[WWW 2021 GLB] New Benchmarks for Learning on Non-Homophilous Graphs

Overview

New Benchmarks for Learning on Non-Homophilous Graphs

Here are the codes and datasets accompanying the paper:
New Benchmarks for Learning on Non-Homophilous Graphs
Derek Lim (Cornell), Xiuyu Li (Cornell), Felix Hohne (Cornell), and Ser-Nam Lim (Facebook AI).
Workshop on Graph Learning Benchmarks, WWW 2021.
[PDF link]

There are codes to load our proposed datasets, compute our measure of the presence of homophily, and train various graph machine learning models in our experimental setup.

Organization

main.py contains the main experimental scripts.

dataset.py loads our datasets.

models.py contains implementations for graph machine learning models, though C&S (correct_smooth.py, cs_tune_hparams.py) is in separate files. Also, gcn-ogbn-proteins.py contains code for running GCN and GCN+JK on ogbn-proteins. Running several of the GNN models on larger datasets may require at least 24GB of VRAM.

homophily.py contains functions for computing homophily measures, including the one that we introduce in our_measure.

Datasets

Alt text

As discussed in the paper, our proposed datasets are "twitch-e", "yelp-chi", "deezer", "fb100", "pokec", "ogbn-proteins", "arxiv-year", and "snap-patents", which can be loaded by load_nc_dataset in dataset.py by passing in their respective string name. Many of these datasets are included in the data/ directory, but due to their size, yelp-chi, snap-patents, and pokec are automatically downloaded from a Google drive link when loaded from dataset.py. The arxiv-year and ogbn-proteins datasets are downloaded using OGB downloaders. load_nc_dataset returns an NCDataset, the documentation for which is also provided in dataset.py. It is functionally equivalent to OGB's Library-Agnostic Loader for Node Property Prediction, except for the fact that it returns torch tensors. See the OGB website for more specific documentation. Just like the OGB function, dataset.get_idx_split() returns fixed dataset split for training, validation, and testing.

When there are multiple graphs (as in the case of twitch-e and fb100), different ones can be loaded by passing in the sub_dataname argument to load_nc_dataset in dataset.py.

twitch-e consists of seven graphs ["DE", "ENGB", "ES", "FR", "PTBR", "RU", "TW"]. In the paper we test on DE.

fb100 consists of 100 graphs. We only include ["Amherst41", "Cornell5", "Johns Hopkins55", "Penn94", "Reed98"] in this repo, although others may be downloaded from the internet archive. In the paper we test on Penn94.

Alt text

Installation instructions

  1. Create and activate a new conda environment using python=3.8 (i.e. conda create --name non-hom python=3.8)
  2. Activate your conda environment
  3. Check CUDA version using nvidia-smi
  4. In the root directory of this repository, run bash install.sh cu110, replacing cu110 with your CUDA version (i.e. CUDA 11 -> cu110, CUDA 10.2 -> cu102, CUDA 10.1 -> cu101). We tested on Ubuntu 18.04, CUDA 11.0.

Running experiments

  1. Make sure a results folder exists in the root directory.
  2. Our experiments are in the experiments/ directory. There are bash scripts for running methods on single and multiple datasets. Please note that the experiments must be run from the root directory. For instance, to run the MixHop experiments on snap-patents, use:
bash experiments/mixhop_exp.sh snap-patents

Some datasets require specifying a second sub_dataset argument e.g. to run MixHop experiments on the twitch-e, DE sub_dataset, do:

bash experiments/mixhop_exp.sh twitch-e DE

Otherwise, run python main.py --help to see the full list of options for running experiments. As one example, to train a GAT with max jumping knowledge connections on (directed) arxiv-year with 32 hidden channels and 4 attention heads, run:

python main.py --dataset arxiv-year --method gatjk --hidden_channels 32 --gat_heads 4 --directed
Owner
Cornell University Artificial Intelligence
HF's ML for Audio study group

Hugging Face Machine Learning for Audio Study Group Welcome to the ML for Audio Study Group. Through a series of presentations, paper reading and disc

Vaibhav Srivastav 110 Jan 01, 2023
OpenChat: Opensource chatting framework for generative models

OpenChat is opensource chatting framework for generative models.

Hyunwoong Ko 427 Jan 06, 2023
ConvBERT-Prod

ConvBERT 目录 0. 仓库结构 1. 简介 2. 数据集和复现精度 3. 准备数据与环境 3.1 准备环境 3.2 准备数据 3.3 准备模型 4. 开始使用 4.1 模型训练 4.2 模型评估 4.3 模型预测 5. 模型推理部署 5.1 基于Inference的推理 5.2 基于Serv

yujun 7 Apr 08, 2022
Backend for the Autocomplete platform. An AI assisted coding platform.

