings for Semantic Image Retrieval
Stars: ✭ 196 (-10.09%)
Mutual labels: representation-learning
Declutr
The corresponding code from our paper "DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations". Do not hesitate to open an issue if you run into any trouble!
Stars: ✭ 111 (-49.08%)
Mutual labels: representation-learning
Awesome Visual Representation Learning With Transformers
Awesome Transformers (self-attention) in Computer Vision
Stars: ✭ 166 (-23.85%)
Mutual labels: representation-learning
Paddlehelix
Bio-Computing Platform featuring Large-Scale Representation Learning and Multi-Task Deep Learning “螺旋桨”生物计算工具集
Stars: ✭ 213 (-2.29%)
Mutual labels: representation-learning
Awesome Network Embedding
A curated list of network embedding techniques.
Stars: ✭ 2,379 (+991.28%)
Mutual labels: representation-learning
Simclr
SimCLRv2 - Big Self-Supervised Models are Strong Semi-Supervised Learners
Stars: ✭ 2,720 (+1147.71%)
Mutual labels: representation-learning
poincare-embedding
These codes implement Poincar'e Embedding introduced in the following paper:
Requirements
- C++ compiler that supports c++14 or later
- for Windows user, using cygwin is recommended (with CMAKE and gcc/g++ selection) (thanks @patrickgitacc)
Build
cd poincare-embedding
mkdir work & cd work
cmake ..
make
Setup python environment
From the poincare-embeddings directory...
python3 -m venv venv
source venv/bin/activate
if using windows:
python3 -m venv venv
venv\Scripts\activate
Then run the following:
python3 -m pip install -r requirements.txt
python3 -c "import nltk; nltk.download('wordnet')"
Tutorial
We assume that you are in work directory
cd poincare-embedding
mkdir work & cd work
Data Creation
You can create WordNet noun hypernym pairs as follows
python ../scripts/create_wordnet_noun_hierarchy.py ./wordnet_noun_hypernyms.tsv
and mammal subtree is created by
python ../scripts/create_mammal_subtree.py ./mammal_subtree.tsv
Run
./poincare_embedding ./mammal_subtree.tsv ./embeddings.tsv -d 2 -t 8 -e 1000 -l 0.1 -L 0.0001 -n 20 -s 0
Plot a Mammal Tree
python ../scripts/plot_mammal_subtree.py ./embeddings.tsv --center_mammal
Note: if that doesn't work, may need to run the following:
tr -d '\015' < embeddings.tsv > embeddings_clean.tsv
Double check that the file has removed the character in question, then run
mv embeddings_clean.tsv embeddings.tsv
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].