Compositional Fairness Constraints for Graph Embeddings

Avishek Bose, William Hamilton
Proceedings of the 36th International Conference on Machine Learning, PMLR 97:715-724, 2019.

Abstract

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.

Cite this Paper


BibTeX
@InProceedings{pmlr-v97-bose19a, title = {Compositional Fairness Constraints for Graph Embeddings}, author = {Bose, Avishek and Hamilton, William}, booktitle = {Proceedings of the 36th International Conference on Machine Learning}, pages = {715--724}, year = {2019}, editor = {Chaudhuri, Kamalika and Salakhutdinov, Ruslan}, volume = {97}, series = {Proceedings of Machine Learning Research}, month = {09--15 Jun}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v97/bose19a/bose19a.pdf}, url = {https://proceedings.mlr.press/v97/bose19a.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T Compositional Fairness Constraints for Graph Embeddings %A Avishek Bose %A William Hamilton %B Proceedings of the 36th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Ruslan Salakhutdinov %F pmlr-v97-bose19a %I PMLR %P 715--724 %U https://proceedings.mlr.press/v97/bose19a.html %V 97 %X 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.
APA
Bose, A. & Hamilton, W.. (2019). Compositional Fairness Constraints for Graph Embeddings. Proceedings of the 36th International Conference on Machine Learning, in Proceedings of Machine Learning Research 97:715-724 Available from https://proceedings.mlr.press/v97/bose19a.html.

Related Material