Code for Understanding Pooling in Graph Neural Networks

Related tags

Deep LearningSRC
Overview

Select, Reduce, Connect

This repository contains the code used for the experiments of:

"Understanding Pooling in Graph Neural Networks"

Setup

Install TensorFlow and other dependencies:

pip install -r requirements.txt

Running experiments

Experiments are found in the following folders:

  • autoencoder/
  • spectral_similarity/
  • graph_classification/

Each folder has a bash script called run_all.sh that will reproduce the results reported in the paper.

To generate the plots and tables that we included in the paper, you can use the plots.py, plots_datasets.py, or tables.py found in the folders.

To run experiments for an individual pooling operator, you can use the run_[OPERATOR NAME].py scripts in each folder.

The pooling operators that we used for the experiments are found in layers/ (trainable) and modules/ (non-trainable). The GNN architectures used in the experiments are found in models/.

The SRCPool class

The core of this repository is the SRCPool class that implements a general interface to create SRC pooling layers with the Keras API.

Our implementation of MinCutPool, DiffPool, LaPool, Top-K, and SAGPool using the SRCPool class can be found in src/layers.

In general, SRC layers compute:

Where is a node equivariant selection function that computes the supernode assignments , is a permutation-invariant function to reduce the supernodes into the new node attributes, and is a permutation-invariant connection function that computes the links between the pooled nodes.

By extending this class, it is possible to create any pooling layer in the SRC framework.

Input

  • X: Tensor of shape ([batch], N, F) representing node features;
  • A: Tensor or SparseTensor of shape ([batch], N, N) representing the adjacency matrix;
  • I: (optional) Tensor of integers with shape (N, ) representing the batch index;

Output

  • X_pool: Tensor of shape ([batch], K, F), representing the node features of the output. K is the number of output nodes and depends on the specific pooling strategy;
  • A_pool: Tensor or SparseTensor of shape ([batch], K, K) representing the adjacency matrix of the output;
  • I_pool: (only if I was given as input) Tensor of integers with shape (K, ) representing the batch index of the output;
  • S_pool: (if return_sel=True) Tensor or SparseTensor representing the supernode assignments;

API

  • pool(X, A, I, **kwargs): pools the graph and returns the reduced node features and adjacency matrix. If the batch index I is not None, a reduced version of I will be returned as well. Any given kwargs will be passed as keyword arguments to select(), reduce() and connect() if any matching key is found. The mandatory arguments of pool() (X, A, and I) must be computed in call() by calling self.get_inputs(inputs).
  • select(X, A, I, **kwargs): computes supernode assignments mapping the nodes of the input graph to the nodes of the output.
  • reduce(X, S, **kwargs): reduces the supernodes to form the nodes of the pooled graph.
  • connect(A, S, **kwargs): connects the reduced supernodes.
  • reduce_index(I, S, **kwargs): helper function to reduce the batch index (only called if I is given as input).

When overriding any function of the API, it is possible to access the true number of nodes of the input (N) as a Tensor in the instance variable self.N (this is populated by self.get_inputs() at the beginning of call()).

Arguments:

  • return_sel: if True, the Tensor used to represent supernode assignments will be returned with X_pool, A_pool, and I_pool;
Owner
Daniele Grattarola
PhD student @ Università della Svizzera italiana
Daniele Grattarola
A dual benchmarking study of visual forgery and visual forensics techniques

A dual benchmarking study of facial forgery and facial forensics In recent years, visual forgery has reached a level of sophistication that humans can

8 Jul 06, 2022
A light weight data augmentation tool for training CNNs and Viola Jones detectors

hey-daug A light weight data augmentation tool for training CNNs and Viola Jones detectors (Haar Cascades). This tool inflates your data by up to six

Jaiyam Sharma 2 Nov 23, 2019
Omnidirectional Scene Text Detection with Sequential-free Box Discretization (IJCAI 2019). Including competition model, online demo, etc.

