GNEE - GAT Neural Event Embeddings

Related tags

Deep LearningGNEE
Overview

GNEE - GAT Neural Event Embeddings

This repository contains source code for the GNEE (GAT Neural Event Embeddings) method introduced in the paper: "Semi-Supervised Graph Attention Networks for Event Representation Learning".

Abstract: Event analysis from news and social networks is very useful for a wide range of social studies and real-world applications. Recently, event graphs have been explored to represent event datasets and their complex relationships, where events are vertices connected to other vertices that represent locations, people's names, dates, and various other event metadata. Graph representation learning methods are promising for extracting latent features from event graphs to enable the use of different classification algorithms. However, existing methods fail to meet important requirements for event graphs, such as (i) dealing with semi-supervised graph embedding to take advantage of some labeled events, (ii) automatically determining the importance of the relationships between event vertices and their metadata vertices, as well as (iii) dealing with the graph heterogeneity. In this paper, we present GNEE (GAT Neural Event Embeddings), a method that combines Graph Attention Networks and Graph Regularization. First, an event graph regularization is proposed to ensure that all graph vertices receive event features, thereby mitigating the graph heterogeneity drawback. Second, semi-supervised graph embedding with self-attention mechanism considers existing labeled events, as well as learns the importance of relationships in the event graph during the representation learning process. A statistical analysis of experimental results with five real-world event graphs and six graph embedding methods shows that GNEE obtains state-of-the-art results.

File Structure

Our method consists of a BERT text encoding and a pre-processment procedure followed by modified version of GAT (Veličković et. al - 2017, https://arxiv.org/abs/1710.10903) to the event embedding task.

In our work, we adopt and modify the PyTorch implementation of GAT, pyGAT, developed by Diego999.

.
├── datasets_runs/ -> Datasets used
├── event_graph_utils.py -> Useful functions when working with event datasets
├── layers.py -> Implementation of Graph Attention layers
├── LICENSE
├── main.py -> Execute this script to reproduce our experiments (refer to our paper for more details)
├── models.py -> Implementation of the original GAT model
├── notebooks -> Run these notebooks to reproduce all our experiments.
├── README.md
├── requirements.txt
├── train.py -> Implementation of our preprocessing, traning and testing pipelines
└── utils.py -> Useful functions used in GAT original implementation.

Reproducibility Notebooks

./notebooks
├── DeepWalk_Event_Embeddings.ipynb -> DeepWalk Benchmark
├── GAT_Event_Embeddings_+_Without_Regularization.ipynb -> GAT w/o embeddings benchmark
├── GCN_Event_Embeddings_.ipynb -> GCN Benchmark
├── GNEE_Attention_Matrices_Example.ipynb -> GNEE Attention matrices visualization
├── GNEE_Embedding_Visualization_t_SNE.ipynb -> GNEE Embeddings visualization using t-SNE
├── GNEE.ipynb -> GNEE Benchmark
├── Label_Propagation_Event_Classification.ipynb -> LP Benchmark
├── LINE_Event_Embeddings.ipynb -> LINE Benchmark
├── Node2Vec_Event_Embeddings.ipynb -> Node2Vec Benchmark
├── SDNE_Event_Embeddings.ipynb -> SDNE Benchmark
└── Struct2Vec_Event_Embeddings.ipynb -> Struct2Vec Benchmark

Hardware requirements

When running on "dense" mode (no --sparse flag), our model uses about 18 GB on GRAM. On the other hand, the sparse mode (using --sparse) uses less than 1.5 GB on GRAM, which is an ideal setup to environments such as Google Colab.

Issues/Pull Requests/Feedbacks

Please, contact the authors in case of issues / pull requests / feedbacks :)

Owner
João Pedro Rodrigues Mattos
Undergraduate Research Assistant, sponsored by FAPESP - Machine Learning | Web Development | Human Computer Interface
João Pedro Rodrigues Mattos
Prompts - Read a textfile of prompts and import into anki via ankiconnect

prompts read a textfile of prompts and import into anki via ankiconnect Usage In

Alexander Cobleigh 2 Jul 28, 2022
PyTorch - Python + Nim

Master Release Pytorch - Py + Nim A Nim frontend for pytorch, aiming to be mostly auto-generated and internally using ATen. Because Nim compiles to C+

Giovanni Petrantoni 425 Dec 22, 2022
A clean and extensible PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners

A clean and extensible PyTorch implementation of Masked Autoencoders Are Scalable Vision Learners A PyTorch re-implementation of Mask Autoencoder trai

