Search

Graph representation learning focuses on abstracting critical information from raw graphs. Unfortunately, there always exist various kinds of uncertainties, such as attribute noise and network topology corruption, in raw graphs. Under the message passing mechanism, certainties are likely to spread throughout the whole graph. Matters like these would induce deep graph models into producing uncertain representations and restrict representation expressiveness. Considering this, we propose a pioneering framework to defend graph uncertainties by improving the robustness and capability of graph neural networks (GNNs). In our framework, we consider that weights and biases are all fuzzy numbers, thus generating representations to assimilate graph uncertainties, which are finally released by defuzzification. To describe the process of the framework, in this article, a graph convolutional network (GCN) is employed to construct a robust graph model, called FuzzyGCN. To verify the effectiveness of FuzzyGCN, it is trained in both supervised and unsupervised ways. In the supervised setting, we find that FuzzyGCN has stronger power and is more immune to data uncertainties when compared with various classical and robust GNNs. In the unsupervised setting, FuzzyGCN surpasses many state-of-the-art models in node classification and community detection over several real-world datasets.

Exploring dynamic patterns from complex and large-scale networks is a significant and challenging task in graph analysis. One of the most advanced solutions is dynamic graph representation learning, which embeds structural and temporal correlations into a representative vector for each node or subgraph. Existing models have made some successes, such as overcoming the problems of induction for unseen nodes and scalability for large-scale evolving networks. However, these models usually rely on crisp representation learning that is incapable of modeling feature fuzziness and capturing uncertainties in dynamic graphs. While real-world dynamic networks as complex systems always contain non-negligible but inestimable uncertainties in node/link attributes and network topology. These uncertainties may cause the learned representations from crisp models hard to precisely reflect network evolution. To address the issues, we propose a new dynamic graph representation learning model, called FuzzyDGL, which first incorporates fuzzy representation learning to handle the uncertainties in dynamic graphs. Through combining acrlong CDGRL with fuzzy logic, the FuzzyDGL digests both of their advantages. On the one hand, it has flexible model scalability and brilliant inductive capability. On the other hand, it can model feature fuzziness to reduce the impact of uncertainties in dynamic graphs, improving the quality of learned representations. To demonstrate its effectiveness, we conduct two important tasks of network analysis, including link prediction and node classification, over eight real-world datasets. The experimental results show the strong competitiveness and generalization of the FuzzyDGL against a number of baseline models.

With the rise of contrastive learning, unsupervised graph representation learning (GRL) has shown strong competitiveness. However, existing graph contrastive models typically either focus on the local view of graphs or take simple considerations of both global and local views. This may cause these models to overemphasize the importance of individual nodes and their ego networks, or to result in poor learning of global knowledge and affect the learning of local views. Additionally, most GRL models pay attention to topological proximity, assuming that nodes that are closer in graph topology are more similar. However, in the real world, close nodes may be dissimilar, which makes the learned embeddings incorporate inappropriate messages and thus lack discrimination. To address these issues, we propose a novel unsupervised GRL model by contrasting cluster assignments, called graph representation learning model via contrasting cluster assignment (GRCCA). To comprehensively explore the global and local views, it combines multiview contrastive learning and clustering algorithms with an opposite augmentation strategy. It leverages clustering algorithms to capture fine-grained global information and explore potential relevance between nodes in different augmented perspectives while preserving high-quality global and local information through contrast between nodes and prototypes. The opposite augmentation strategy further enhances the contrast of both views, allowing the model to excavate more invariant features. Experimental results show that GRCCA has strong competitiveness compared to state-of-the-art models in different graph analysis tasks.