Rank and Align: Towards Effective Source-free Graph Domain Adaptation

Authors: Junyu Luo, Zhiping Xiao, Yifan Wang, Xiao Luo, Jingyang Yuan, Wei Ju, Langechuan Liu, Ming Zhang

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed RNA.
Researcher Affiliation Collaboration Junyu Luo1 , Zhiping Xiao2 , Yifan Wang3 , Xiao Luo2 , Jingyang Yuan1 , Wei Ju1 , Langechuan Liu4 and Ming Zhang1 1 School of Computer Science, National Key Laboratory for Multimedia Information Processing Peking University-Anker Embodied AI Lab, Peking University, Beijing 2 University of California, Los Angeles 3 University of International Business and Economics 4 Anker Innovations
Pseudocode Yes Algorithm 1 Optimization Algorithm of RNA
Open Source Code No The paper does not provide any concrete access information (specific repository link, explicit code release statement, or code in supplementary materials) for the source code of the methodology described.
Open Datasets Yes Datasets. We perform experiments with practical sourcefree domain adaptation settings and benchmark datasets. We test our RNA in cross-dataset and split-dataset scenarios. For biochemical datasets, e.g., Mutagenicity [Kazius et al., 2005], PROTEINS [Borgwardt et al., 2005], and FRANKENSTEIN [Orsini et al., 2015]. Furthermore, we test our method on the sub-datasets of the COX2 [Sutherland et al., 2003] and BZR [Sutherland et al., 2003] datasets.
Dataset Splits No The paper mentions using specific datasets but does not provide specific percentages or counts for train/validation/test splits. It also does not explicitly state how the data was partitioned for training and validation, or refer to standard predefined splits for its experimental setup.
Hardware Specification No The paper does not provide any specific hardware details such as GPU/CPU models, processor types, or memory amounts used for running its experiments.
Software Dependencies No The paper mentions using a GCN encoder and Adam optimizer but does not provide specific version numbers for any software libraries or dependencies, such as Python, PyTorch, TensorFlow, or CUDA.
Experiment Setup Yes For RNA, we encode the graph data with a 2-layer GCN encoder, with an embedding dimension of 128. We optimize the model with an Adam optimizer with a mini-batch of 128 and a learning rate of 0.001. The model is initialized with 100 epochs of pre-training on the source domain In domain adaptation, the harmonic set ratio is 40%. To reduce randomness, we perform 5 runs and report the average accuracy.