TY - GEN
T1 - Graph Reciprocal Neural Networks by Abstracting Node as Attribute
AU - Yang, Liang
AU - Wang, Jiayi
AU - He, Dongxiao
AU - Wang, Chuan
AU - Cao, Xiaochun
AU - Niu, Bingxin
AU - Wang, Zhen
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Graph neural network (GNN) can be formulated as the multiplication of the topology-related matrix (adjacency or Laplacian matrix) and node attribute matrix, i.e., operation in node-wise. Unfortunately, this unified formula reveals two inherent drawbacks. Firstly, the topology and node attribute are not reciprocal but biased. From employment, the topology information is repeatedly employed, while the node attribute is only used once. From parameterization perspective, the node attribute is parameterized with highly expressive MLPs, while topology is not. Secondly, the graph topology can not be fully explored. Only the local pairwise relation is explored, but the mesoscopic community structure, which is one of the most prominent characteristics of networks, is ignored. To alleviate these issues, this paper proposes the Graph Reciprocal Network (GRN) by treating node attribute and topology reciprocal. Firstly, it is illustrated that the node can be regarded and utilized as another kind of attribute. Secondly, a novel node representation scheme is proposed from the theory of Quadratic Networks, with a theoretical guarantee of the fine-grained element-wise product of the representations of the topology and attribute. Extensive experiments demonstrate the superior performance and robustness of the proposed GRN.
AB - Graph neural network (GNN) can be formulated as the multiplication of the topology-related matrix (adjacency or Laplacian matrix) and node attribute matrix, i.e., operation in node-wise. Unfortunately, this unified formula reveals two inherent drawbacks. Firstly, the topology and node attribute are not reciprocal but biased. From employment, the topology information is repeatedly employed, while the node attribute is only used once. From parameterization perspective, the node attribute is parameterized with highly expressive MLPs, while topology is not. Secondly, the graph topology can not be fully explored. Only the local pairwise relation is explored, but the mesoscopic community structure, which is one of the most prominent characteristics of networks, is ignored. To alleviate these issues, this paper proposes the Graph Reciprocal Network (GRN) by treating node attribute and topology reciprocal. Firstly, it is illustrated that the node can be regarded and utilized as another kind of attribute. Secondly, a novel node representation scheme is proposed from the theory of Quadratic Networks, with a theoretical guarantee of the fine-grained element-wise product of the representations of the topology and attribute. Extensive experiments demonstrate the superior performance and robustness of the proposed GRN.
KW - community structure
KW - graph neural networks
KW - node attribute
KW - parameterization
KW - quadratic networks
UR - http://www.scopus.com/inward/record.url?scp=85185408370&partnerID=8YFLogxK
U2 - 10.1109/ICDM58522.2023.00192
DO - 10.1109/ICDM58522.2023.00192
M3 - 会议稿件
AN - SCOPUS:85185408370
T3 - Proceedings - IEEE International Conference on Data Mining, ICDM
SP - 1463
EP - 1468
BT - Proceedings - 23rd IEEE International Conference on Data Mining, ICDM 2023
A2 - Chen, Guihai
A2 - Khan, Latifur
A2 - Gao, Xiaofeng
A2 - Qiu, Meikang
A2 - Pedrycz, Witold
A2 - Wu, Xindong
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 23rd IEEE International Conference on Data Mining, ICDM 2023
Y2 - 1 December 2023 through 4 December 2023
ER -