Topology Optimization based Graph Convolutional Network

Authors: Liang Yang, Zesheng Kang, Xiaochun Cao, Di Jin, Bo Yang, Yuanfang Guo

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on real attributed networks demonstrate the superiority of the proposed TO-GCN against the state-of-the-art approaches.
Researcher Affiliation Academia Liang Yang1,2,3 , Zesheng Kang1 , Xiaochun Cao2 , Di Jin4 , Bo Yang5,3 and Yuanfang Guo6, 1School of Artificial Intelligence, Hebei University of Technology, China 2State Key Laboratory of Information Security, Institute of Information Engineering, CAS, China 3Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, China 4College of Intelligence and Computing, Tianjin University, China 5College of Computer Science and Technology, Jilin University, China 6School of Computer Science and Engineering, Beihang University, China
Pseudocode No The paper describes the optimization process and various mathematical derivations, but does not include structured pseudocode or an algorithm block.
Open Source Code No The paper does not provide any explicit statement about open-sourcing its code or a link to a code repository.
Open Datasets Yes As in previous work, three citation networks, in which the vertices and edges are documents and undirected citations respectively, are utilized for performance evaluation... The statistics of the networks, Cora, Cite Seer and Pub Med, are summarized in Table 2.
Dataset Splits Yes The performance of all the baseline methods are evaluated on 1,000 test nodes with 500 additional nodes for validation.
Hardware Specification No The paper does not provide any specific details regarding the hardware used for running the experiments.
Software Dependencies No The paper does not specify any software dependencies with version numbers.
Experiment Setup Yes To speedup the optimization, the refined network topology O is firstly initialized by minimizing Eq. (13) without considering the backward-propagation of the classification errors. Besides, the updating rule in Eq. (17) is only applied to update the weights of the existing edges and the must-link constraints, i.e., A + Q. Thus, the complexity of TO-GCN is O(M) instead of O(N 2), where N and M are the numbers of nodes and edges, respectively. ... Although the second and third terms in Eq. (14) both possess analytical solutions, the gradient decent approach is still adopted to optimize Eq. (14), because the first term does not have a close-form solution. ... α and λ, which are the hyperparameters for cannot-link and must-link constraints, are set according to the results of the validation set.