90 citations · 200 across the 28 of their papers we have counts for
16 papers · 1 filter
HeterSEED: Semantics-Structure Decoupling for Heterogeneous Graph Learning under Heterophily
Xinyi Li, Ming Li, Lu Bai +5
Many real-world heterogeneous graphs exhibit pronounced heterophily, where connected nodes often have dissimilar labels or play different semantic roles. In such settings, standard…
LGAN: An Efficient High-Order Graph Neural Network via the Line Graph Aggregation
Lin Du, Lu Bai, Jincheng Li +5
Graph Neural Networks (GNNs) have emerged as a dominant paradigm for graph classification. Specifically, most existing GNNs mainly rely on the message passing strategy between neig…
Knowledge Probing for Graph Representation Learning
Mingyu Zhao, Xingyu Huang, Ziyu Lyu +3
Graph learning methods have been extensively applied in diverse application areas. However, what kind of inherent graph properties e.g. graph proximity, graph structural informatio…
HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning
Zhuo Xu, Lu Bai, Lixin Cui +3
Graph Auto-Encoders (GAEs) are powerful tools for graph representation learning. In this paper, we develop a novel Hierarchical Cluster-based GAE (HC-GAE), that can learn effective…
ENADPool: The Edge-Node Attention-based Differentiable Pooling for Graph Neural Networks
Zhehan Zhao, Lu Bai, Lixin Cui +4
Graph Neural Networks (GNNs) are powerful tools for graph classification. One important operation for GNNs is the downsampling or pooling that can learn effective embeddings from t…
AKBR: Learning Adaptive Kernel-based Representations for Graph Classification
Feifei Qian, Lixin Cui, Ming Li +6
In this paper, we propose a new model to learn Adaptive Kernel-based Representations (AKBR) for graph classification. Unlike state-of-the-art R-convolution graph kernels that are d…
AERK: Aligned Entropic Reproducing Kernels through Continuous-time Quantum Walks
Lixin Cui, Ming Li, Yue Wang +2
In this work, we develop an Aligned Entropic Reproducing Kernel (AERK) for graph classification. We commence by performing the Continuous-time Quantum Walk (CTQW) on each graph str…
QESK: Quantum-based Entropic Subtree Kernels for Graph Classification
Lu Bai, Lixin Cui, Edwin R. Hancock
In this paper, we propose a novel graph kernel, namely the Quantum-based Entropic Subtree Kernel (QESK), for Graph Classification. To this end, we commence by computing the Average…
HAQJSK: Hierarchical-Aligned Quantum Jensen-Shannon Kernels for Graph Classification
Lu Bai, Lixin Cui, Yue Wang +2
In this work, we propose a family of novel quantum kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), for un-attributed graphs. Different from most e…
Generative Temporal Link Prediction via Self-tokenized Sequence Modeling
Yue Wang, Chenwei Zhang, Shen Wang +4
We formalize networks with evolving structures as temporal networks and propose a generative link prediction model, Generative Link Sequence Modeling (GLSM), to predict future link…
Competitive Multi-Agent Deep Reinforcement Learning with Counterfactual Thinking
Yue Wang, Yao Wan, Chenwei Zhang +3
Counterfactual thinking describes a psychological phenomenon that people re-infer the possible results with different solutions about things that have already happened. It helps pe…
Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification
Lu Bail, Lixin Cui, Yuhang Jiao +2
In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification. Our idea is to tran…
Learning Vertex Convolutional Networks for Graph Classification
Lu Bai, Lixin Cui, Shu Wu +2
In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification. Our idea is to transform the g…
Fused Lasso for Feature Selection using Structural Information
Lu Bai, Lixin Cui, Yue Wang +2
Feature selection has been proven a powerful preprocessing step for high-dimensional data analysis. However, most state-of-the-art methods tend to overlook the structural correlati…
Identifying The Most Informative Features Using A Structurally Interacting Elastic Net
Lixin Cui, Lu Bai, Zhihong Zhang +2
Feature selection can efficiently identify the most informative features with respect to the target feature used in training. However, state-of-the-art vector-based methods are una…
Graph Convolutional Neural Networks based on Quantum Vertex Saliency
Lu Bai, Yuhang Jiao, Luca Rossi +3
This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike…