Semi-Supervised Learning With Graph Learning-Convolutional Networks

Jiang, Bo; Zhang, Ziyan; Lin, Doudou; Tang, Jin; Luo, Bin

doi:10.1109/cvpr.2019.01157

Cited by 278 publications

(138 citation statements)

References 8 publications

Supporting

Mentioning

138

Contrasting

Order By: Relevance

“…Aiming to learn graph representation in the second feature learning stage, we introduce graph convolutional network to exploit the inherent correlations between the samples both in source and target domains, where GCN has been proved its high-efficiency in several semi-supervised learning methods [12], [15]. In particular, the shared GCN is defined by G(A, H c ), where A ∈ R (Ns+Nt)×(Ns+Nt) is the pairwise relationship adjacent matrix and A ij denotes the relationship (such as distance, similarity) between i-th and j-th samples in source and target domains.…”

Section: A Graph Feature Representationmentioning

confidence: 99%

“…The semi-supervised learning only requires a small number of annotated samples to exploit identical information from unlabeled data, which performance is between supervised and unsupervised approaches. There is a major concern that existing semi-supervised medical image classification methods ignore the interactive influence between image samples, which can be addressed by the Graph Convolutional Network (GCN) with a graph learning module [12]. There lefts a major challenge for the automatic histological image classification that is the limited amount of data available under supervised learning and temporally annotating a large number of breast histological images is unsubstantial in clinical application as demonstrated in [1], [18], [30].…”

Section: Introductionmentioning

confidence: 99%

“…Nevertheless, transfer learning provides a novel ideology that has been proved to be effective for solving the challenge of limited labeled histology data [27], [29], [33], and it needs a completely labeled dataset as the source domain with a target domain of partially labeled data. When we exploit the interactive influence between samples in transfer learning, there exists a major problem that the topology graph learning can not be well transferred because the semisupervised GCN [12] only builds graph learning in single domain, which will lose efficacy moving to another.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Semi-Supervised Breast Histological Image Classification by Node-Attention Graph Transfer Network

2020

View full text Add to dashboard Cite

As a major cause of leading female death, breast cancer is often diagnosed by histological images which has been resolved by many deep learning methods with the assistance of large amounts of annotated data. However, their performances are severely limited by the lack of sufficient labeled data in clinical practice. This paper aims to relieve the annotating workload by a semi-supervised transfer learning algorithm to conduct knowledge distillation from a completely labeled source domain. To achieve this goal, we propose a node-attention graph transfer network to exploit the inherent correlation between individual samples by graph convolutional network, along with a cross-domain graph learning module to stimulate the graph construction in target domain. In the meanwhile, we design a node-attention mechanism to learn the individual contribution of each source image for target domain, which can further leverage the domain-gap by our node-attention transfer learning. Results of semi-supervised breast histological image classification with various scales of annotated training images are performable and further experiments demonstrate the significant contributions of each component we proposed.

show abstract

Section: A Graph Feature Representationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Semi-Supervised Breast Histological Image Classification by Node-Attention Graph Transfer Network

2020

View full text Add to dashboard Cite

show abstract

“…On the other hand, graph spectral learning methods offer an alternative (or additional) signal representation perspective, where observed signals are assumed to lie in a lowdimensional subspace spanned by the low frequency components of the underlying graph topologies [18]- [25]. Specifically, the frequency components are eigenvectors of a chosen variational operator on graphs like the adjacency matrix or the graph Laplacian matrix [26].…”

Section: Introductionmentioning

confidence: 99%

Feature Graph Learning for 3D Point Cloud Denoising

Gao

Cheung

et al. 2020

IEEE Trans. Signal Process.

View full text Add to dashboard Cite

Identifying an appropriate underlying graph kernel that reflects pairwise similarities is critical in many recent graph spectral signal restoration schemes, including image denoising, dequantization, and contrast enhancement. Existing graph learning algorithms compute the most likely entries of a properly defined graph Laplacian matrix L, but require a large number of signal observations z's for a stable estimate. In this work, we assume instead the availability of a relevant feature vector fi per node i, from which we compute an optimal feature graph via optimization of a feature metric. Specifically, we alternately optimize the diagonal and off-diagonal entries of a Mahalanobis distance matrix M by minimizing the graph Laplacian regularizer (GLR) z Lz, where edge weight is wi,j = exp{−(fi − fj) M(fi − fj)}, given a single observation z. We optimize diagonal entries via proximal gradient (PG), where we constrain M to be positive definite (PD) via linear inequalities derived from the Gershgorin circle theorem. To optimize off-diagonal entries, we design a block descent algorithm that iteratively optimizes one row and column of M. To keep M PD, we constrain the Schur complement of sub-matrix M2,2 of M to be PD when optimizing via PG. Our algorithm mitigates full eigen-decomposition of M, thus ensuring fast computation speed even when feature vector fi has high dimension. To validate its usefulness, we apply our feature graph learning algorithm to the problem of 3D point cloud denoising, resulting in state-of-the-art performance compared to competing schemes in extensive experiments.

show abstract

“…There existed some methods incorporating label consistency and feature correlations [7,8]. Besides, previous proposed methods also attempt to combine label propagation with neighbor aggregation to achieve the goal [9,10]. However, these methods relied on the original features and labels, resulting in arXiv:2007.13435v1 [cs.LG] 27 Jul 2020…”

Section: Introductionmentioning

confidence: 99%

Label-Consistency based Graph Neural Networks for Semi-supervised Node Classification

Huang

Hou

et al. 2020

Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Graph neural networks (GNNs) achieve remarkable success in graph-based semi-supervised node classification, leveraging the information from neighboring nodes to improve the representation learning of target node. The success of GNNs at node classification depends on the assumption that connected nodes tend to have the same label. However, such an assumption does not always work, limiting the performance of GNNs at node classification. In this paper, we propose label-consistency based graph neural network (LC-GNN), leveraging node pairs unconnected but with the same labels to enlarge the receptive field of nodes in GNNs. Experiments on benchmark datasets demonstrate the proposed LC-GNN outperforms traditional GNNs in graph-based semi-supervised node classification. We further show the superiority of LC-GNN in sparse scenarios with only a handful of labeled nodes.

show abstract

Semi-Supervised Learning With Graph Learning-Convolutional Networks

Cited by 278 publications

References 8 publications

Semi-Supervised Breast Histological Image Classification by Node-Attention Graph Transfer Network

Semi-Supervised Breast Histological Image Classification by Node-Attention Graph Transfer Network

Feature Graph Learning for 3D Point Cloud Denoising

Label-Consistency based Graph Neural Networks for Semi-supervised Node Classification

Contact Info

Product

Resources

About