All Projects → rctzeng → EgoCNN

rctzeng / EgoCNN

Licence: MIT license
Code for "Distributed, Egocentric Representations of Graphs for Detecting Critical Structures" (ICML 2019)

Programming Languages

python
139335 projects - #7 most used programming language
Jupyter Notebook
11667 projects
shell
77523 projects

Projects that are alternatives of or similar to EgoCNN

Walk-Transformer
From Random Walks to Transformer for Learning Node Embeddings (ECML-PKDD 2020) (In Pytorch and Tensorflow)
Stars: ✭ 26 (+62.5%)
Mutual labels:  graph-embeddings, graph-neural-networks
BGCN
A Tensorflow implementation of "Bayesian Graph Convolutional Neural Networks" (AAAI 2019).
Stars: ✭ 129 (+706.25%)
Mutual labels:  graph-neural-networks, graph-convolutional-neural-networks
probnmn-clevr
Code for ICML 2019 paper "Probabilistic Neural-symbolic Models for Interpretable Visual Question Answering" [long-oral]
Stars: ✭ 63 (+293.75%)
Mutual labels:  icml, icml-2019
QGNN
Quaternion Graph Neural Networks (ACML 2021) (Pytorch and Tensorflow)
Stars: ✭ 31 (+93.75%)
Mutual labels:  graph-embeddings, graph-neural-networks
Stellargraph
StellarGraph - Machine Learning on Graphs
Stars: ✭ 2,235 (+13868.75%)
Mutual labels:  interpretability, graph-neural-networks
ntds 2019
Material for the EPFL master course "A Network Tour of Data Science", edition 2019.
Stars: ✭ 62 (+287.5%)
Mutual labels:  graph-neural-networks
Pro-GNN
Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"
Stars: ✭ 202 (+1162.5%)
Mutual labels:  graph-neural-networks
grb
Graph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for evaluating the adversarial robustness of Graph Machine Learning.
Stars: ✭ 70 (+337.5%)
Mutual labels:  graph-neural-networks
kernel-mod
NeurIPS 2018. Linear-time model comparison tests.
Stars: ✭ 17 (+6.25%)
Mutual labels:  interpretability
visual-compatibility
Context-Aware Visual Compatibility Prediction (https://arxiv.org/abs/1902.03646)
Stars: ✭ 92 (+475%)
Mutual labels:  graph-neural-networks
DCGCN
Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning (authors' MXNet implementation for the TACL19 paper)
Stars: ✭ 73 (+356.25%)
Mutual labels:  graph-neural-networks
xai-iml-sota
Interesting resources related to Explainable Artificial Intelligence, Interpretable Machine Learning, Interactive Machine Learning, Human in Loop and Visual Analytics.
Stars: ✭ 51 (+218.75%)
Mutual labels:  interpretability
ALPS 2021
XAI Tutorial for the Explainable AI track in the ALPS winter school 2021
Stars: ✭ 55 (+243.75%)
Mutual labels:  interpretability
FedScale
FedScale is a scalable and extensible open-source federated learning (FL) platform.
Stars: ✭ 274 (+1612.5%)
Mutual labels:  icml
GNNLens2
Visualization tool for Graph Neural Networks
Stars: ✭ 155 (+868.75%)
Mutual labels:  graph-neural-networks
SimP-GCN
Implementation of the WSDM 2021 paper "Node Similarity Preserving Graph Convolutional Networks"
Stars: ✭ 43 (+168.75%)
Mutual labels:  graph-neural-networks
demo-routenet
Demo of RouteNet in ACM SIGCOMM'19
Stars: ✭ 79 (+393.75%)
Mutual labels:  graph-neural-networks
awesome-efficient-gnn
Code and resources on scalable and efficient Graph Neural Networks
Stars: ✭ 498 (+3012.5%)
Mutual labels:  graph-neural-networks
SIAN
Code and data for ECML-PKDD paper "Social Influence Attentive Neural Network for Friend-Enhanced Recommendation"
Stars: ✭ 25 (+56.25%)
Mutual labels:  graph-neural-networks
kaggle-champs
Code for the CHAMPS Predicting Molecular Properties Kaggle competition
Stars: ✭ 49 (+206.25%)
Mutual labels:  graph-neural-networks

Ego-CNN

This is the repo for "Distributed, Egocentric Representations of Graphs for Detecting Critical Structures", Ruo-Chun Tzeng, Shan-Hung Wu, In Proceedings of ICML 2019.

In the paper, we proposed Ego-Convolution layer, which keeps the nice properties of Convolution layer to the graph including:

  • detection of location-invariant patterns
  • enlarged receptive fields in multi-layer architecture
  • [most importantly] detection of precise patterns

This enables our Ego-CNN to provide explanation to its prediction when jointly learned with a task. picture

  1. In effect, Ego-CNN with L layers can detect patterns up-to L-hop ego-networks.
  2. By using the existing CNN visualization techniques such as Transposed Convolution or Grad-CAM variants, we can visualize the detected patterns in a specific filter or a specific neuron.
  3. By tying the weight of filter across different layers, our Ego-CNN is regularized to detect self-similar patterns

Dependence

  • Python >= 3.6
  • Tensorflow >= 1.0
  • NetworkX 2.0
  • Numpy >= 1.13, Matplotlib >= 2.1
  • Optparse

To Reproduce Our Result On ICML'19

Step 1. Download and Preprocess Graph Classification Datasets

Execute Command python download_dataset.py to download all the bioinformatic and social network datasets used in the paper.

Step 2. Train Ego-CNN on specified datasets for specified tasks

To reproduce ...

  • Graph Classification Experiments: run ./execute-graph-classification-on-benchmarks.sh
  • Effectiveness of Scale-Free Regularizer: run ./execute-graph-classification-on-benchmarks.sh
  • Visualization on synthetic compounds: run ./execute-graph-classification-on-benchmarks.sh
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].