sota.md

List of State-of-the-art methods and link to the code

Pre-processing

• FairOT
  Laclau et al., All All of the Fairness for Edge Prediction with Optimal Transport (2021)
  Code [here]

• FairDrop
  Spinelli et al., FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning (2021)
  Code [here]

In-processing

• FairWalk
  Rahman et al., Fairwalk: Towards Fair Graph Embedding (2019)
  Code [here]

• CrossWalk
  Khajehnejad et al., CrossWalk: Fairness-enhanced Node Representation Learning (2021)
  Code [here]

• DeBayes Buyl et al., DeBayes: a Bayesian method for debiasing network embeddings (2020)
  Code [here]

• FIPR Buyl et al., The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizer (2021)
  Code [here]

Adversarial approaches

• CFC
  Bose et al., Compositional fairness constraints for graph embeddings (2019)
  Code [here]

• FLIP
  Masrour et al., Bursting the Filter Bubble: Fairness-Aware Network Link Prediction (2020)
  Code [here]

• DKGE
  Fisher et al., Debiasing knowledge graph embeddings (2020)
  Code not available

Graph-neural networks

• MONET
  Palowitch et al., MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit (2020)
  Code [here]

• FairAdj
  Li et al., On Dyadic Fairness: Exploring and Mitigating Bias in Graph Connections (2020)
  Code [here]

• FairGNN
  Enyan et al., Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information (2021)
  Code [here]

• NIFTY

Other approaches

• INFORM
  Kang et al., InFoRM: Individual Fairness on Graph Mining (2020)
  Code [here]