115 citations · 292 across the 27 of their papers we have counts for
19 papers · 1 filter
Dynamic Graph Information Bottleneck
Haonan Yuan, Qingyun Sun, Xingcheng Fu +2
Dynamic Graphs widely exist in the real world, which carry complicated spatial and temporal feature patterns, challenging their representation learning. Dynamic Graph Neural Networ…
Poincaré Differential Privacy for Hierarchy-Aware Graph Embedding
Yuecen Wei, Haonan Yuan, Xingcheng Fu +4
Hierarchy is an important and commonly observed topological property in real-world graphs that indicate the relationships between supervisors and subordinates or the organizational…
Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization
Haonan Yuan, Qingyun Sun, Xingcheng Fu +4
Dynamic graph neural networks (DGNNs) are increasingly pervasive in exploiting spatio-temporal patterns on dynamic graphs. However, existing works fail to generalize under distribu…
Does Graph Distillation See Like Vision Dataset Counterpart?
Beining Yang, Kai Wang, Qingyun Sun +5
Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have attracted increasing concerns. Existing graph condens…
Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification
Xingcheng Fu, Yuecen Wei, Qingyun Sun +4
Learning unbiased node representations for imbalanced samples in the graph has become a more remarkable and important topic. For the graph, a significant challenge is that the topo…
Unbiased and Efficient Self-Supervised Incremental Contrastive Learning
Cheng Ji, Jianxin Li, Hao Peng +4
Contrastive Learning (CL) has been proved to be a powerful self-supervised approach for a wide range of domains, including computer vision and graph representation learning. Howeve…
Self-organization Preserved Graph Structure Learning with Principle of Relevant Information
Qingyun Sun, Jianxin Li, Beining Yang +3
Most Graph Neural Networks follow the message-passing paradigm, assuming the observed structure depicts the ground-truth node relationships. However, this fundamental assumption ca…
Heterogeneous Graph Neural Network for Privacy-Preserving Recommendation
Yuecen Wei, Xingcheng Fu, Qingyun Sun +4
Social networks are considered to be heterogeneous graph neural networks (HGNNs) with deep learning technological advances. HGNNs, compared to homogeneous data, absorb various aspe…
Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing
Qingyun Sun, Jianxin Li, Haonan Yuan +5
Topology-imbalance is a graph-specific imbalance problem caused by the uneven topology positions of labeled nodes, which significantly damages the performance of GNNs. What topolog…
Automating DBSCAN via Deep Reinforcement Learning
Ruitong Zhang, Hao Peng, Yingtong Dou +4
DBSCAN is widely used in many scientific and engineering fields because of its simplicity and practicality. However, due to its high sensitivity parameters, the accuracy of the clu…
Curvature Graph Generative Adversarial Networks
Jianxin Li, Xingcheng Fu, Qingyun Sun +4
Generative adversarial network (GAN) is widely used for generalized and robust learning on graph data. However, for non-Euclidean graph data, the existing GAN-based graph represent…
Graph Structure Learning with Variational Information Bottleneck
Qingyun Sun, Jianxin Li, Hao Peng +4
Graph Neural Networks (GNNs) have shown promising results on a broad spectrum of applications. Most empirical studies of GNNs directly take the observed graph as input, assuming th…
ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network
Xingcheng Fu, Jianxin Li, Jia Wu +6
Graph Neural Networks (GNNs) have been widely studied in various graph data mining tasks. Most existingGNNs embed graph data into Euclidean space and thus are less effective to cap…
A Robust and Generalized Framework for Adversarial Graph Embedding
Jianxin Li, Xingcheng Fu, Hao Peng +5
Graph embedding is essential for graph mining tasks. With the prevalence of graph data in real-world applications, many methods have been proposed in recent years to learn high-qua…
A Recipe for Global Convergence Guarantee in Deep Neural Networks
Kenji Kawaguchi, Qingyun Sun
Existing global convergence guarantees of (stochastic) gradient descent do not apply to practical deep networks in the practical regime of deep learning beyond the neural tangent k…
SUGAR: Subgraph Neural Network with Reinforcement Pooling and Self-Supervised Mutual Information Mechanism
Qingyun Sun, Jianxin Li, Hao Peng +4
Graph representation learning has attracted increasing research attention. However, most existing studies fuse all structural features and node attributes to provide an overarching…
GRAC: Self-Guided and Self-Regularized Actor-Critic
Lin Shao, Yifan You, Mengyuan Yan +2
Deep reinforcement learning (DRL) algorithms have successfully been demonstrated on a range of challenging decision making and control tasks. One dominant component of recent deep…
Degrees of Freedom Analysis of Unrolled Neural Networks
Morteza Mardani, Qingyun Sun, Vardan Papyan +3
Unrolled neural networks emerged recently as an effective model for learning inverse maps appearing in image restoration tasks. However, their generalization risk (i.e., test mean-…
Convolutional Imputation of Matrix Networks
Qingyun Sun, Mengyuan Yan David Donoho, Stephen Boyd
A matrix network is a family of matrices, with relatedness modeled by a weighted graph. We consider the task of completing a partially observed matrix network. We assume a novel sa…