LoadingByte / are-gnn-defenses-robustLinks
Adaptive evaluation reveals that most examined adversarial defenses for GNNs show no or only marginal improvement in robustness. (NeurIPS 2022)
☆29Updated 2 years ago
Alternatives and similar repositories for are-gnn-defenses-robust
Users that are interested in are-gnn-defenses-robust are comparing it to the libraries listed below
Sorting:
- This repository contains the official implementation of the paper "Robustness of Graph Neural Networks at Scale" (NeurIPS, 2021).☆30Updated 2 years ago
- [ICLR 2022] Understanding and Improving Graph Injection Attack by Promoting Unnoticeability☆37Updated last year
- Graph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for evaluating the adversarial robustness of Graph M…☆95Updated last year
- Open source code for paper "EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks".☆27Updated 3 years ago
- The official implementation for ICLR22 paper "Handling Distribution Shifts on Graphs: An Invariance Perspective"☆92Updated 2 years ago
- [WWW 2021 GLB] New Benchmarks for Learning on Non-Homophilous Graphs☆114Updated 3 years ago
- A graph reliability toolbox based on PyTorch and PyTorch Geometric (PyG).☆85Updated 10 months ago
- [ICLR'23] Implementation of "Empowering Graph Representation Learning with Test-Time Graph Transformation"☆60Updated 2 years ago
- [ICLR'22] [KDD'22] [IJCAI'24] Implementation of "Graph Condensation for Graph Neural Networks"☆140Updated 9 months ago
- source code of KDD 2022 paper "Reliable Representations Make A Stronger Defender: Unsupervised Structure Refinement for Robust GNN".☆28Updated last year
- ☆18Updated 3 years ago
- G-NIA model from "Single Node Injection Attack against Graph Neural Networks" (CIKM 2021)☆29Updated 3 years ago
- [ICLR 2023] "Graph Domain Adaptation via Theory-Grounded Spectral Regularization" by Yuning You, Tianlong Chen, Zhangyang Wang, Yang Shen☆23Updated 2 years ago
- How Powerful are Spectral Graph Neural Networks☆73Updated 2 years ago
- Pytorch implementation of gnn meta attack (mettack). Paper title: Adversarial Attacks on Graph Neural Networks via Meta Learning.☆21Updated 4 years ago
- Codebase used to generate the results for NeurIPS23 "Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directi…☆11Updated last year
- [ICML2022] G-Mixup: Graph Data Augmentation for Graph Classification☆106Updated last year
- Open-source datasets for paper "Fairness in Graph Mining: A Survey".☆18Updated 2 years ago
- ICML 2022, Finding Global Homophily in Graph Neural Networks When Meeting Heterophily☆44Updated 3 years ago
- Paper List for Fair Graph Learning (FairGL).☆140Updated 11 months ago
- ☆29Updated 3 years ago
- An official PyTorch implementation of "Towards Robust Graph Neural Networks for Noisy Graphs with Sparse Labels" (WSDM 2022))☆33Updated 3 years ago
- [AAAI'23] Beyond Smoothing: Unsupervised Graph Representation Learning with Edge Heterophily Discriminating☆52Updated 2 years ago
- Defending graph neural networks against adversarial attacks (NeurIPS 2020)☆71Updated 2 years ago
- [NeurIPS 2022] Learning Causally Invariant Representations for Out-of-Distribution Generalization on Graphs☆116Updated 2 years ago
- PyTorch implementation of BGRL (https://arxiv.org/abs/2102.06514)☆81Updated 2 years ago
- Graph Information Bottleneck (GIB) for learning minimal sufficient structural and feature information using GNNs☆137Updated 2 years ago
- A curated list of resources for OOD detection with graph data.☆19Updated last year
- Papers about developing DL methods on disassortative graphs☆48Updated 3 years ago
- Official implementation of our FLAG paper (CVPR2022)☆145Updated 3 years ago