Introduction A custom predictor allows you to deploy your own prediction implementation, useful when the existing serving implementations don't fit yo

Tatenda Christopher Chinyamakobvu 1 Jan 31, 2022
Yes it's true :broken_heart:

Information WARNING: No longer hosted If you would like to be on this repo's readme simply fork or star it! Forks 1 - Flowzii 2 - Errorcrafter 3 - vk-

Dropout 66 Dec 31, 2022
Words-per-minute - A terminal app written in python utilizing the curses module that tests the user's ability to type

words-per-minute A terminal app written in python utilizing the curses module th

Tanim Islam 1 Jan 14, 2022
Mysticbbs-rjam - rJAM splitscreen message reader for MysticBBS A46+

rJAM splitscreen message reader for MysticBBS A46+

Robbert Langezaal 4 Nov 22, 2022
PyTorch Language Model for 1-Billion Word (LM1B / GBW) Dataset

PyTorch Large-Scale Language Model A Large-Scale PyTorch Language Model trained on the 1-Billion Word (LM1B) / (GBW) dataset Latest Results 39.98 Perp

Ryan Spring 114 Nov 04, 2022
Transformer Based Korean Sentence Spacing Corrector

TKOrrector Transformer Based Korean Sentence Spacing Corrector License Summary This solution is made available under Apache 2 license. See the LICENSE

Paul Hyung Yuel Kim 3 Apr 18, 2022
LSTM based Sentiment Classification using Tensorflow - Amazon Reviews Rating

LSTM based Sentiment Classification using Tensorflow - Amazon Reviews Rating (Dataset) The dataset is from Amazon Review Data (2018)

Immanuvel Prathap S 1 Jan 16, 2022
jel - Japanese Entity Linker - is Bi-encoder based entity linker for japanese.

jel: Japanese Entity Linker jel - Japanese Entity Linker - is Bi-encoder based entity linker for japanese. Usage Currently, link and question methods

izuna385 10 Jan 06, 2023
Main repository for the chatbot Bobotinho.

Bobotinho Bot Main repository for the chatbot Bobotinho. ℹ️ Introduction Twitch chatbot with entertainment commands. ‎ 💻 Technologies Concurrent code

Bobotinho 14 Nov 29, 2022
Official codebase for Can Wikipedia Help Offline Reinforcement Learning?

Official codebase for Can Wikipedia Help Offline Reinforcement Learning?

Machel Reid 82 Dec 19, 2022
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding

Bethge Lab 61 Dec 21, 2022
Easy-to-use CPM for Chinese text generation

CPM 项目描述 CPM(Chinese Pretrained Models)模型是北京智源人工智能研究院和清华大学发布的中文大规模预训练模型。官方发布了三种规模的模型,参数量分别为109M、334M、2.6B,用户需申请与通过审核,方可下载。 由于原项目需要考虑大模型的训练和使用,需要安装较为复杂

382 Jan 07, 2023
Graph4nlp is the library for the easy use of Graph Neural Networks for NLP

Graph4NLP Graph4NLP is an easy-to-use library for R&D at the intersection of Deep Learning on Graphs and Natural Language Processing (i.e., DLG4NLP).

Graph4AI 1.5k Dec 23, 2022
STonKGs is a Sophisticated Transformer that can be jointly trained on biomedical text and knowledge graphs

STonKGs STonKGs is a Sophisticated Transformer that can be jointly trained on biomedical text and knowledge graphs. This multimodal Transformer combin

STonKGs 27 Aug 11, 2022
Watson Natural Language Understanding and Knowledge Studio

Material de demonstração dos serviços: Watson Natural Language Understanding e Knowledge Studio Visão Geral: https://www.ibm.com/br-pt/cloud/watson-na

Vanderlei Munhoz 4 Oct 24, 2021
Python3 to Crystal Translation using Python AST Walker

py2cr.py A code translator using AST from Python to Crystal. This is basically a NodeVisitor with Crystal output. See AST documentation (https://docs.

66 Jul 25, 2022
Extracting Summary Knowledge Graphs from Long Documents

GraphSum This repo contains the data and code for the G2G model in the paper: Extracting Summary Knowledge Graphs from Long Documents. The other basel

Zeqiu (Ellen) Wu 10 Oct 21, 2022