The KL-Divergence Between a Graph Model and its Fair I-Projection as a Fairness Regularizer.
Maarten BuylTijl De BiePublished in: ECML/PKDD (2) (2021)
Keyphrases
- graph model
- kl divergence
- kullback leibler divergence
- information theoretic
- mahalanobis distance
- gaussian mixture
- bipartite graph
- gaussian distribution
- semi supervised
- probability density
- mutual information
- exponential family
- posterior distribution
- graph structure
- similarity measure
- high dimensional
- weighted graph
- euclidean distance
- clustering method
- nearest neighbor
- density estimation
- probability density function
- text mining
- feature vectors
- pairwise