Deep Graph-Level Clustering Using Pseudo-Label-Guided Mutual Information Maximization Network
In this work, we study the problem of partitioning a set of graphs into different groups such that the graphs in the same group are similar while the graphs in different groups are dissimilar. This problem was rarely studied previously, although there have been a lot of work on node clustering and graph classification. The problem is challenging because it is difficult to measure the similarity or distance between graphs. One feasible approach is using graph kernels to compute a similarity matrix for the graphs and then performing spectral clustering, but the effectiveness of existing graph kernels in measuring the similarity between graphs is very limited. To solve the problem, we propose a novel method called Deep Graph-Level Clustering (DGLC). DGLC utilizes a graph isomorphism network to learn graph-level representations by maximizing the mutual information between the representations of entire graphs and substructures, under the regularization of a clustering module that ensures discriminative representations via pseudo labels. DGLC achieves graph-level representation learning and graph-level clustering in an end-to-end manner. The experimental results on six benchmark datasets of graphs show that our DGLC has state-of-the-art performance in comparison to many baselines.
Code (0)
등록된 구현이 없습니다.
Tasks
ClusteringGraph ClassificationNode ClusteringPseudo LabelRepresentation LearningSimilar Papers 제목 키워드 기반
Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identification
Unsupervised person re-identification (ReID) aims at learning discriminative identity features for person retrieval without any annotations. Recent advances accomplish this task by leveraging clustering-based pseudo labe…
ClusteringPerson Re-IdentificationPerson RetrievalPseudo Label+2Exploiting Sample Uncertainty for Domain Adaptive Person Re-Identification
Many unsupervised domain adaptive (UDA) person re-identification (ReID) approaches combine clustering-based pseudo-label prediction with feature fine-tuning. However, because of domain gap, the pseudo-labels are not alwa…
ClusteringDomain Adaptive Person Re-IdentificationPerson Re-IdentificationPseudo Label+2SPICE: Semantic Pseudo-labeling for Image Clustering
The similarity among samples and the discrepancy between clusters are two crucial aspects of image clustering. However, current deep clustering methods suffer from the inaccurate estimation of either feature similarity o…
ClusteringContrastive LearningDeep ClusteringImage Clustering+3Plug-and-Play Pseudo Label Correction Network for Unsupervised Person Re-identification
Clustering-based methods, which alternate between the generation of pseudo labels and the optimization of the feature extraction network, play a dominant role in both unsupervised learning (USL) and unsupervised domain a…
ClusteringPerson Re-IdentificationPseudo LabelUnsupervised Person Re-IdentificationAn Adaptor for Triggering Semi-Supervised Learning to Out-of-Box Serve Deep Image Clustering
Recently, some works integrate SSL techniques into deep clustering frameworks to enhance image clustering performance. However, they all need pretraining, clustering learning, or a trained clustering model as prerequisit…
Image ClusteringDeep Clustering