Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
Authors: Yunsheng Shi, Zhengjie Huang, Shikun Feng, Hui Zhong, Wenjing Wang, Yu Sun
IJCAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We evaluate our Uni MP model on three semi-supervised classification datasets in the Open Graph Benchmark (OGB), where our new methods achieve the new state-of-the-art results in all tasks, gaining 82.56% ACC in ogbn-products, 86.42% ROC-AUC in ogbn-proteins and 73.11% ACC in ogbn-arxiv. We also conduct ablation studies for our Uni MP model, to evaluate the effectiveness of our unified method. |
| Researcher Affiliation | Industry | Yunsheng Shi , Zhengjie Huang , Shikun Feng , Hui Zhong , Wenjing Wang , Yu Sun Baidu Inc., China |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper mentions 'open source codes' in the context of OGB leaderboard reproducibility, but it does not provide an explicit statement from the authors releasing their code or a specific link to their implementation's source code. |
| Open Datasets | Yes | Consequently, we conduct our experiments on the recently released datasets of Open Graph Benchmark (OGB) [Hu et al., 2020], which overcome the main drawbacks of commonly used datasets and thus are much more realistic and challenging. More details about these datasets are provided in appendix A in the supplementary file. |
| Dataset Splits | Yes | We set the hyper-parameter of our model for each dataset in Table 3, and the label rate means the percentage of labels we preserve during applying masked label prediction strategy. In ogbn-products dataset, we use Neighbor Sampling with size =10 for each layer to sample the subgraph during training and use full-batch for inference. In ogbn-proteins dataset, we use Random Partition to split the dense graph into subgraph to train and test our model. As for small-size ogbn-arxiv dataset, we just apply full batch for both training and test. Table 4: Results for ogbn-products (Validation Accuracy column). Table 5: Results for ogbn-proteins (Validation ROC-AUC column). Table 6: Results for ogbn-arxiv (Validation Accuracy column). |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments. |
| Software Dependencies | No | The paper mentions using 'Adam optimizer' but does not provide specific version numbers for any software libraries or dependencies (e.g., Python, PyTorch, TensorFlow versions). |
| Experiment Setup | Yes | We set the hyper-parameter of our model for each dataset in Table 3, and the label rate means the percentage of labels we preserve during applying masked label prediction strategy. We use Adam optimizer with lr = 0.001 to train our model. Specially, we set weight decay to 0.0005 for our model in small-size ogbn-arxiv dataset to prevent overfitting. Table 3: The hyper-paramerter setting of our model (num layers, hidden size, num heads, dropout, lr, weight decay, label rate columns). |