A PyTorch implementation of "Semi-Supervised Graph Classification: A Hierarchical Graph Perspective" (WWW 2019)

Overview

SEAL

PWC codebeat badge repo sizebenedekrozemberczki⠀⠀

A PyTorch implementation of Semi-Supervised Graph Classification: A Hierarchical Graph Perspective (WWW 2019)

Abstract

Node classification and graph classification are two graph learning problems that predict the class label of a node and the class label of a graph respectively. A node of a graph usually represents a real-world entity, e.g., a user in a social network, or a protein in a protein-protein interaction network. In this work, we consider a more challenging but practically useful setting, in which a node itself is a graph instance. This leads to a hierarchical graph perspective which arises in many domains such as social network, biological network and document collection. For example, in a social network, a group of people with shared interests forms a user group, whereas a number of user groups are interconnected via interactions or common members. We study the node classification problem in the hierarchical graph where a `node' is a graph instance, e.g., a user group in the above example. As labels are usually limited in real-world data, we design two novel semi-supervised solutions named Semi-supervised graph classification via Cautious/Active Iteration (or SEAL-C/AI in short). SEAL-C/AI adopt an iterative framework that takes turns to build or update two classifiers, one working at the graph instance level and the other at the hierarchical graph level. To simplify the representation of the hierarchical graph, we propose a novel supervised, self-attentive graph embedding method called SAGE, which embeds graph instances of arbitrary size into fixed-length vectors. Through experiments on synthetic data and Tencent QQ group data, we demonstrate that SEAL-C/AI not only outperform competing methods by a significant margin in terms of accuracy/Macro-F1, but also generate meaningful interpretations of the learned representations.

This repository provides a PyTorch implementation of SEAL-CI as described in the paper:

Semi-Supervised Graph Classification: A Hierarchical Graph Perspective. Jia Li, Yu Rong, Hong Cheng, Helen Meng, Wenbing Huang, Junzhou Huang. WWW, 2019. [Paper]

A TensorFlow implementatio of the model is available [here].

Requirements

The codebase is implemented in Python 3.5.2. package versions used for development are just below.

networkx          2.4
tqdm              4.28.1
numpy             1.15.4
pandas            0.23.4
texttable         1.5.0
scipy             1.1.0
argparse          1.1.0
torch             1.1.0
torch-scatter     1.4.0
torch-sparse      0.4.3
torch-cluster     1.4.5
torch-geometric   1.3.2
torchvision       0.3.0

Datasets

Graphs

The code takes graphs for training from an input folder where each graph is stored as a JSON. Graphs used for testing are also stored as JSON files. Every node id and node label has to be indexed from 0. Keys of dictionaries are stored strings in order to make JSON serialization possible.

The graphs file has to be unzipped in the input folder.

Every JSON file has the following key-value structure:

{"edges": [[0, 1],[1, 2],[2, 3],[3, 4]],
 "features": {"0": ["A","B"], "1": ["B","K"], "2": ["C","F","A"], "3": ["A","B"], "4": ["B"]},
 "label": "A"}

The edges key has an edge list value which descibes the connectivity structure. The features key has features for each node which are stored as a dictionary -- within this nested dictionary features are list values, node identifiers are keys. The label key has a value which is the class membership.

Hierarchical graph

The hierarchical graph is stored as an edge list, where graph identifiers integers are the node identifiers. Finally, node pairs are separated by commas in the comma separated values file. This edge list file has a header.

Options

Training a SEAL-CI model is handled by the src/main.py script which provides the following command line arguments.

Input and output options

  --graphs                STR    Training graphs folder.      Default is `input/graphs/`.
  --hierarchical-graph    STR    Macro level graph.           Default is `input/synthetic_edges.csv`.

Model options

  --epochs                      INT     Number of epochs.                  Default is 10.
  --budget                      INT     Nodes to be added.                 Default is 20.
  --labeled-count               INT     Number of labeled instances.       Default is 100.
  --first-gcn-dimensions        INT     Graph level GCN 1st filters.       Default is 16.
  --second-gcn-dimensions       INT     Graph level GCN 2nd filters.       Default is 8.
  --first-dense-neurons         INT     SAGE aggregator neurons.           Default is 16.
  --second-dense-neurons        INT     SAGE attention neurons.            Default is 4.
  --macro-gcn-dimensions        INT     Macro level GCN neurons.           Default is 16.
  --weight-decay                FLOAT   Weight decay of Adam.              Defatul is 5*10^-5.
  --gamma                       FLOAT   Regularization parameter.          Default is 10^-5.
  --learning-rate               FLOAT   Adam learning rate.                Default is 0.01.

