Heterogeneous Graph Information Bottleneck
Authors: Liang Yang, Fan Wu, Zichen Zheng, Bingxin Niu, Junhua Gu, Chuan Wang, Xiaochun Cao, Yuanfang Guo
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on real datasets demonstrate that the consensus-based unsupervised HGIB significantly outperforms most semi-supervised SOTA methods based on complementary assumption. |
| Researcher Affiliation | Academia | 1School of Artificial Intelligence & Hebei Province Key Laboratory of Big Data Calculation, Hebei University of Technology, Tianjin, China 2State Key Laboratory of Information Security, Institute of Information Engineering, CAS, Beijing, China 3State Key Laboratory of Software Development Environment, Beihang University, China yangliang@vip.qq.com, andyguo@buaa.edu.cn |
| Pseudocode | No | The paper describes the model and optimization steps mathematically and in text, but there are no formally labeled 'Algorithm' or 'Pseudocode' blocks. |
| Open Source Code | No | The paper does not provide any explicit statement about releasing source code or a link to a code repository. |
| Open Datasets | Yes | Datasets. Two citation network datasets ACM and DBLP, and a movie dataset IMDB, are employed for evaluation. The detailed descriptions of these heterogeneous graph data used in experiments are shown in Table 1. |
| Dataset Splits | Yes | The detailed descriptions of these heterogeneous graph data used in experiments are shown in Table 1. ... For classification task, we randomly draw out 20%, 40% and 60% of nodes for training the linear regression classifier. ... Table 1: Statistics of the datasets - Validation: ACM 300, DBLP 400, IMDB 300; Training & Testing: ACM 2,725, DBLP 3,657, IMDB 2,639 |
| Hardware Specification | No | The paper does not specify any hardware details (e.g., GPU/CPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions software components like 'Adam' optimizer and 'multi-layer perceptron (MLP)' but does not provide specific version numbers for any software dependencies. |
| Experiment Setup | Yes | The embedding dimension is set to 128 for all the above methods . Adam is employed as the optimizer. For IMDB and ACM, the learning rate is set to 10 3, and the encoder consists of two layers GCN with the output dimensions of two GCN layers are 512 and 128 respectively. For DBLP, the learning rate is set as the same as above but the output dimensions of the GCN layer are 256 and 128 respectively. The early stopping with patience of 30 is utilized. The hyper-parameter γ is always fixed as 10 3. |