Related papers: E2EG: End-to-End Node Classification Using Graph T…

Modularity plays a crucial role in the development and maintenance of complex systems. While end-to-end text spotting efficiently mitigates the issues of error accumulation and sub-optimal performance seen in traditional two-step…

Graph-based neural network models are gaining traction in the field of representation learning due to their ability to uncover latent topological relationships between entities that are otherwise challenging to identify. These models have…

This work studies ensemble learning for graph neural networks (GNNs) under the popular semi-supervised setting. Ensemble learning has shown superiority in improving the accuracy and robustness of traditional machine learning by combining…

Contrastive learning methods have attracted considerable attention due to their remarkable success in analyzing graph-structured data. Inspired by the success of contrastive learning, we propose a novel framework for contrastive…

We present a novel end-to-end framework that generates highly compact (typically 6-15 dimensions), discrete (int4 type), and interpretable node representations, termed node identifiers (node IDs), to tackle inference challenges on…

Graph-structured information offers rich contextual information that can enhance language models by providing structured relationships and hierarchies, leading to more expressive embeddings for various applications such as retrieval,…

Graph Neural Networks (GNNs) have achieved great success among various domains. Nevertheless, most GNN methods are sensitive to the quality of graph structures. To tackle this problem, some studies exploit different graph structure learning…

Recently, end-to-end (E2E) trained models for question answering over knowledge graphs (KGQA) have delivered promising results using only a weakly supervised dataset. However, these models are trained and evaluated in a setting where…

Graph Neural Networks (GNNs), originally proposed for node classification, have also motivated many recent works on edge prediction (a.k.a., link prediction). However, existing methods lack elaborate design regarding the distinctions…

In this thesis, we study the problem of feature learning on heterogeneous knowledge graphs. These features can be used to perform tasks such as link prediction, classification and clustering on graphs. Knowledge graphs provide rich…

Networks are fundamental to the study of complex systems, ranging from social contacts, message transactions, to biological regulations and economical networks. In many realistic applications, these networks may vary over time. Modeling and…

Many real-world problems are naturally modeled as heterogeneous graphs, where nodes and edges represent multiple types of entities and relations. Existing learning models for heterogeneous graph representation usually depend on the…

Accurate citation count prediction of newly published papers could help editors and readers rapidly figure out the influential papers in the future. Though many approaches are proposed to predict a paper's future citation, most ignore the…

In this paper, we investigate the modeling power of contextualized embeddings from pre-trained language models, e.g. BERT, on the E2E-ABSA task. Specifically, we build a series of simple yet insightful neural baselines to deal with…

Node-link diagrams are widely used to visualize graphs. Most graph layout algorithms only use graph topology for aesthetic goals (e.g., minimize node occlusions and edge crossings) or use node attributes for exploration goals (e.g.,…

Link Prediction (LP) is a crucial problem in graph-structured data. Graph Neural Networks (GNNs) have gained prominence in LP, with Graph AutoEncoders (GAEs) being a notable representation. However, our empirical findings reveal that GAEs'…

As an alternative to traditional fault injection-based methodologies and to explore the applicability of modern machine learning algorithms in the field of reliability engineering, this paper proposes a systemic framework that explores…

Spectral graph convolutional neural networks (GCNNs) have been producing encouraging results in graph classification tasks. However, most spectral GCNNs utilize fixed graphs when aggregating node features, while omitting edge feature…

Graph embedding is an important approach for graph analysis tasks such as node classification and link prediction. The goal of graph embedding is to find a low dimensional representation of graph nodes that preserves the graph information.…

Graph-to-text generation has benefited from pre-trained language models (PLMs) in achieving better performance than structured graph encoders. However, they fail to fully utilize the structure information of the input graph. In this paper,…