Generalized Taxonomy-Guided Graph Neural Networks
Authors: Yu Zhou, Di Jin, Jianguo Wei, Dongxiao He, Zhizhi Yu, Weixiong Zhang
IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on various real-world networks illustrate the effectiveness of TG-GNN over the state-of-the-art methods on scenarios involving incomplete taxonomies and inductive settings. |
| Researcher Affiliation | Academia | 1College of Intelligence and Computing, Tianjin University, Tianjin, China 2Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Kowloon, Hong Kong {zhouyu , jindi, jianguo, hedongxiao, yuzhizhi}@tju.edu.cn, weixiong.zhang@polyu.edu.hk |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide concrete access to source code for the described methodology. |
| Open Datasets | Yes | We used four real-world networks with taxonomies (Table 1). Aminer1 is a co-author network with the research topic taxonomy2, where node labels represent the types of conferences authors participate in. Patent3 is a patent citation dataset with the patent taxonomy, where the range of the patent generality index determines the node labels. Pub Med4 is a protein network with the disease taxonomy5, where a clustering algorithm on the protein network determines the node label. Yelp6 is a business network with the category taxonomy7, where node labels are determined by a clustering algorithm on the business network, which can be viewed as product themes. |
| Dataset Splits | Yes | Each dataset is divided into three distinct sets: training, validation, and testing, with allocation proportions of 60%, 20%, and 20%, respectively. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions software components like Word2Vec, GAT, and Adam optimizer, but does not provide specific version numbers for any of them or for broader libraries/frameworks like Python, PyTorch, or TensorFlow. |
| Experiment Setup | Yes | In taxonomy representation learning, we employed a self-supervised training approach to acquire representations for all taxonomy categories. Our approach uses a two-layer position-enhanced GAT, with the first layer comprising four attention heads and the second layer using one attention head. Both layers utilize 200-dimensional semantic embeddings and 50-dimensional position embeddings, with a dropout rate of 0.1 applied to the input feature vectors. Additionally, we utilized the Adam optimizer with an initial learning rate of 0.001. In network representation learning, we utilized two GAT layers along with three MRF layers and set the dropout ratio to 0.5 to prevent overfitting. |