Document detail
ID
oai:HAL:hal-04105310v3
Topic
clustering differentiable clustering deepclustering perturbed optimizer perturbed optimization randomized smoothing trees spanning trees forests spanning forests kruskal kruskal's deep learning machine learning [INFO.INFO-AI]Computer Science [cs... [STAT.ML]Statistics [stat]/Machine...Author
Stewart, Lawrence Bach, Francis, S López, Felipe Llinares Berthet, QuentinLangue
enEditor
HAL CCSD
Category
technologies: computer sciences
Year
2023
listing date
12/15/2023
Keywords
learning data clusteringAbstract
International audience; We introduce a differentiable clustering method based on stochastic perturbations of minimum-weight spanning forests.
This allows us to include clustering in end-to-end trainable pipelines, with efficient gradients.
We show that our method performs well even in difficult settings, such as data sets with high noise and challenging geometries.
We also formulate an ad hoc loss to efficiently learn from partial clustering data using this operation.
We demonstrate its performance on several data sets for supervised and semi-supervised tasks.
Stewart, Lawrence,Bach, Francis, S,López, Felipe Llinares,Berthet, Quentin, 2023, Differentiable Clustering with Perturbed Spanning Forests, HAL CCSD
xNeuSM: Explainable Neural Subgraph Matching with Graph Learnable Multi-hop Attention Networks
science neural graph attention
