dc.contributor.author | Bianchi, Filippo Maria | |
dc.contributor.author | Grattarola, Daniele | |
dc.contributor.author | Alippi, Cesare | |
dc.date.accessioned | 2020-09-10T10:36:53Z | |
dc.date.available | 2020-09-10T10:36:53Z | |
dc.date.issued | 2020 | |
dc.description.abstract | Spectral clustering (SC) is a popular clustering
technique to find strongly connected communities on a graph. SC can be used in Graph Neural Networks (GNNs) to implement pooling operations that aggregate nodes belonging to the
same cluster. However, the eigendecomposition
of the Laplacian is expensive and, since clustering results are graph-specific, pooling methods
based on SC must perform a new optimization
for each new sample. In this paper, we propose
a graph clustering approach that addresses these
limitations of SC. We formulate a continuous relaxation of the normalized minCUT problem and
train a GNN to compute cluster assignments that
minimize this objective. Our GNN-based implementation is differentiable, does not require to
compute the spectral decomposition, and learns
a clustering function that can be quickly evaluated on out-of-sample graphs. From the proposed
clustering method, we design a graph pooling operator that overcomes some important limitations
of state-of-the-art graph pooling techniques and
achieves the best performance in several supervised and unsupervised tasks. | en_US |
dc.description | Source at <a href=http://proceedings.mlr.press/>http://proceedings.mlr.press/. </a> | en_US |
dc.identifier.citation | Bianchi FM, Grattarola, Alippi C. (2020). Spectral clustering with graph neural networks for graph pooling. ACM Digital Library. Proceedings of Machine Learning Research (PMLR)(119) | en_US |
dc.identifier.cristinID | FRIDAID 1826429 | |
dc.identifier.uri | https://hdl.handle.net/10037/19303 | |
dc.language.iso | eng | en_US |
dc.publisher | PMLR | en_US |
dc.relation.ispartofseries | Proceedings of Machine Learning Research (PMLR) ; 119 (2020) | en_US |
dc.rights.accessRights | openAccess | en_US |
dc.rights.holder | Copyright 2020 The Author(s) | en_US |
dc.subject | VDP::Mathematics and natural science: 400::Mathematics: 410 | en_US |
dc.subject | VDP::Matematikk og Naturvitenskap: 400::Matematikk: 410 | en_US |
dc.title | Spectral clustering with graph neural networks for graph pooling | en_US |
dc.type.version | publishedVersion | en_US |
dc.type | Conference object | en_US |
dc.type | Konferansebidrag | en_US |