Graph Decoupling Attention Markov Networks for Semisupervised Graph Node Classification

Chen, Jie; Chen, Shouzhen; Bai, Mingyuan; Pu, Jian; Zhang, Junping; Gao, Junbin

doi:10.1109/tnnls.2022.3161453

Cited by 16 publications

(10 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this experiment, the loss is computed for each optimization iteration of the DTI association network and iteratively updated using eqs and until the loss falls below the predefined threshold. Compared to a fixed number of iterations, the experiment employs a dynamic stopping optimization strategy, which proves to be more effective for the optimization process, especially for small-sample data sets. , …”

Section: Methodsmentioning

confidence: 99%

“…However, current methods based on similarity measurements of DTI association networks typically assume that the network topology is stable and low-noise, which does not align with reality. Constructed DTI networks often come with noise or structural incompleteness issues . Noise in the network may introduce false interactions, distorting the true relationships between drugs and targets, thereby affecting model learning and prediction .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

AIGO-DTI: Predicting Drug–Target Interactions Based on Improved Drug Properties Combined with Adaptive Iterative Algorithms

Zhang,

Tian,

Chen

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Artificial intelligence-based methods for predicting drug–target interactions (DTIs) aim to explore reliable drug candidate targets rapidly and cost-effectively to accelerate the drug development process. However, current methods are often limited by the topological regularities of drug molecules, making them difficult to generalize to a broader chemical space. Additionally, the use of similarity to measure DTI network links often introduces noise, leading to false DTI relationships and affecting the prediction accuracy. To address these issues, this study proposes an Adaptive Iterative Graph Optimization (AIGO)-DTI prediction framework. This framework integrates atomic cluster information and enhances molecular features through the design of functional group prompts and graph encoders, optimizing the construction of DTI association networks. Furthermore, the optimization of graph structure is transformed into a node similarity learning problem, utilizing multihead similarity metric functions to iteratively update the network structure to improve the quality of DTI information. Experimental results demonstrate the outstanding performance of AIGO-DTI on multiple public data sets and label reversal data sets. Case studies, molecular docking, and existing research validate its effectiveness and reliability. Overall, the method proposed in this study can construct comprehensive and reliable DTI association network information, providing new graphing and optimization strategies for DTI prediction, which contribute to efficient drug development and reduce target discovery costs.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

AIGO-DTI: Predicting Drug–Target Interactions Based on Improved Drug Properties Combined with Adaptive Iterative Algorithms

Zhang,

Tian,

Chen

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

show abstract

“…GSL [52][53][54][55] is an important branch of the graph representation learning field, which focuses on optimizing the structure of graphs through joint training to enhance the performance of GNN. GSL methods can be divided into three main categories: metric learning methods [56][57][58], neural network methods [59,60] and direct methods [52,61,62]. In prediction tasks, the traditional GSL process and the GSL process used for traffic prediction are shown in Fig.…”

Section: Graph Structure Learningmentioning

confidence: 99%

“…Next, the final embedding representation h is transformed into a dynamic graph structure using a metric learning method [66]. In this paper, the weighted cosine distance is chosen as the metric function [57]: α ij = cos (w ⊙ h i , w ⊙ h j ), where ⊙ denotes the Hadamard product, and w is a learnable weight vector with the same dimension as the final embedding representations h i and h j . To stabilize the learning process and enhance expressiveness, this paper extends the similarity metric function to a multihead version.…”

Section: Inmentioning

confidence: 99%

An Integrated Static and Dynamic Graph Fusion Approach for Traffic Flow Prediction

Che,

Xiong,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

The major challenge in accurate traffic flow prediction lies in effectively capturing the dynamic spatiotemporal correlations within the traffic system. In this paper, we propose a novel traffic flow prediction method based on the fusion of static and dynamic graphs. Firstly, a predefined graph structure is used as the initial static graph. Secondly, a temporal graph convolution module constructed in a data-driven manner is designed, further implementing a dynamic graph structure that varies with the input data, thoroughly constructing the spatial relations between traffic flow sequence data. Finally, specific spatial and temporal relations are modeled from the perspective of graphs, effectively merging static and dynamic spatial relations. The performance of our method was validated using two real public datasets, PEMS04 and PEMS08. Experimental results demonstrate that our model outperforms existing traffic flow prediction models by 9.32% in terms of prediction error when compared to 18 benchmark methods.

show abstract

“…GLCN (Jiang et al 2019) exploits a unified framework for executing graph learning and graph convolution. IDGL (Chen, Wu, and Zaki 2020) leverages graph regularization terms to enhance learning quality. Pro-GNN (Jin et al 2020) employs alternating optimization to realize the mutual regularization of graph learning and network update.…”

Section: Related Work Graph Structure Learningmentioning

confidence: 99%

Deep Contrastive Graph Learning with Clustering-Oriented Guidance

Chen,

Wang,

2024

AAAI

View full text Add to dashboard Cite

Graph Convolutional Network (GCN) has exhibited remarkable potential in improving graph-based clustering. To handle the general clustering scenario without a prior graph, these models estimate an initial graph beforehand to apply GCN. Throughout the literature, we have witnessed that 1) most models focus on the initial graph while neglecting the original features. Therefore, the discriminability of the learned representation may be corrupted by a low-quality initial graph; 2) the training procedure lacks effective clustering guidance, which may lead to the incorporation of clustering-irrelevant information into the learned graph. To tackle these problems, the Deep Contrastive Graph Learning (DCGL) model is proposed for general data clustering. Specifically, we establish a pseudo-siamese network, which incorporates auto-encoder with GCN to emphasize both the graph structure and the original features. On this basis, feature-level contrastive learning is introduced to enhance the discriminative capacity, and the relationship between samples and centroids is employed as the clustering-oriented guidance. Afterward, a two-branch graph learning mechanism is designed to extract the local and global structural relationships, which are further embedded into a unified graph under the cluster-level contrastive guidance. Experimental results on several benchmark datasets demonstrate the superiority of DCGL against state-of-the-art algorithms.

show abstract

Graph Decoupling Attention Markov Networks for Semisupervised Graph Node Classification

Cited by 16 publications

References 24 publications

AIGO-DTI: Predicting Drug–Target Interactions Based on Improved Drug Properties Combined with Adaptive Iterative Algorithms

AIGO-DTI: Predicting Drug–Target Interactions Based on Improved Drug Properties Combined with Adaptive Iterative Algorithms

An Integrated Static and Dynamic Graph Fusion Approach for Traffic Flow Prediction

Deep Contrastive Graph Learning with Clustering-Oriented Guidance

Contact Info

Product

Resources

About