MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unit

by   John Palowitch, et al.

Are Graph Neural Networks (GNNs) fair? In many real world graphs, the formation of edges is related to certain node attributes (e.g. gender, community, reputation). In this case, standard GNNs using these edges will be biased by this information, as it is encoded in the structure of the adjacency matrix itself. In this paper, we show that when metadata is correlated with the formation of node neighborhoods, unsupervised node embedding dimensions learn this metadata. This bias implies an inability to control for important covariates in real-world applications, such as recommendation systems. To solve these issues, we introduce the Metadata-Orthogonal Node Embedding Training (MONET) unit, a general model for debiasing embeddings of nodes in a graph. MONET achieves this by ensuring that the node embeddings are trained on a hyperplane orthogonal to that of the node metadata. This effectively organizes unstructured embedding dimensions into an interpretable topology-only, metadata-only division with no linear interactions. We illustrate the effectiveness of MONET though our experiments on a variety of real world graphs, which shows that our method 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.


page 1

page 2

page 3

page 4


Tripartite Heterogeneous Graph Propagation for Large-scale Social Recommendation

Graph Neural Networks (GNNs) have been emerging as a promising method fo...

PersonaSAGE: A Multi-Persona Graph Neural Network

Graph Neural Networks (GNNs) have become increasingly important in recen...

IM-META: Influence Maximization Using Node Metadata in Networks With Unknown Topology

In real-world applications of influence maximization (IM), the network s...

Position-based Hash Embeddings For Scaling Graph Neural Networks

Graph Neural Networks (GNNs) bring the power of deep representation lear...

Node metadata can produce predictability transitions in network inference problems

Network inference is the process of learning the properties of complex n...

Unsupervised Detection of Contextualized Embedding Bias with Application to Ideology

We propose a fully unsupervised method to detect bias in contextualized ...

A Map Equation with Metadata: Varying the Role of Attributes in Community Detection

As the No Free Lunch theorem formally states [1], algorithms for detecti...

Please sign up or login with your details

Forgot password? Click here to reset