Measuring Task Similarity and Its Implication in Fine-Tuning Graph Neural Networks
Authors: Renhong Huang, Jiarong Xu, Xin Jiang, Chenglu Pan, Zhiming Yang, Chunping Wang, Yang Yang
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The superiority of the presented fine-tuning strategy is validated via numerous experiments with different pre-trained models and downstream tasks. |
| Researcher Affiliation | Collaboration | Renhong Huang1, 2 , Jiarong Xu2 , Xin Jiang3, Chenglu Pan1, Zhiming Yang2, Chunping Wang4, Yang Yang1 1Zhejiang University, 2Fudan University, 3Lehigh University, 4Fin Volution Group |
| Pseudocode | No | The paper describes the steps of its method verbally and with equations but does not include a formal pseudocode block or an 'Algorithm' section. |
| Open Source Code | Yes | Our codes are available at https://github.com/zjunet/Bridge-Tune. |
| Open Datasets | Yes | Datasets. We use a total of 12 downstream datasets for evaluation: US-Airport, Brazil-Airport, Europe-Airport, H-index, Wisconsin, Texas, Cora, Cornell, DD242, DD68, DD687, and the large-scale dataset Ogbarxiv. |
| Dataset Splits | No | The paper mentions using 12 downstream datasets but does not explicitly provide the training, validation, and test dataset splits (e.g., percentages or sample counts). |
| Hardware Specification | No | The paper does not specify any hardware details such as GPU or CPU models used for the experiments. |
| Software Dependencies | No | The paper mentions pre-trained models and learning rates but does not list specific software dependencies with version numbers (e.g., Python, PyTorch, CUDA versions). |
| Experiment Setup | Yes | We set the learning rate as 5, 0.1, 0.1, 0.1 when fine-tuning GCC (Qiu et al. 2020), Graph CL (You et al. 2020), Edge Pred (Hamilton, Ying, and Leskovec 2017), and Context Pred (Hu et al. 2020b) respectively. We utilize mini-batch training and the batch size is 32. The total iterations of fine-tuning is 30, alternating between one iteration of pre-trained model refinement and one iteration of downstream fine-tuning. |