Dynamic graph fusion label propagation for semi-supervised multi-modality classification

Lin, Guanghui; Liao, Kaiyang; Sun, Bangyong; Chen, Yajun; Zhao, Fan

doi:10.1016/j.patcog.2017.03.014

Cited by 54 publications

(36 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The third kind of methods can capture the dynamic changes of multiple structures for semi-supervised classification [13] or the structure propagation method for zero-shot learning [14][15][16][17] for transferring the structure information of the different data objects. These methods can find the dynamic rule of the structure change to help understand the cross-domain data.…”

Section: Structure Fusionmentioning

confidence: 99%

“…to discriminate the different data objects.The recent learning methods for mining multi-graph structure information mainly have tow categories. One is structure fusion [7][8][9][10][11][12][13][14][15][16][17] or diffusion on the tensor product graph [18-23] based on the complete data, which include each view observation datum. Another is graph convolutional networks for the salient graph structure preservation [6] or node information fusion [24,25] based on incomplete data, which lacks some view observation data.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Structure Fusion Based on Graph Convolutional Networks for Node Classification in Citation Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

Suffering from the multi-view data diversity and complexity, most of the existing graph convolutional networks focus on the networks’ architecture construction or the salient graph structure preservation for node classification in citation networks and usually ignore capturing the complete graph structure of nodes for enhancing classification performance. To mine the more complete distribution structure from multi-graph structures of multi-view data with the consideration of their specificity and the commonality, we propose structure fusion based on graph convolutional networks (SF-GCN) for improving the performance of node classification in a semi-supervised way. SF-GCN can not only exploit the special characteristic of each view datum by spectral embedding preserving multi-graph structures, but also explore the common style of multi-view data by the distance metric between multi-graph structures. Suppose the linear relationship between multi-graph structures; we can construct the optimization function of the structure fusion model by balancing the specificity loss and the commonality loss. By solving this function, we can simultaneously obtain the fusion spectral embedding from the multi-view data and the fusion structure as the adjacent matrix to input graph convolutional networks for node classification in a semi-supervised way. Furthermore, we generalize the structure fusion to structure diffusion propagation and present structure propagation fusion based on graph convolutional networks (SPF-GCN) for utilizing these structure interactions. Experiments demonstrate that the performance of SPF-GCN outperforms that of the state-of-the-art methods on three challenging datasets, which are Cora, Citeseer, and Pubmed in citation networks.

show abstract

Section: Structure Fusionmentioning

confidence: 99%

mentioning

confidence: 99%

Structure Fusion Based on Graph Convolutional Networks for Node Classification in Citation Networks

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…In recent works, there are two kinds of the impressive methods. One is structure information propagation in label space, such as dynamic structure fusion and label propagation to refining the relation of objects for semi-supervised multi-modality classification [18] and information propagation mechanism from the semantic label space, which can be applied to model the interdependencies between seen and unseen class labels [19]. The other is structure information propagation between seen and unseen classes, for instant structure fusion and propagation to update the relevance of multi-semantic classes by the iteration computation for ZSL [20] [10], structure propagation constraining the encoderdecoder mechanism of the bidirectional projection for ZSL [21], and absorbing Markov chain process propagation constructing semantic class prototype graph for ZSL [22].…”

Section: Structure Propagationmentioning

confidence: 99%

Transfer Feature Generating Networks With Semantic Classes Structure for Zero-Shot Learning

