AKGNN

The source code for Adaptive Kernel Graph Neural Network at AAAI2022.

Please cite our paper if you think our work is helpful to you:

@inproceedings{ju2022akgnn,
  title={Adaptive Kernel Graph Neural Network},
  author={Ju, Mingxuan and Hou, Shifu and Fan, Yujie and Zhao, Jianan and Ye, Yanfang and Zhao, Liang},
  booktitle={36th AAAI Conference on Artificial Intelligence (AAAI)},
  year={2022}
}

Requirements

Python 3.8.3
Please install other pakeages by pip install -r requirement.txt

Usage Example

Running on Cora: python train_cora.py
Running on Citeseer: python train_citeseer.py
Running on Pubmed: python train_pubmed.py

Results

Our model achieves the following accuracies on Cora, CiteSeer and Pubmed with the public splits:

Model name	Cora	CiteSeer	Pubmed
AKGNN	84.8%	73.5%	80.4%

Running Environment

The experimental results reported in paper are conducted on a single NVIDIA GeForce RTX 2080 Ti with CUDA 11.1, which might be slightly inconsistent with the results induced by other platforms.

The source code for Adaptive Kernel Graph Neural Network at AAAI2022

Related tags

Overview

AKGNN

Requirements

Usage Example

Results

Running Environment

Owner

PyTorch code for the paper: FeatMatch: Feature-Based Augmentation for Semi-Supervised Learning

A curated list of awesome papers for Semantic Retrieval (TOIS Accepted: Semantic Models for the First-stage Retrieval: A Comprehensive Review).

Learning Features with Parameter-Free Layers (ICLR 2022)

Script that attempts to force M1 macs into RGB mode when used with monitors that are defaulting to YPbPr.

Noether Networks: meta-learning useful conserved quantities

Implementation of Uniformer, a simple attention and 3d convolutional net that achieved SOTA in a number of video classification tasks

PyTorch implementation of Convolutional Neural Fabrics http://arxiv.org/abs/1606.02492

Existing Literature about Machine Unlearning

Multi-task head pose estimation in-the-wild

How the Deep Q-learning method works and discuss the new ideas that makes the algorithm work

Code for AutoNL on ImageNet (CVPR2020)

Hyperopt for solving CIFAR-100 with a convolutional neural network (CNN) built with Keras and TensorFlow, GPU backend

PyTorch implementation for Graph Contrastive Learning with Augmentations

PyTorch GPU implementation of the ES-RNN model for time series forecasting

A Transformer-Based Siamese Network for Change Detection

Wind Speed Prediction using LSTMs in PyTorch

Pytorch implementation of Learning with Opponent-Learning Awareness

(ICCV 2021) PyTorch implementation of Paper "Progressive Correspondence Pruning by Consensus Learning"

Individual Treatment Effect Estimation

Implementation of ResMLP, an all MLP solution to image classification, in Pytorch