Matches in SemOpenAlex for { <https://semopenalex.org/work/W4312106962> ?p ?o ?g. }
Showing items 1 to 63 of
63
with 100 items per page.
- W4312106962 endingPage "13" @default.
- W4312106962 startingPage "1" @default.
- W4312106962 abstract "Since the representative capacity of graph-based clustering methods is usually limited by the graph constructed on the original features, it is attractive to find whether graph neural networks (GNNs) can be applied to augment the capacity. The core problems mainly come from two aspects: (1) the graph is unavailable in the most clustering scenes so that how to construct high-quality graphs on the non-graph data is usually the most important part; (2) given n samples, the graph-based clustering methods usually consume at least $mathcal O(n^2)$ time to build graphs and the graph convolution requires nearly $mathcal O(n^2)$ for a dense graph and $mathcal O(|mathcal{E}|)$ for a sparse one with $|mathcal{E}|$ edges. Accordingly, both graph-based clustering and GNNs suffer from the severe inefficiency problem. To tackle these problems, we propose a novel clustering method, AnchorGAE, with the self-supervised estimation of graph and efficient graph convolution. We first show how to convert a non-graph dataset into a graph dataset, by introducing the generative graph model and anchors. We then show that the constructed bipartite graph can reduce the computational complexity of graph convolution from $mathcal O(n^2)$ and $mathcal O(|mathcal{E}|)$ to $mathcal O(n)$. The succeeding steps for clustering can be easily designed as $mathcal O(n)$ operations. Interestingly, the anchors naturally lead to siamese architecture with the help of the Markov process. Furthermore, the estimated bipartite graph is updated dynamically according to the features extracted by GNN, to promote the quality of the graph. However, we theoretically prove that the self-supervised paradigm frequently results in a collapse that often occurs after 2-3 update iterations in experiments, especially when the model is well-trained. A specific strategy is accordingly designed to prevent the collapse." @default.
- W4312106962 created "2023-01-04" @default.
- W4312106962 creator A5004015448 @default.
- W4312106962 creator A5042869276 @default.
- W4312106962 creator A5065037360 @default.
- W4312106962 creator A5068918243 @default.
- W4312106962 date "2022-01-01" @default.
- W4312106962 modified "2023-10-16" @default.
- W4312106962 title "Non-Graph Data Clustering via $mathcal {O}(n)$ Bipartite Graph Convolution" @default.
- W4312106962 doi "https://doi.org/10.1109/tpami.2022.3231470" @default.
- W4312106962 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37015533" @default.
- W4312106962 hasPublicationYear "2022" @default.
- W4312106962 type Work @default.
- W4312106962 citedByCount "0" @default.
- W4312106962 crossrefType "journal-article" @default.
- W4312106962 hasAuthorship W4312106962A5004015448 @default.
- W4312106962 hasAuthorship W4312106962A5042869276 @default.
- W4312106962 hasAuthorship W4312106962A5065037360 @default.
- W4312106962 hasAuthorship W4312106962A5068918243 @default.
- W4312106962 hasBestOaLocation W43121069622 @default.
- W4312106962 hasConcept C11413529 @default.
- W4312106962 hasConcept C114614502 @default.
- W4312106962 hasConcept C118615104 @default.
- W4312106962 hasConcept C132525143 @default.
- W4312106962 hasConcept C154945302 @default.
- W4312106962 hasConcept C197657726 @default.
- W4312106962 hasConcept C203776342 @default.
- W4312106962 hasConcept C22149727 @default.
- W4312106962 hasConcept C33923547 @default.
- W4312106962 hasConcept C41008148 @default.
- W4312106962 hasConcept C73555534 @default.
- W4312106962 hasConceptScore W4312106962C11413529 @default.
- W4312106962 hasConceptScore W4312106962C114614502 @default.
- W4312106962 hasConceptScore W4312106962C118615104 @default.
- W4312106962 hasConceptScore W4312106962C132525143 @default.
- W4312106962 hasConceptScore W4312106962C154945302 @default.
- W4312106962 hasConceptScore W4312106962C197657726 @default.
- W4312106962 hasConceptScore W4312106962C203776342 @default.
- W4312106962 hasConceptScore W4312106962C22149727 @default.
- W4312106962 hasConceptScore W4312106962C33923547 @default.
- W4312106962 hasConceptScore W4312106962C41008148 @default.
- W4312106962 hasConceptScore W4312106962C73555534 @default.
- W4312106962 hasFunder F4320321001 @default.
- W4312106962 hasLocation W43121069621 @default.
- W4312106962 hasLocation W43121069622 @default.
- W4312106962 hasLocation W43121069623 @default.
- W4312106962 hasOpenAccess W4312106962 @default.
- W4312106962 hasPrimaryLocation W43121069621 @default.
- W4312106962 hasRelatedWork W1500336836 @default.
- W4312106962 hasRelatedWork W2031266950 @default.
- W4312106962 hasRelatedWork W2040232932 @default.
- W4312106962 hasRelatedWork W2963671725 @default.
- W4312106962 hasRelatedWork W3029390739 @default.
- W4312106962 hasRelatedWork W3104688290 @default.
- W4312106962 hasRelatedWork W4243953177 @default.
- W4312106962 hasRelatedWork W4246687640 @default.
- W4312106962 hasRelatedWork W4253608841 @default.
- W4312106962 hasRelatedWork W4287773996 @default.
- W4312106962 isParatext "false" @default.
- W4312106962 isRetracted "false" @default.
- W4312106962 workType "article" @default.