Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Hypergraph Self-supervised Learning with Sampling-efficient Signals
Authors: Fan Li, Xiaoyang Wang, Dawei Cheng, Wenjie Zhang, Ying Zhang, Xuemin Lin
IJCAI 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Through comprehensive experiments on 7 real-world hypergraphs, we demonstrate the superiority of our approach over the state-of-the-art method in terms of both effectiveness and efficiency. (Abstract) and In this section, We first briefly introduce the experimental setups. Subsequently, we conduct extensive experiments to validate the effectiveness and efficiency of our model. (Section 4 Introduction) |
| Researcher Affiliation | Academia | 1University of New South Wales, Sydney, Australia 2Tongji University, Shanghai, China 3University of Technology Sydney, Sydney, Australia 4Shanghai Jiaotong University, Shanghai, China |
| Pseudocode | No | The paper describes its methods using prose, equations, and figures (e.g., Figure 1), but does not contain a distinct block or section labeled 'Pseudocode' or 'Algorithm'. |
| Open Source Code | Yes | We have released our code in https://github.com/Coco-Hut/SE-HSSL. |
| Open Datasets | Yes | We empirically evaluate the model performance on 7 commonly used hypergraph benchmark datasets, whose details are shown in Table 1. and Table 1 lists datasets like Cora [Wei et al., 2022] citation, Citeseer [Wei et al., 2022] citation, Pubmed [Wei et al., 2022] citation, Cora-CA [Yadati et al., 2019] co-author, NTU2012 [Yang et al., 2022] graphics, Model Net40 [Yang et al., 2022] graphics, Zoo [Hein et al., 2013] animal. |
| Dataset Splits | Yes | Specifically, we first train the hypergraph encoder in a self-supervised manner as described in Section 3. Afterward, with the trained model, we generate node embeddings and randomly split them into training, validation, and test samples using splitting percentages of 10%, 10%, and 80%, respectively. |
| Hardware Specification | No | The paper discusses the efficiency of its model in terms of training time but does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used for the experiments. |
| Software Dependencies | No | The paper mentions using a 'logistic regression classifier' and refers to various models (e.g., HGNN, DCCA) and libraries (e.g., PRe LU nonlinear activation function) but does not provide specific version numbers for any software dependencies. |
| Experiment Setup | Yes | For SE-HSSL, we set the number of encoder layers to 1 for all datasets. We set the group-level coefficient λ1 = 1 and regularization coefficient λ3 = 0.05. The sampling number d in each membership set is fixed to 10. The membership-level coefficient λ2 is tuned over {0.1, 0.18, 0.20} . Besides, we tune the embedding size D in {256, 512, 784, 1024}, the hyperedge hop K in {1, 2, 3, 4}, the temperature τ in {0.4, 0.5, 0.6}, and threshold α in {0.62, 0.65}. |