Box_Discretization_Network This repository is built on the pytorch [maskrcnn_benchmark]. The method is the foundation of our ReCTs-competition method

Yuliang Liu 266 Nov 24, 2022
Benchmarking the robustness of Spatial-Temporal Models

Benchmarking the robustness of Spatial-Temporal Models This repositery contains the code for the paper Benchmarking the Robustness of Spatial-Temporal

Yi Chenyu Ian 15 Dec 16, 2022
RM Operation can equivalently convert ResNet to VGG, which is better for pruning; and can help RepVGG perform better when the depth is large.

RMNet: Equivalently Removing Residual Connection from Networks This repository is the official implementation of "RMNet: Equivalently Removing Residua

184 Jan 04, 2023
CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensors

CZU-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and 10 wearable inertial sensors   In order to facilitate the res

yujmo 11 Dec 12, 2022
A flexible submap-based framework towards spatio-temporally consistent volumetric mapping and scene understanding.

Panoptic Mapping This package contains panoptic_mapping, a general framework for semantic volumetric mapping. We provide, among other, a submap-based

ETHZ ASL 194 Dec 20, 2022
Regularizing Generative Adversarial Networks under Limited Data (CVPR 2021)

Regularizing Generative Adversarial Networks under Limited Data [Project Page][Paper] Implementation for our GAN regularization method. The proposed r

Google 148 Nov 18, 2022
Molecular Sets (MOSES): A Benchmarking Platform for Molecular Generation Models

Molecular Sets (MOSES): A benchmarking platform for molecular generation models Deep generative models are rapidly becoming popular for the discovery

MOSES 656 Dec 29, 2022
This is the official released code for our paper, The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos

The-Emergence-of-Objectness This is the official released code for our paper, The Emergence of Objectness: Learning Zero-Shot Segmentation from Videos

44 Oct 08, 2022
This repository contains the source code of an efficient 1D probabilistic model for music time analysis proposed in ICASSP2022 venue.

Jump Reward Inference for 1D Music Rhythmic State Spaces An implementation of the probablistic jump reward inference model for music rhythmic informat

Mojtaba Heydari 25 Dec 16, 2022
Experimenting with computer vision techniques to generate annotated image datasets from gameplay recordings automatically.

Experimenting with computer vision techniques to generate annotated image datasets from gameplay recordings automatically. The collected data will then be used to train a deep neural network that can

Martin Valchev 3 Apr 24, 2022
Unsupervised Pre-training for Person Re-identification (LUPerson)

LUPerson Unsupervised Pre-training for Person Re-identification (LUPerson). The repository is for our CVPR2021 paper Unsupervised Pre-training for Per

143 Dec 24, 2022
K-FACE Analysis Project on Pytorch

Installation Setup with Conda # create a new environment conda create --name insightKface python=3.7 # or over conda activate insightKface #install t

Jung Jun Uk 7 Nov 10, 2022
Skipgram Negative Sampling in PyTorch

PyTorch SGNS Word2Vec's SkipGramNegativeSampling in Python. Yet another but quite general negative sampling loss implemented in PyTorch. It can be use

Jamie J. Seol 287 Dec 14, 2022
Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

Text-AutoAugment (TAA) This repository contains the code for our paper Text AutoAugment: Learning Compositional Augmentation Policy for Text Classific

LancoPKU 105 Jan 03, 2023
PyTorch code for: Learning to Generate Grounded Visual Captions without Localization Supervision

Learning to Generate Grounded Visual Captions without Localization Supervision This is the PyTorch implementation of our paper: Learning to Generate G

Chih-Yao Ma 41 Nov 17, 2022
Human4D Dataset tools for processing and visualization

HUMAN4D: A Human-Centric Multimodal Dataset for Motions & Immersive Media HUMAN4D constitutes a large and multimodal 4D dataset that contains a variet

tofis 15 Nov 09, 2022
meProp: Sparsified Back Propagation for Accelerated Deep Learning

meProp The codes were used for the paper meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting (ICML 2017) [pdf]

LancoPKU 107 Nov 18, 2022
This repository is an implementation of paper : Improving the Training of Graph Neural Networks with Consistency Regularization

CRGNN Paper : Improving the Training of Graph Neural Networks with Consistency Regularization Environments Implementing environment: GeForce RTX™ 3090

THUDM 28 Dec 09, 2022