Directed Graph Convolutional Network

Tong, Zekun; Liang, Yuxuan; Sun, Changsheng; Rosenblum, David S.; Lim, Andrew

doi:10.48550/arxiv.2004.13970

Cited by 29 publications

(43 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GraphSAGE [1] aggregates and updates features in a range of the two-hop neighbors to the center node. DGCN [8] considers the first-and second-order proximity to aggregate the attributes on the directed graphs. However, these message aggregators collect information from all neighbors equally, ignoring the relative importance of different neighbor nodes.…”

Section: Graph Neural Networkmentioning

confidence: 99%

“…Graph neural networks (GNNs) offer effective graph-based techniques applied to solve abundant real-world problems in diverse fields, such as social science [1], physical systems [2,3], protein-protein interaction networks [4], brain neuroscience [5], knowledge graphs [6], etc. The power of current GNNs [1,7,8,9,10] is largely due to their message-passing mechanisms. However, the underlying behavior that spontaneously aggregates messages on the graph structure is obscure.…”

Section: Introductionmentioning

confidence: 99%

“…In some research [1,7,8], messages were passed along edges uniformly without accounting for priority of either graph structure or node attributes. Intuitively, each neighbor node's impact was distinctive to the center node in the node classification task.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification

Yan¹,

Liu²

2022

Preprint

View full text Add to dashboard Cite

Graph neural networks can be effectively applied to find solutions for many real-world problems across widely diverse fields. The success of graph neural networks is linked to the message-passing mechanism on the graph, however the message-aggregating behavior is still not entirely clear in most algorithms. To improve functionality, we propose a new transparent network called Graph Decipher to investigate the message-passing mechanism by prioritizing in two main components: the graph structure and node attributes, at the graph, feature, and global levels on a graph under the node classification task. However the computation burden now becomes the most significant issue because the relevance of both graph structure and node attributes are computed on a graph. In order to solve this issue, only relevant representative node attributes are extracted by graph feature filters, allowing calculations to be performed in a category-oriented manner. Experiments on seven datasets show that Graph Decipher achieves state-of-the-art performance while imposing a substantially lower computation burden under the node classification task. Additionally, since our algorithm has the ability to explore the representative node attributes by category, it is utilized to alleviate the imbalanced node classification problem on multi-class graph datasets.

show abstract

Section: Graph Neural Networkmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification

Yan¹,

Liu²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…• General GNNs: GCN [17], ChebyNet [8], GAT [33], Graph-SAGE (Mean aggregation) [14], APPNP [18], and jumping knowledge networks (GCN+JK, GCN+r) [35], where GCN+r only integrates knowledge from the input features. • Digraph GNNs: DGCN [32], DiGCN and DiGCN-IB [31].…”

Section: Baselinesmentioning

confidence: 99%

Graph Neural Networks with Feature and Structure Aware Random Walk

Zhuo¹,

Yu²,

Tan³

2021

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have received increasing attention for representation learning in various machine learning tasks. However, most existing GNNs applying neighborhood aggregation usually perform poorly on the graph with heterophily where adjacent nodes belong to different classes. In this paper, we show that in typical heterphilous graphs, the edges may be directed, and whether to treat the edges as is or simply make them undirected greatly affects the performance of the GNN models. Furthermore, due to the limitation of heterophily, it is highly beneficial for the nodes to aggregate messages from similar nodes beyond local neighborhood.These motivate us to develop a model that adaptively learns the directionality of the graph, and exploits the underlying long-distance correlations between nodes. We first generalize the graph Laplacian to digraph based on the proposed Feature-Aware PageRank algorithm, which simultaneously considers the graph directionality and long-distance feature similarity between nodes. Then digraph Laplacian defines a graph propagation matrix that leads to a model called DiglacianGCN. Based on this, we further leverage the node proximity measured by commute times between nodes, in order to preserve the nodes' long-distance correlation on the topology level. Extensive experiments on ten datasets with different levels of homophily demonstrate the effectiveness of our method over existing solutions in the task of node classification. CCS CONCEPTS• Mathematics of computing → Graph algorithms; • Computing methodologies → Learning latent representations; Neural networks.

show abstract

“…In addition, the edges in a CPS graph often have physical directions to propagating information. That caused "feature mismatching" [10,11] when modelling by normal GCNs, and several methods [12,13,14] have studied directed graph modeling as remedies.…”

Section: Introductionmentioning

confidence: 99%

Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems

Zheng

Guo

Yang

et al. 2021

Preprint

View full text Add to dashboard Cite

Multi-agent control is a central theme in the Cyber-Physical Systems (CPS). However, current control methods either receive non-Markovian states due to insufficient sensing and decentralized design, or suffer from poor convergence. This paper presents the Delayed Propagation Transformer (DePT), a new transformerbased model that specializes in the global modeling of CPS while taking into account the immutable constraints from the physical world. DePT induces a cone-shaped spatial-temporal attention prior, which injects the information propagation and aggregation principles and enables a global view. With physical constraint inductive bias baked into its design, our DePT is ready to plug and play for a broad class of multi-agent systems. The experimental results on one of the most challenging CPS -network-scale traffic signal control system in the open world -show that our model outperformed the state-of-the-art expert methods on synthetic and real-world datasets. Our codes are released at: https://github.com/VITA-Group/DePT.

show abstract

Directed Graph Convolutional Network

Cited by 29 publications

References 17 publications

Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification

Graph Decipher: A transparent dual-attention graph neural network to understand the message-passing mechanism for the node classification

Graph Neural Networks with Feature and Structure Aware Random Walk

Delayed Propagation Transformer: A Universal Computation Engine towards Practical Control in Cyber-Physical Systems

Contact Info

Product

Resources

About