DFNMF is a deep nonnegative tri-factorization model for graphs that directly optimizes cluster assignments using a tunable soft fairness regularizer to achieve better group balance at comparable modularity than prior methods.
Individual fairness for graph neural networks: A ranking based approach
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
A Deep Latent Factor Graph Clustering with Fairness-Utility Trade-off Perspective
DFNMF is a deep nonnegative tri-factorization model for graphs that directly optimizes cluster assignments using a tunable soft fairness regularizer to achieve better group balance at comparable modularity than prior methods.