107 citations · 182 across the 14 of their papers we have counts for
15 papers
MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy
Haitian Jiang, Renjie Liu, Zengfeng Huang +5
Among the many variants of graph neural network (GNN) architectures capable of modeling data with cross-instance relations, an important subclass involves layers designed such that…
Geometric Imbalance in Semi-Supervised Node Classification
Liang Yan, Shengzhong Zhang, Bisheng Li +6
Class imbalance in graph data presents a significant challenge for effective node classification, particularly in semi-supervised scenarios. In this work, we formally introduce the…
FreshGNN: Reducing Memory Access via Stable Historical Embeddings for Graph Neural Network Training
Kezhao Huang, Haitian Jiang, Minjie Wang +7
A key performance bottleneck when training graph neural network (GNN) models on large, real-world graphs is loading node features onto a GPU. Due to limited GPU memory, expensive d…
ASGNN: Graph Neural Networks with Adaptive Structure
Zepeng Zhang, Songtao Lu, Zengfeng Huang +1
The graph neural network (GNN) models have presented impressive achievements in numerous machine learning tasks. However, many existing GNN models are shown to be vulnerable to adv…
Transformers from an Optimization Perspective
Yongyi Yang, Zengfeng Huang, David Wipf
Deep learning models such as the Transformer are often constructed by heuristics and experience. To provide a complementary foundation, in this work we study the following problem:…
BSAL: A Framework of Bi-component Structure and Attribute Learning for Link Prediction
Bisheng Li, Min Zhou, Shengzhong Zhang +3
Given the ubiquitous existence of graph-structured data, learning the representations of nodes for the downstream tasks ranging from node classification, link prediction to graph c…
Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily
Jie Chen, Shouzhen Chen, Junbin Gao +3
Due to the homophily assumption in graph convolution networks (GNNs), a common consensus in the graph node classification task is that GNNs perform well on homophilic graphs but ma…
Implicit vs Unfolded Graph Neural Networks
Yongyi Yang, Tang Liu, Yangkun Wang +2
It has been observed that message-passing graph neural networks (GNN) sometimes struggle to maintain a healthy balance between the efficient/scalable modeling of long-range depende…
Why Propagate Alone? Parallel Use of Labels and Features on Graphs
Yangkun Wang, Jiarui Jin, Weinan Zhang +7
Graph neural networks (GNNs) and label propagation represent two interrelated modeling strategies designed to exploit graph structure in tasks such as node property prediction. The…
Discrete-time Temporal Network Embedding via Implicit Hierarchical Learning in Hyperbolic Space
Menglin Yang, Min Zhou, Marcus Kalander +2
Representation learning over temporal networks has drawn considerable attention in recent years. Efforts are mainly focused on modeling structural dependencies and temporal evolvin…
Scaling Up Graph Neural Networks Via Graph Coarsening
Zengfeng Huang, Shengzhong Zhang, Chong Xi +2
Scalability of graph neural networks remains one of the major challenges in graph machine learning. Since the representation of a node is computed by recursively aggregating and tr…
BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
Mingguo He, Zhewei Wei, Zengfeng Huang +1
Many representative graph neural networks, e.g., GPR-GNN and ChebNet, approximate graph convolutions with graph spectral filters. However, existing work either applies predefined f…
Learning Based Proximity Matrix Factorization for Node Embedding
Xingyi Zhang, Kun Xie, Sibo Wang +1
Node embedding learns a low-dimensional representation for each node in the graph. Recent progress on node embedding shows that proximity matrix factorization methods gain superb p…
Understanding Bandits with Graph Feedback
Houshuang Chen, Zengfeng Huang, Shuai Li +1
The bandit problem with graph feedback, proposed in [Mannor and Shamir, NeurIPS 2011], is modeled by a directed graph where is the collection of bandit arms, and once…
Effective Stabilized Self-Training on Few-Labeled Graph Data
Ziang Zhou, Jieming Shi, Shengzhong Zhang +2
Graph neural networks (GNNs) are designed for semi-supervised node classification on graphs where only a subset of nodes have class labels. However, under extreme cases when very f…