• Corpus ID: 239998101

Unbiased Graph Embedding with Biased Graph Observations

  title={Unbiased Graph Embedding with Biased Graph Observations},
  author={Nan Wang and Lu Lin and Jundong Li and Hongning Wang},
Graph embedding techniques have been increasingly employed in real-world machine learning tasks on graph-structured data, such as social recommendations and protein structure modeling. Since the generation of a graph is inevitably affected by some sensitive node attributes (such as gender and age of users in a social network), the learned graph representations can inherit such sensitive information and introduce undesirable biases in downstream tasks. Most existing works on debiasing graph… 

Figures and Tables from this paper

Implications of Topological Imbalance for Representation Learning on Biomedical Knowledge Graphs
Focusing on target discovery, it is shown how knowledge graph embedding models can be affected by this structural imbalance, resulting in densely connected entities being highly ranked no matter the context, creating a lack of specificity in predictions.


MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit
The Metadata-Orthogonal Node Embedding Training (MONET) unit is introduced, a general model for debiasing embeddings of nodes in a graph that can learn and remove the effect of arbitrary covariates in tasks such as preventing the leakage of political party affiliation in a blog network, and thwarting the gaming of embedding-based recommendation systems.
Graph Embedding Techniques, Applications, and Performance: A Survey
Compositional Fairness Constraints for Graph Embeddings
This work introduces an adversarial framework to enforce fairness constraints on graph embeddings and its approach is compositional---meaning that it can flexibly accommodate different combinations of fairness constraints during inference.
LINE: Large-scale Information Network Embedding
A novel network embedding method called the ``LINE,'' which is suitable for arbitrary types of information networks: undirected, directed, and/or weighted, and optimizes a carefully designed objective function that preserves both the local and global network structures.
Attributed graph models: modeling network structure with correlated attributes
This work presents the Attributed Graph Model (AGM) framework, a framework to jointly model network structure and vertex attributes, and demonstrates the efficiency and accuracy of this framework on two large real-world networks.
Fairwalk: Towards Fair Graph Embedding
This paper proposes a fairness-aware embedding method, namely Fairwalk, which extends node2vec, and demonstrates that Fairwalk reduces bias under multiple fairness metrics while still preserving the utility.
node2vec: Scalable Feature Learning for Networks
In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.
Learning Fair Graph Neural Networks with Limited and Private Sensitive Attribute Information
The proposed FairGNN is proposed to eliminate the bias of GNNs whilst maintaining high node classification accuracy by leveraging graph structures and limited sensitive information, and is extended to NT-FairGNN which can achieve both fairness and privacy on sensitive attributes by using limited and private sensitive attributes.
Real-time social recommendation based on graph embedding and temporal context
A novel dynamic graph-based embedding (DGE) model for social recommendation which is capable of recommending relevant users and interested items and its advantages over other state-of-the-art methods are shown.
DeepWalk: online learning of social representations
DeepWalk is an online learning algorithm which builds useful incremental results, and is trivially parallelizable, which make it suitable for a broad class of real world applications such as network classification, and anomaly detection.