Multigraph Fusion for Dynamic Graph Convolutional Network

Task-radMBNet: An Improved Task-Driven Dynamic Graph Sparsity Pattern Radiomics-Based Morphological Brain Network for Alzheimer's Disease Characterization

Background: The study of task-driven dynamic adaptive graph sparsity patterns in Alzheimer's disease (AD) analysis is of great importance, as it allows for better focus on regions and connections of interest and enhances task sensitivity. Methods: In this study, we introduced a task-driven dynamic adaptive graph sparsity model (called task-driven radiomics-based morphological brain network [Task-radMBNet]) for AD diagnosis based on radiomics-based morphological brain network (radMBN). Specifically, the Task-radMBNet was established by devising a connectivity feature-based graph convolutional network (GCN) channel (called a connectivity-GCN channel) and a radiomics feature-based GCN channel (called a radiomics-GCN channel), where the two GCN channels shared a same dynamic sparse brain network in graph convolution but worked for different aims separately. The connectivity-GCN channel dynamically learned the graph's sparse topology that best suits the target task, while the radiomics-GCN channel combined radiomics node features and dynamic topology to improve AD diagnostic accuracy. Results: The Task-radMBNet achieved superior classification accuracy of 87.8% and 86.0% in early AD diagnosis across a total of 1273 subjects within the AD Neuroimaging Initiative and European Diffusion Tensor Imaging (DTI) Study on Dementia databases. We also visualized the topology heat map and important connectivity under different network sparse settings. Conclusions: The results demonstrated significant promise in the diagnosis of neurological disorders by integrating Task-radMBNet with radMBN.

Motif Graph Neural Network

Graphs can model complicated interactions between entities, which naturally emerge in many important applications. These applications can often be cast into standard graph learning tasks, in which a crucial step is to learn low-dimensional graph representations. Graph neural networks (GNNs) are currently the most popular model in graph embedding approaches. However, standard GNNs in the neighborhood aggregation paradigm suffer from limited discriminative power in distinguishing high-order graph structures as opposed to low-order structures. To capture high-order structures, researchers have resorted to motifs and developed motif-based GNNs. However, the existing motif-based GNNs still often suffer from less discriminative power on high-order structures. To overcome the above limitations, we propose motif GNN (MGNN), a novel framework to better capture high-order structures, hinging on our proposed motif redundancy minimization operator and injective motif combination. First, MGNN produces a set of node representations with respect to each motif. The next phase is our proposed redundancy minimization among motifs which compares the motifs with each other and distills the features unique to each motif. Finally, MGNN performs the updating of node representations by combining multiple representations from different motifs. In particular, to enhance the discriminative power, MGNN uses an injective function to combine the representations with respect to different motifs. We further show that our proposed architecture increases the expressive power of GNNs with a theoretical analysis. We demonstrate that MGNN outperforms state-of-the-art methods on seven public benchmarks on both the node classification and graph classification tasks.

A Novel Composite Graph Neural Network

Graph neural networks (GNNs) have achieved great success in many fields due to their powerful capabilities of processing graph-structured data. However, most GNNs can only be applied to scenarios where graphs are known, but real-world data are often noisy or even do not have available graph structures. Recently, graph learning has attracted increasing attention in dealing with these problems. In this article, we develop a novel approach to improving the robustness of the GNNs, called composite GNN. Different from existing methods, our method uses composite graphs (C-graphs) to characterize both sample and feature relations. The C-graph is a unified graph that unifies these two kinds of relations, where edges between samples represent sample similarities, and each sample has a tree-based feature graph to model feature importance and combination preference. By jointly learning multiaspect C-graphs and neural network parameters, our method improves the performance of semisupervised node classification and ensures robustness. We conduct a series of experiments to evaluate the performance of our method and the variants of our method that only learn sample relations or feature relations. Extensive experimental results on nine benchmark datasets demonstrate that our proposed method achieves the best performance on almost all the datasets and is robust to feature noises.