et al. 2019

Self Cite

View full text Add to dashboard Cite

Feature generating networks face to the most important question, which is the fitting difference (inconsistence) of the distribution between the generated feature and the real data. This inconsistence further influence the performance of the networks model, because training samples from seen classes is disjointed with testing samples from unseen classes in zero-shot learning (ZSL). In generalization zero-shot learning (GZSL), testing samples come from not only seen classes but also unseen classes for closer to the practical situation. Therefore, most of feature generating networks difficultly obtain satisfactory performance for the challenging GZSL by adversarial learning the distribution of semantic classes. To alleviate the negative influence of this inconsistence for ZSL and GZSL, transfer feature generating networks with semantic classes structure (TFGNSCS) is proposed to construct networks model for improving the performance of ZSL and GZSL. TFGNSCS can not only consider the semantic structure relationship between seen and unseen classes, but also learn the difference of generating features by transferring classification model information from seen to unseen classes in networks.The proposed method can integrate the transfer loss, the classification loss and the Wasserstein distance loss to generate enough CNN features, on which softmax classifiers are trained for ZSL and GZSL. Experiments demonstrate that the performance of TFGNSCS outperforms that of the state of the arts on four challenging datasets, which are CUB,FLO,SUN, AWA in GZSL.

show abstract

“…LP has different applications in community detection [16], image segmentation [17], clustering [18], and classification [19] tasks. Although most of the algorithms use one single graph as an input of the LP algorithms, such as the Zhou method [20], flexible manifold embedding (FME) [21], local and global consistency (LGC) [22], and Gaussian fields and harmonic function (GFHF) [23], exploiting various similarity graphs can enhance the performance of LP process (graph-fusion methods) [15,[24][25][26][27][28], thereby creating multiple similarity graphs where each contains complementary information of data and fusing them together can lead to a better representation of data.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, graph fusion methods have been proposed as one of the approaches to fuse different views. While different algorithms for graph fusion have been designed in three levels of graph integration (early integration [31], late integration [15], and intermediate integration [24][25][26][27][28]32,33]), a common solution is to construct different graphs based on multiple views called intermediate integration and then fuse the graphs either linearly via dynamic graph fusion LP (DGFLP) [25], sparse multiple graph integration (SMGI) [24], multi-view LGC [32], and deep graph fusion [33]), or nonlinearly with similarity network fusion (SNF) [27], nonlinear graph fusion (NGF) [26], and multi-modality dynamic LP (MDLP) for semi-supervised multi-class multi-label [28]. Furthermore, some methods attempt to learn different metrics based on different feature descriptors [2][3][4][5], whereas, in some cases, the variation of multi-view leads to misalignment in feature descriptors [34].…”

Section: Introductionmentioning

confidence: 99%

Multi Similarity Metric Fusion in Graph-Based Semi-Supervised Learning

2019

View full text Add to dashboard Cite

In semi-supervised label propagation (LP), the data manifold is approximated by a graph, which is considered as a similarity metric. Graph estimation is a crucial task, as it affects the further processes applied on the graph (e.g., LP, classification). As our knowledge of data is limited, a single approximation cannot easily find the appropriate graph, so in line with this, multiple graphs are constructed. Recently, multi-metric fusion techniques have been used to construct more accurate graphs which better represent the data manifold and, hence, improve the performance of LP. However, most of these algorithms disregard use of the information of label space in the LP process. In this article, we propose a new multi-metric graph-fusion method, based on the Flexible Manifold Embedding algorithm. Our proposed method represents a unified framework that merges two phases: graph fusion and LP. Based on one available view, different simple graphs were efficiently generated and used as input to our proposed fusion approach. Moreover, our method incorporated the label space information as a new form of graph, namely the Correlation Graph, with other similarity graphs. Furthermore, it updated the correlation graph to find a better representation of the data manifold. Our experimental results on four face datasets in face recognition demonstrated the superiority of the proposed method compared to other state-of-the-art algorithms.

show abstract

Dynamic graph fusion label propagation for semi-supervised multi-modality classification

Cited by 54 publications

References 36 publications

Structure Fusion Based on Graph Convolutional Networks for Node Classification in Citation Networks

Structure Fusion Based on Graph Convolutional Networks for Node Classification in Citation Networks

Transfer Feature Generating Networks With Semantic Classes Structure for Zero-Shot Learning

Multi Similarity Metric Fusion in Graph-Based Semi-Supervised Learning

Contact Info

Product

Resources

About