Examples

The following commands learn a model and score on the unlabaled instances. Training a model on the default dataset:

python src/main.py

Training each SEAL-CI model for a 100 epochs.

python src/main.py --epochs 100

Changing the budget size.

python src/main.py --budget 200

You might also like...
Unofficial PyTorch Implementation of AHDRNet (CVPR 2019)
Unofficial PyTorch Implementation of AHDRNet (CVPR 2019)

AHDRNet-PyTorch This is the PyTorch implementation of Attention-guided Network for Ghost-free High Dynamic Range Imaging (CVPR 2019). The official cod

This Repo is the official CUDA implementation of ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures

Introduction This Repo is the official CUDA implementation of ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures. @inproceedings{Wa

An implementation of
An implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019).

MixHop and N-GCN ⠀ A PyTorch implementation of "MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing" (ICML 2019)

[CIKM 2019] Code and dataset for "Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction"

FiGNN for CTR prediction The code and data for our paper in CIKM2019: Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Predicti

Code for: Gradient-based Hierarchical Clustering using Continuous Representations of Trees in Hyperbolic Space. Nicholas Monath, Manzil Zaheer, Daniel Silva, Andrew McCallum, Amr Ahmed. KDD 2019.

gHHC Code for: Gradient-based Hierarchical Clustering using Continuous Representations of Trees in Hyperbolic Space. Nicholas Monath, Manzil Zaheer, D

《A-CNN: Annularly Convolutional Neural Networks on Point Clouds》(2019)
《A-CNN: Annularly Convolutional Neural Networks on Point Clouds》(2019)

A-CNN: Annularly Convolutional Neural Networks on Point Clouds Created by Artem Komarichev, Zichun Zhong, Jing Hua from Department of Computer Science

《Deep Single Portrait Image Relighting》(ICCV 2019)

Ratio Image Based Rendering for Deep Single-Image Portrait Relighting [Project Page] This is part of the Deep Portrait Relighting project. If you find

《Single Image Reflection Removal Beyond Linearity》(CVPR 2019)

Single-Image-Reflection-Removal-Beyond-Linearity Paper Single Image Reflection Removal Beyond Linearity. Qiang Wen, Yinjie Tan, Jing Qin, Wenxi Liu, G

Official repository for Jia, Raghunathan, Göksel, and Liang, "Certified Robustness to Adversarial Word Substitutions" (EMNLP 2019)

Certified Robustness to Adversarial Word Substitutions This is the official GitHub repository for the following paper: Certified Robustness to Adversa

Comments
  • question about python-cluster and python-scatter

    question about python-cluster and python-scatter

    Hello, I failed to build python-cluster 1.2.4 and python-scatter 1.1.2 with pytorch 0.4.1

    It seems that python-scatter 1.0.4 can fit pytorch 0.4.1 However, I cant find proper verision for python-cluster

    Thank you!

    opened by gyc913 1
  • 关于  RuntimeError: index 145 is out of bounds for dimension 0 with size 1 的报错

    关于 RuntimeError: index 145 is out of bounds for dimension 0 with size 1 的报错

    您好,我在运行您的代码的时候报错 RuntimeError: index 145 is out of bounds for dimension 0 with size 1, 提示错误可能出现在node_features_1 = torch.nn.functional.relu(self.graph_convolution_1(features, edges))这一句处,涉及scatter.py。查了很久的资料,都没有解决。请问您知道是什么问题导致的吗?

    opened by heyjiege 0
  • The details about json file

    The details about json file

    Hi, I have an question about the json file. In the graph folder, every json file is a dictionary include label,feature and edge, the feature is displayed by the index of the node, while the key is "cc_XX" and the "deg_4", so what does the "cc_XX" stand for? When I build my own dataset, how can I obtain the "cc_XX".

    opened by ChenTao2017110 0
Releases(v_001)
Owner
Benedek Rozemberczki
Machine Learning Engineer at AstraZeneca | PhD from The University of Edinburgh.
Benedek Rozemberczki
Application of the L2HMC algorithm to simulations in lattice QCD.

l2hmc-qcd 📊 Slides Recent talk on Training Topological Samplers for Lattice Gauge Theory from the Machine Learning for High Energy Physics, on and of

Sam Foreman 37 Dec 14, 2022
A PoC Corporation Relationship Knowledge Graph System on top of Nebula Graph.