Tianyu Hua 23 Dec 13, 2022
Code from Daniel Lemire, A Better Alternative to Piecewise Linear Time Series Segmentation

PiecewiseLinearTimeSeriesApproximation code from Daniel Lemire, A Better Alternative to Piecewise Linear Time Series Segmentation, SIAM Data Mining 20

Daniel Lemire 21 Oct 27, 2022
Pytorch implementation of the paper SPICE: Semantic Pseudo-labeling for Image Clustering

SPICE: Semantic Pseudo-labeling for Image Clustering By Chuang Niu and Ge Wang This is a Pytorch implementation of the paper. (In updating) SOTA on 5

Chuang Niu 154 Dec 15, 2022
A curated list of resources for Image and Video Deblurring

A curated list of resources for Image and Video Deblurring

Subeesh Vasu 1.7k Jan 01, 2023
Title: Heart-Failure-Classification

This Notebook is based off an open source dataset available on where I have created models to classify patients who can potentially witness heart failure on the basis of various parameters. The best

Akarsh Singh 2 Sep 13, 2022
Faster RCNN pytorch windows

Faster-RCNN-pytorch-windows Faster RCNN implementation with pytorch for windows Open cmd, compile this comands: cd lib python setup.py build develop T

Hwa-Rang Kim 1 Nov 11, 2022
Official implementation for NIPS'17 paper: PredRNN: Recurrent Neural Networks for Predictive Learning Using Spatiotemporal LSTMs.

PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning The predictive learning of spatiotemporal sequences aims to generate future

THUML: Machine Learning Group @ THSS 243 Dec 26, 2022
Few-shot Neural Architecture Search

One-shot Neural Architecture Search uses a single supernet to approximate the performance each architecture. However, this performance estimation is super inaccurate because of co-adaption among oper

Yiyang Zhao 38 Oct 18, 2022
DimReductionClustering - Dimensionality Reduction + Clustering + Unsupervised Score Metrics

Dimensionality Reduction + Clustering + Unsupervised Score Metrics Introduction

11 Nov 15, 2022
This repository contains the code for the paper Neural RGB-D Surface Reconstruction

Neural RGB-D Surface Reconstruction Paper | Project Page | Video Neural RGB-D Surface Reconstruction Dejan Azinović, Ricardo Martin-Brualla, Dan B Gol

Dejan 406 Jan 04, 2023
Reproducing code of hair style replacement method from Barbershorp.

Barbershorp Reproducing code of hair style replacement method from Barbershorp. Also reproduces II2S, an improved version of Image2StyleGAN. Requireme

1 Dec 24, 2021
Zero-shot Synthesis with Group-Supervised Learning (ICLR 2021 paper)

GSL - Zero-shot Synthesis with Group-Supervised Learning Figure: Zero-shot synthesis performance of our method with different dataset (iLab-20M, RaFD,

Andy_Ge 62 Dec 21, 2022
Face Recognition plus identification simply and fast | Python

PyFaceDetection Face Recognition plus identification simply and fast Ubuntu Setup sudo pip3 install numpy sudo pip3 install cmake sudo pip3 install dl

Peyman Majidi Moein 16 Sep 22, 2022
End-to-end image segmentation kit based on PaddlePaddle.

English | 简体中文 PaddleSeg PaddleSeg has released the new version including the following features: Our team won the 6.2k Jan 02, 2023

Train robotic agents to learn pick and place with deep learning for vision-based manipulation in PyBullet.

Ravens is a collection of simulated tasks in PyBullet for learning vision-based robotic manipulation, with emphasis on pick and place. It features a Gym-like API with 10 tabletop rearrangement tasks,

Google Research 367 Jan 09, 2023
FairMOT for Multi-Class MOT using YOLOX as Detector

FairMOT-X Project Overview FairMOT-X is a multi-class multi object tracker, which has been tailored for training on the BDD100K MOT Dataset. It makes

Jonathan Tan 33 Dec 28, 2022
Local Attention - Flax module for Jax

Local Attention - Flax Autoregressive Local Attention - Flax module for Jax Install $ pip install local-attention-flax Usage from jax import random fr

Phil Wang 16 Jun 16, 2022
Funnels: Exact maximum likelihood with dimensionality reduction.

Funnels This repository contains the code needed to reproduce the experiments from the paper: Funnels: Exact maximum likelihood with dimensionality re

2 Apr 21, 2022