HGMP: Heterogeneous Graph Multi-Task Prompt Learning
Authors: Pengfei Jiao, Jialong Ni, Di Jin, Xuan Guo, Huan Liu, Hongjiang Chen, Yanxian Bi
IJCAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on public datasets show that our proposed method adapts well to various tasks and significantly outperforms baseline methods. 5 Experiments This section presents experimental results and analyses to demonstrate the superiority of our approach. |
| Researcher Affiliation | Collaboration | 1School of Cyberspace Security,Hangzhou Dianzi University 2College of Intelligence and Computing,Tianjin University 3CETC Academy of Electronics and Information Technology Group,China Academy of Electronic and Information Technology |
| Pseudocode | No | The paper describes methods and processes using descriptive text and mathematical formulas (e.g., in Section 4.3 and 4.4), but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | No | For reproducibility, we provide the specific construction methods for each task and the detailed hyperparameter values in the supplement. This statement refers to methods and hyperparameters, not explicit source code release or a repository link. |
| Open Datasets | Yes | Datasets. We use two real-world HIN datasets, summarized in Table 1. (1) ACM [Lv et al., 2021] dataset is an academic network... (2) IMDB [Lv et al., 2021] dataset serves as a benchmark for graph neural networks... |
| Dataset Splits | Yes | For the few-shot setting, we evaluate tasks under a 10-shot configuration across three categories: node classification, edge classification, and graph classification. The task construction mainly follows the approach of Pro G [Sun et al., 2023a] works. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., GPU models, CPU types) used for the experiments. |
| Software Dependencies | No | The paper does not provide specific software names with version numbers for reproducibility. |
| Experiment Setup | No | For reproducibility, we provide the specific construction methods for each task and the detailed hyperparameter values in the supplement. While hyperparameters are mentioned, the explicit values are stated to be in the supplement, not in the main text. |