Coupling Category Alignment for Graph Domain Adaptation

Authors: Nan Yin, Xiao Teng, Zhiguang Cao, Mengzhu Wang

IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on benchmark datasets validate the superiority of the proposed Co CA compared with baselines. Extensive experiments conducted on various datasets with domain shifts for graph classification demonstrate the superiority of proposed Co CA. Table 1, 2 and 3 show the comparison performance of Co CA and baselines on Mutagenicity, FRANKENSTEIN and NCI1 datasets under different domain shift. We conduct ablation experiments with various configurations. We investigate the influence of hyperparameters on the performance of the proposed Co CA.
Researcher Affiliation Academia 1Hong Kong University of Science and Technology 2Naval University of Engineering 3Singapore Management University 4Hebei University of Technology EMAIL, t EMAIL, EMAIL. All listed institutions are universities or public research institutions, indicating academic affiliations.
Pseudocode No The paper describes methods and processes in paragraph form and mathematical equations but does not include any clearly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not contain any explicit statement about releasing source code for the described methodology, nor does it provide a link to a code repository.
Open Datasets Yes We use 4 graph classification benchmarks: Mutagenicity (M) [Kazius et al., 2005], FRANKENSTEIN (F) [Orsini et al., 2015], NCI1 (N) [Wale et al., 2008], and PROTEINS (P) [Dobson and Doig, 2003], obtained from TUDataset [Morris et al., 2020] to evaluate the effectiveness of the Co CA.
Dataset Splits No To assess the domain shift in each dataset, we follow [Yin et al., 2023] and partition each dataset into four sub-datasets (D0, D1, D2, and D3, where D represents the respective dataset) based on edge and node density and graph flux. This describes domain partitioning, but not the explicit training/validation/test splits used for model evaluation within these domains.
Hardware Specification No The paper does not provide specific details about the hardware used to run the experiments, such as GPU or CPU models.
Software Dependencies No The paper does not specify any particular software dependencies with version numbers (e.g., programming languages, libraries, or frameworks with their versions) that would be needed to reproduce the experimental results.
Experiment Setup Yes We specifically examine the effects of two key hyperparameters, including the threshold ϑ in the branch coupling module for category alignment, and the shortest path length K in the SP branch. We report the results of ϑ and K in Figure 4. ϑ determines the number of reliable samples selected from each branch, and we vary ϑ in the range from 0.5 to 0.9...Therefore, we set ϑ to 0.7 as default. Additionally, the parameter K controls the number of shortest paths extracted in the SP branch, and we vary K in the range of {2, 3, 4, 5, 6}...we set K = 5.