Deep Learning for Dynamic Graphs: Models and Benchmarks

Recent progress in research on deep graph networks (DGNs) has led to a maturation of the domain of learning on graphs. Despite the growth of this research field, there are still important challenges that are yet unsolved. Specifically, there is an urge of making DGNs suitable for predictive tasks on real-world systems of interconnected entities, which evolve over time. With the aim of fostering research in the domain of dynamic graphs, first, we survey recent advantages in learning both temporal and spatial information, providing a comprehensive overview of the current state-of-the-art in the domain of representation learning for dynamic graphs. Second, we conduct a fair performance comparison among the most popular proposed approaches on node- and edge-level tasks, leveraging rigorous model selection and assessment for all the methods, thus establishing a sound baseline for evaluating new architectures and approaches.

Bayesian graph convolutional network with partial observations

As a widely studied model in the machine learning and data processing society, graph convolutional network reveals its advantage in non-grid data processing. However, existing graph convolutional networks generally assume that the node features can be fully observed. This may violate the fact that many real applications come with only the pairwise relationships and the corresponding node features are unavailable. In this paper, a novel graph convolutional network model based on Bayesian framework is proposed to handle the graph node classification task without relying on node features. First, we equip the graph node with the pseudo-features generated from the stochastic process. Then, a hidden space structure preservation term is proposed and embedded into the generation process to maintain the independent and identically distributed property between the training and testing dataset. Although the model inference is challenging, we derive an efficient training and predication algorithm using variational inference. Experiments on different datasets demonstrate the proposed graph convolutional networks can significantly outperform traditional methods, achieving an average performance improvement of 9%.

GRLC: Graph Representation Learning With Constraints

Contrastive learning has been successfully applied in unsupervised representation learning. However, the generalization ability of representation learning is limited by the fact that the loss of downstream tasks (e.g., classification) is rarely taken into account while designing contrastive methods. In this article, we propose a new contrastive-based unsupervised graph representation learning (UGRL) framework by 1) maximizing the mutual information (MI) between the semantic information and the structural information of the data and 2) designing three constraints to simultaneously consider the downstream tasks and the representation learning. As a result, our proposed method outputs robust low-dimensional representations. Experimental results on 11 public datasets demonstrate that our proposed method is superior over recent state-of-the-art methods in terms of different downstream tasks. Our code is available at https://github.com/LarryUESTC/GRLC.

Path-enhanced graph convolutional networks for node classification without features

Most current graph neural networks (GNNs) are designed from the view of methodology and rarely consider the inherent characters of graph. Although the inherent characters may impact the performance of GNNs, very few methods are proposed to resolve the issue. In this work, we mainly focus on improving the performance of graph convolutional networks (GCNs) on the graphs without node features. In order to resolve the issue, we propose a method called t-hopGCN to describe t-hop neighbors by the shortest path between two nodes, then the adjacency matrix of t-hop neighbors as features to perform node classification. Experimental results show that t-hopGCN can significantly improve the performance of node classification in the graphs without node features. More importantly, adding the adjacency matrix of t-hop neighbors can improve the performance of existing popular GNNs on node classification.

Adaptive Feature Projection With Distribution Alignment for Deep Incomplete Multi-View Clustering

Incomplete multi-view clustering (IMVC) analysis, where some views of multi-view data usually have missing data, has attracted increasing attention. However, existing IMVC methods still have two issues: 1) they pay much attention to imputing or recovering the missing data, without considering the fact that the imputed values might be inaccurate due to the unknown label information, 2) the common features of multiple views are always learned from the complete data, while ignoring the feature distribution discrepancy between the complete and incomplete data. To address these issues, we propose an imputation-free deep IMVC method and consider distribution alignment in feature learning. Concretely, the proposed method learns the features for each view by autoencoders and utilizes an adaptive feature projection to avoid the imputation for missing data. All available data are projected into a common feature space, where the common cluster information is explored by maximizing mutual information and the distribution alignment is achieved by minimizing mean discrepancy. Additionally, we design a new mean discrepancy loss for incomplete multi-view learning and make it applicable in mini-batch optimization. Extensive experiments demonstrate that our method achieves the comparable or superior performance compared with state-of-the-art methods.