Compositional Fairness Constraints for Graph Embeddings

By Avishek Joey Bose, William L. Hamilton. 2019

301 citations recorded by the source corpus.

Learning high-quality node embeddings is a key building block for machine learning models that operate on graph data, such as social networks and recommender systems. However, existing graph embedding techniques are unable to cope with fairness constraints, e.g., ensuring that the learned representations do not correlate with certain attributes, such as age or gender. Here, we introduce an adversarial framework to enforce fairness constraints on graph embeddings. Our approach is compositional---meaning that it can flexibly accommodate different combinations of fairness constraints during inference. For instance, in the context of social recommendations, our framework would allow one user to request that their recommendations are invariant to both their age and gender, while also allowing another user to request invariance to just their age. Experiments on standard knowledge graph and recommender system benchmarks highlight the utility of our proposed framework.

Subfields: Artificial Intelligence, Safety Research, Safety, Robustness & Interpretability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Safety Research

In Safety, Robustness & Interpretability

Citations in the corpus

Does Gender Matter? Towards Fairness in Dialogue Systems (2019, background): “Existing works attempt to address the issue of fairness in various Machine Learning (ML) tasks such as classiﬁcation [28, 29], regression [30], graph embedding [31] and clustering [32, 33].”
A Survey on Bias and Fairness in Machine Learning (2019, methodology): “Fair methods in domains similar to community detection are also proposed, such as graph embedding [21] and clustering [7, 30].”
Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition (2019, background): “From representation learning (Moyer et al. 2018) to graph embedding (Bose and Hamilton 2019) to community detection (Mehrabi et al. 2019a) and clustering (Backurs et al. 2019), researchers have studied biases in these areas and tried to address them by pointing out the observed problems and…”
Flexibly Fair Representation Learning by Disentanglement (2019, background): “Bose & Hamilton (2018) proposed a compositional fair representation of graph-structured data.”
Algorithmic Fairness (2020, background): “are network structures that define relationships between providers and between users (such as in [20]).”
A Survey on the Fairness of Recommender Systems (2022, methodology): “A fair representation should be independent of fairness-related attributes, so some work [9, 96] trains a classiier to predict fairness-related attributes of users and items according to their representations.”
A Review on Fairness in Machine Learning (2022, background): “Future work may also focus on fairness in systems where there are network structures that define relationships between providers and between users (e.g., [28]).”
Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information (2020, methodology): “• Debias-e : Similar to the ALFR-e, we also add the deepwalk embeddings • FCGE [4]: FCGE is proposed to learn fair node embeddings in ALFR and ALFR-e are trained with features of all the users V , labels of V 𝐿 , and the sensitive attributes of V 𝑆 is on contrary with our setting that V 𝐿 V 𝑆 Th”
A Survey on Heterogeneous Graph Embedding: Methods, Techniques, Applications and Sources (2020, unknown): “, age or gender, which may amplify the societal stereotypes in the prediction results [151], [152].”
Machine Learning on Graphs: A Model and Comprehensive Taxonomy (2020, background): “The most popular technique for adding fairness constraints to models relies on using adversarial learning to debias the model’s predictions relative to the sensitive feature(s), and can be extended to graph representation learning [14].”
A Survey of Graph Neural Networks for Recommender Systems: Challenges, Methods, and Directions (2021, methodology): “Network Design Achieving Fairness Fairwalk [147] Node2vec (GE) learning fair graph embeddings by sampling CFCGE [10] Invariant GE learning fair graph embeddings by adversarial learning FairGo [195] HetGNN(GNN) learning fair graph embeddings by adversarial learning FairGNN [36] GraphSage(GNN) learnin”
Bias and Debias in Recommender System: A Survey and Future Directions (2020, background): “[133] extended the ALFR framework by enforcing compositional fairness constraints on graph embeddings for multiple sensitive attributes, which are evaluated in the scenarios of movie and friendship recommendation.”