59 citations · 387 across the 30 of their papers we have counts for
23 papers · 1 filter
Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power
Junru Zhou, Jiarui Feng, Xiyuan Wang +1
The ability of graph neural networks (GNNs) to count certain graph substructures, especially cycles, is important for the success of GNNs on a wide range of tasks. It has been rece…
VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
Ling Yang, Ye Tian, Minkai Xu +7
GNN-to-MLP distillation aims to utilize knowledge distillation (KD) to learn computationally-efficient multi-layer perceptron (student MLP) on graph data by mimicking the output re…
From Relational Pooling to Subgraph GNNs: A Universal Framework for More Expressive Graph Neural Networks
Cai Zhou, Xiyuan Wang, Muhan Zhang
Relational pooling is a framework for building more expressive and permutation-invariant graph neural networks. However, there is limited understanding of the exact enhancement in…
Improving Graph Neural Networks on Multi-node Tasks with the Labeling Trick
Xiyuan Wang, Pan Li, Muhan Zhang
In this paper, we study using graph neural networks (GNNs) for \textit{multi-node representation learning}, where a representation for a set of more than one node (such as a link)…
An Empirical Study of Realized GNN Expressiveness
Yanbo Wang, Muhan Zhang
Research on the theoretical expressiveness of Graph Neural Networks (GNNs) has developed rapidly, and many methods have been proposed to enhance the expressiveness. However, most m…
An Efficient Subgraph GNN with Provable Substructure Counting Power
Zuoyu Yan, Junru Zhou, Liangcai Gao +2
We investigate the enhancement of graph neural networks' (GNNs) representation power through their ability in substructure counting. Recent advances have seen the adoption of subgr…
SUREL+: Moving from Walks to Sets for Scalable Subgraph-based Graph Representation Learning
Haoteng Yin, Muhan Zhang, Jianguo Wang +1
Subgraph-based graph representation learning (SGRL) has recently emerged as a powerful tool in many prediction tasks on graphs due to its advantages in model expressiveness and gen…
Is Distance Matrix Enough for Geometric Deep Learning?
Zian Li, Xiyuan Wang, Yinan Huang +1
Graph Neural Networks (GNNs) are often used for tasks involving the 3D geometry of a given graph, such as molecular dynamics simulation. While incorporating Euclidean distance into…
Neural Common Neighbor with Completion for Link Prediction
Xiyuan Wang, Haotong Yang, Muhan Zhang
In this work, we propose a novel link prediction model and further boost it by studying graph incompleteness. First, we introduce MPNN-then-SF, an innovative architecture leveragin…
Boosting the Cycle Counting Power of Graph Neural Networks with I-GNNs
Yinan Huang, Xingang Peng, Jianzhu Ma +1
Message Passing Neural Networks (MPNNs) are a widely used class of Graph Neural Networks (GNNs). The limited representational power of MPNNs inspires the study of provably powerful…
Geodesic Graph Neural Network for Efficient Graph Representation Learning
Lecheng Kong, Yixin Chen, Muhan Zhang
Graph Neural Networks (GNNs) have recently been applied to graph learning tasks and achieved state-of-the-art (SOTA) results. However, many competitive methods run GNNs multiple ti…
Graph Neural Network with Local Frame for Molecular Potential Energy Surface
Xiyuan Wang, Muhan Zhang
Modeling molecular potential energy surface is of pivotal importance in science. Graph Neural Networks have shown great success in this field. However, their message passing scheme…
Two-Dimensional Weisfeiler-Lehman Graph Neural Networks for Link Prediction
Yang Hu, Xiyuan Wang, Zhouchen Lin +2
Link prediction is one important application of graph neural networks (GNNs). Most existing GNNs for link prediction are based on one-dimensional Weisfeiler-Lehman (1-WL) test. 1-W…
How Powerful are Spectral Graph Neural Networks
Xiyuan Wang, Muhan Zhang
Spectral Graph Neural Network is a kind of Graph Neural Network (GNN) based on graph signal filters. Some models able to learn arbitrary spectral filters have emerged recently. How…
How Powerful are K-hop Message Passing Graph Neural Networks
Jiarui Feng, Yixin Chen, Fuhai Li +2
The most popular design paradigm for Graph Neural Networks (GNNs) is 1-hop message passing -- aggregating information from 1-hop neighbors repeatedly. However, the expressive power…
Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networks
Haorui Wang, Haoteng Yin, Muhan Zhang +1
Graph neural networks (GNN) have shown great advantages in many graph-based learning tasks but often fail to predict accurately for a task-based on sets of nodes such as link/motif…
Algorithm and System Co-design for Efficient Subgraph-based Graph Representation Learning
Haoteng Yin, Muhan Zhang, Yanbang Wang +2
Subgraph-based graph representation learning (SGRL) has been recently proposed to deal with some fundamental challenges encountered by canonical graph neural networks (GNNs), and h…
Decoupling the Depth and Scope of Graph Neural Networks
Hanqing Zeng, Muhan Zhang, Yinglong Xia +6
State-of-the-art Graph Neural Networks (GNNs) have limited scalability with respect to the graph and model sizes. On large graphs, increasing the model depth often means exponentia…
Efficient Dynamic Graph Representation Learning at Scale
Xinshi Chen, Yan Zhu, Haowen Xu +4
Dynamic graphs with ordered sequences of events between nodes are prevalent in real-world industrial applications such as e-commerce and social platforms. However, representation l…
Network In Graph Neural Network
Xiang Song, Runjie Ma, Jiahang Li +2
Graph Neural Networks (GNNs) have shown success in learning from graph structured data containing node/edge feature information, with application to social networks, recommendation…
Nested Graph Neural Networks
Muhan Zhang, Pan Li
Graph neural network (GNN)'s success in graph classification is closely related to the Weisfeiler-Lehman (1-WL) algorithm. By iteratively aggregating neighboring node features to a…
Deep Graph Neural Networks with Shallow Subgraph Samplers
Hanqing Zeng, Muhan Zhang, Yinglong Xia +6
While Graph Neural Networks (GNNs) are powerful models for learning representations on graphs, most state-of-the-art models do not have significant accuracy gain beyond two to thre…
Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
Muhan Zhang, Pan Li, Yinglong Xia +2
In this paper, we provide a theory of using graph neural networks (GNNs) for multi-node representation learning (where we are interested in learning a representation for a set of m…