Context-aware Entity Typing in Knowledge Graphs

This is the source code for: Context-aware Entity Typing in Knowledge Graphs.

Requirements

Python 3
PyTorch >= 1.6.0
dgl >= 0.5.3

Usage

Data preprocessing:

cd data
python preprocess.py --dataset FB15kET
python preprocess.py --dataset YAGO43kET

Train:

########### FB15kET ###########
# CET
python run.py --model CET --dataset FB15kET --load_ET --load_KG --neighbor_sampling \
--hidden_dim 100 --temperature 0.5 --lr 0.001 --loss FNA --beta 4.0 --cuda

# R-GCN
python run.py --model RGCN --dataset FB15kET --load_ET --load_KG --neighbor_sampling \
--hidden_dim 100 --lr 0.001 --loss FNA --beta 3.0 --cuda

# CompGCN
python run.py --model CompGCN --dataset FB15kET --load_ET --load_KG --neighbor_sampling \
--hidden_dim 100 --lr 0.001 --loss FNA --activation relu --cuda

########### YAGO43kET ###########
# CET
python run.py --model CET --dataset YAGO43kET --load_ET --load_KG --neighbor_sampling \
--hidden_dim 100 --temperature 0.5 --lr 0.001 --loss FNA --beta 2.0 --cuda

# R-GCN
python run.py --model RGCN --dataset YAGO43kET --load_ET --load_KG --neighbor_sampling \
--hidden_dim 100 --lr 0.001 --loss FNA --beta 2.0 --cuda

# CompGCN
python run.py --model CompGCN --dataset YAGO43kET --load_ET --load_KG --neighbor_sampling \
--hidden_dim 100 --lr 0.001 --loss FNA --activation relu --cuda

The KGE baselines can be found in KGE_baselines.

Acknowledgement

We refer to the code of DGL. Thanks for their contributions.

This is the source code for: Context-aware Entity Typing in Knowledge Graphs.

Related tags

Overview

Context-aware Entity Typing in Knowledge Graphs

Requirements

Usage

Acknowledgement

Owner

【ACMMM 2021】DSANet: Dynamic Segment Aggregation Network for Video-Level Representation Learning

Code for the paper "Query Embedding on Hyper-relational Knowledge Graphs"

Code of paper Interact, Embed, and EnlargE (IEEE): Boosting Modality-specific Representations for Multi-Modal Person Re-identification.

Online Pseudo Label Generation by Hierarchical Cluster Dynamics for Adaptive Person Re-identification

🍅🍅🍅YOLOv5-Lite: lighter, faster and easier to deploy. Evolved from yolov5 and the size of model is only 1.7M (int8) and 3.3M (fp16). It can reach 10+ FPS on the Raspberry Pi 4B when the input size is 320×320~

Old Photo Restoration (Official PyTorch Implementation)

📚 Papermill is a tool for parameterizing, executing, and analyzing Jupyter Notebooks.

[AAAI2021] The source code for our paper 《Enhancing Unsupervised Video Representation Learning by Decoupling the Scene and the Motion》.

Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models

Este conversor criará a medida exata para sua receita de capuccino gelado da grandiosa Rafaella Ballerini!

利用python脚本实现微信、支付宝账单的合并，并保存到excel文件实现自动记账，可查看可视化图表。

A criticism of a recent paper on buggy image downsampling methods in popular image processing and deep learning libraries.

Dynamic Divide-and-Conquer Adversarial Training for Robust Semantic Segmentation （ICCV2021）

Official PyTorch code for CVPR 2020 paper "Deep Active Learning for Biased Datasets via Fisher Kernel Self-Supervision"

Identify the emotion of multiple speakers in an Audio Segment

Voice Conversion by CycleGAN (语音克隆/语音转换)：CycleGAN-VC3

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

Official PyTorch Implementation of paper "Deep 3D Mask Volume for View Synthesis of Dynamic Scenes", ICCV 2021.

Receptive Field Block Net for Accurate and Fast Object Detection, ECCV 2018

PyTorch implementation for paper "Full-Body Visual Self-Modeling of Robot Morphologies".