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.
A tutorial on spectral clustering
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
AdaGraph clusters data using kNN graph topology and pairs with the new Graph-SCOPE validity index, reporting strong ARI and correct k selection on synthetic high-dimensional benchmarks plus three scientific applications.
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.
-
AdaGraph: A Graph-Native Clustering Algorithm That Overcomes the Curse of Dimensionality and Enables Scientific Discovery
AdaGraph clusters data using kNN graph topology and pairs with the new Graph-SCOPE validity index, reporting strong ARI and correct k selection on synthetic high-dimensional benchmarks plus three scientific applications.