predictions.md

Prediction Explanations

The listing conforms the taxonomy introduced in this [survey paper].

Perturbation Based Methods

• MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networks (IJCNN 2021)

  • Danilo Numeroso, Davide Bacciu
  • [Paper]
  • [Reference Code]

• Model agnostic generation of counterfactual explanations for molecules (ChemRxiv 2021)

  • Geemi P Wellawatte, Aditi Seshadri , Andrew D White
  • [Paper]
  • [Reference Code]

• Generative Causal Explanations for Graph Neural Networks (ICML 2021)

  • Wanyu Lin, Hao Lan, Baochun Li
  • [Paper]
  • [Reference Code]

• CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networks (Arxiv 2021)

  • Ana Lucic, Maartje ter Hoeve, Gabriele Tolomei, Maarten de Rijke, Fabrizio Silvestri
  • [Paper]
  • [Reference Code]

• On Explainability of Graph Neural Networks via Subgraph Explorations (ICML 2021)

  • Hao Yuan, Haiyang Yu, Jie Wang, Kang Li, Shuiwang Ji
  • [Paper]
  • [Reference Code]

• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking (ICLR 2021)

  • Michael Sejr Schlichtkrull, Nicola De Cao, Ivan Titov
  • [Paper]
  • [Reference Code]

• Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification (CD-MAKE 2020)

  • Xiaoxiao Li, Joao Saude
  • [Paper]

• Contrastive Graph Neural Network Explanation (ICML 2020)

  • Lukas Faber, Amin K. Moghaddam, Roger Wattenhofer
  • [Paper]
  • [Reference Code]

• Hard Masking for Explaining Graph Neural Networks (OpenReview 2020)

  • Thorben Funke, Megha Khosla, Avishek Anand
  • [Paper]

• Graph Neural Networks Including Sparse Interpretability (Arxiv 2020)

  • Chris Lin, Gerald J. Sun, Krishna C. Bulusu, Jonathan R. Dry, Marylens Hernandez
  • [Paper]

• Causal Screening to Interpret Graph Neural Networks (OpenReview 2020)

  • Xiang Wang, Yingxin Wu, An Zhang, Xiangnan He, Tat-seng Chua
  • [Paper]

• XGNN: Towards Model-Level Explanations of Graph Neural Networks (KDD 2020)

  • Hao Yuan, Jiliang Tang, Xia Hu, Shuiwang Ji
  • [Paper]
  • [Code]

• Parameterized Explainer for Graph Neural Network (NeurIPS 2020)

  • Dongsheng Luo, Wei Cheng, Dongkuan Xu, Wenchao Yu, Bo Zong, Haifeng Chen, Xiang Zhang
  • [Paper]
  • [Reference Code]
  • [Code]
  • [Code]

• GNNExplainer: Generating Explanations for Graph Neural Networks (NeurIPS 2019)

  • Rex Ying, Dylan Bourgeois, Jiaxuan You, Marinka Zitnik, Jure Leskovec
  • [Paper]
  • [Reference Code]

Surrogate Model Based Methods

• GraphSVX: Shapley Value Explanations for Graph Neural Networks (CORR 2021)

  • Alexandre Duval, Fragkiskos D. Malliaros
  • [Paper]
  • [Reference Code]

• GraphLIME:Local Interpretable Model Explanations for Graph Neural Networks (CORR 2020)

  • Qiang Huang, Makoto Yamada, Yuan Tian, Dinesh Singh, Dawei Yin, Yi Chang
  • [Paper]
  • [Reference Code]

• RelEX: A Model-Agnostic Relational Model Explainer (CORR 2020)

  • Yue Zhang, David Defazio, Arti Ramesh
  • [Paper]

• PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkrk (CORR 2020)

  • Minh N. Vu, My T. Thai
  • [Paper]

Decomposition and Gradient Integration Based Methods

• Explainability Techniques for Graph Convolutional Networks (ICML 2019)

  • Federico Baldassarre, Hossein Azizpour
  • [Paper]
  • [Code]

• Layerwise Relevance Visualization in Convolutional Text Graph Classifiers (WS 2019)

  • Robert Schwarzenberg, Marc Hübner, David Harbecke, Christoph Alt, Leonhard Hennig
  • [Paper]
  • [Code]

• Higher-Order Explanations of Graph Neural Networks via Relevant Walks (Arxiv 2020)

  • Thomas Schnake, Oliver Eberle, Jonas Lederer, Shinichi Nakajima, Kristof T. Schütt, Klaus-Robert Müller, Grégoire Montavon
  • [Paper]

• GCN-LRP Explanation: Exploring Latent Attention of Graph Convolutional Networks (IJCNN 2020)

  • Jinlong Hu, Tenghui Li, Shoubin Dong
  • [Paper]
  • [Code]

• Explainability Methods for Graph Convolutional Neural Networks (CVPR 2019)

  • Phillip E. Pope, Soheil Kolouri, Mohammad Rostami, Charles E. Martin, Heiko Hoffmann
  • [Paper]
  • [Code]

• Evaluating Attribution for Graph Neural Networks (NeurIPS 2020)

  • Sanchez-Lengeling Benjamin, Wei Jennifer, Lee Brian, Reif Emily, Wang Peter, Qian Wesley, McCloskey Kevin, Colwell Lucy, Wiltschko Alexander
  • [Paper]
  • [Code]

Concept Based Methods

• GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks (ICML Workshop 2021)
  • Lucie Charlotte Magister, Dmitry Kazhdan, Vikash Singh, Pietro Liò
  • [Paper]
  • [Code]