Corp-Rel is a PoC of Corpartion Relationship Knowledge Graph System. It's built on top of the Open Source Graph Database: Nebula Graph with a dataset

Wey Gu 20 Dec 11, 2022
NumQMBasic - A mini-course offered to Undergrad physics students

The best way to use this material is by forking it by click the Fork button at the top, right corner. Then you will get your own copy to play with! Th

Raghu 35 Dec 05, 2022
KoCLIP: Korean port of OpenAI CLIP, in Flax

KoCLIP This repository contains code for KoCLIP, a Korean port of OpenAI's CLIP. This project was conducted as part of Hugging Face's Flax/JAX communi

Jake Tae 100 Jan 02, 2023
Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19)

Spatial Attentive Single-Image Deraining with a High Quality Real Rain Dataset (CVPR'19) Tianyu Wang*, Xin Yang*, Ke Xu, Shaozhe Chen, Qiang Zhang, Ry

Steve Wong 177 Dec 01, 2022
Lightweight tool to perform MITM attack on local network

ARPSpy - A lightweight tool to perform MITM attack Using many library to perform ARP Spoof and auto-sniffing HTTP packet containing credential. (Never

MinhItachi 8 Aug 28, 2022
f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation

f-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation [Paper] [PyTorch] [MXNet] [Video] This repository provides code for training

Visual Understanding Lab @ Samsung AI Center Moscow 516 Dec 21, 2022
Code for the paper Learning the Predictability of the Future

Learning the Predictability of the Future Code from the paper Learning the Predictability of the Future. Website of the project in hyperfuture.cs.colu

Computer Vision Lab at Columbia University 139 Nov 18, 2022
UniFormer - official implementation of UniFormer

UniFormer This repo is the official implementation of "Uniformer: Unified Transf

SenseTime X-Lab 573 Jan 04, 2023
Cross-platform CLI tool to generate your Github profile's stats and summary.

ghs Cross-platform CLI tool to generate your Github profile's stats and summary. Preview Hop on to examples for other usecases. Jump to: Installation

HackerRank 134 Dec 20, 2022
Equivariant CNNs for the sphere and SO(3) implemented in PyTorch

Equivariant CNNs for the sphere and SO(3) implemented in PyTorch

Jonas Köhler 893 Dec 28, 2022
A framework that constructs deep neural networks, autoencoders, logistic regressors, and linear networks

A framework that constructs deep neural networks, autoencoders, logistic regressors, and linear networks without the use of any outside machine learning libraries - all from scratch.

Kordel K. France 2 Nov 14, 2022
Learning to Draw: Emergent Communication through Sketching

Learning to Draw: Emergent Communication through Sketching This is the official code for the paper "Learning to Draw: Emergent Communication through S

19 Jul 22, 2022
Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis

Readme File for "Using Machine Learning to Test Causal Hypotheses in Conjoint Analysis" by Ham, Imai, and Janson. (2022) All scripts were written and

0 Jan 27, 2022
Segmentation for medical image.

EfficientSegmentation Introduction EfficientSegmentation is an open source, PyTorch-based segmentation framework for 3D medical image. Features A whol

68 Nov 28, 2022
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

face.evoLVe: High-Performance Face Recognition Library based on PaddlePaddle & PyTorch Evolve to be more comprehensive, effective and efficient for fa

Zhao Jian 3.1k Jan 02, 2023
Fine-tune pretrained Convolutional Neural Networks with PyTorch

Fine-tune pretrained Convolutional Neural Networks with PyTorch. Features Gives access to the most popular CNN architectures pretrained on ImageNet. A

Alex Parinov 694 Nov 23, 2022
Greedy Gaussian Segmentation

GGS Greedy Gaussian Segmentation (GGS) is a Python solver for efficiently segmenting multivariate time series data. For implementation details, please

Stanford University Convex Optimization Group 72 Dec 07, 2022
Elevation Mapping on GPU.

Elevation Mapping cupy Overview This is a ros package of elevation mapping on GPU. Code are written in python and uses cupy for GPU calculation. * pla

Robotic Systems Lab - Legged Robotics at ETH Zürich 183 Dec 19, 2022
Official Repository for the ICCV 2021 paper "PixelSynth: Generating a 3D-Consistent Experience from a Single Image"

PixelSynth: Generating a 3D-Consistent Experience from a Single Image (ICCV 2021) Chris Rockwell, David F. Fouhey, and Justin Johnson [Project Website

Chris Rockwell 95 Nov 22, 2022