Uncertainty Aware Semi-Supervised Learning on Graph Data

Authors: Xujiang Zhao, Feng Chen, Shu Hu, Jin-Hee Cho

NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We validated the outperformance of our proposed model compared to the state-of-the-art counterparts in terms of misclassification detection and OOD detection based on six real network datasets.
Researcher Affiliation Academia 1The University of Texas at Dallas, {xujiang.zhao, feng,chen}@utdallas.edu 2University at Buffalo, SUNY, shuhu@buffalo.edu 3Virginia Tech, jicho@vt.edu
Pseudocode No The paper describes methods through text and equations but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes The source code and datasets are accessible at https://github.com/zxj32/uncertainty-GNN
Open Datasets Yes We used six datasets, including three citation network datasets [17] (i.e., Cora, Citeseer, Pubmed) and three new datasets [20] (i.e., Coauthor Physics, Amazon Computer, and Amazon Photo).
Dataset Splits No The paper refers to 'training nodes' and 'testing nodes' and mentions OOD categories, but it does not provide specific percentages or absolute counts for training, validation, or test splits in the main text. It defers some setup details to an appendix.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used to run the experiments.
Software Dependencies No The paper mentions implementing models based on GCN but does not list specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions or library versions).
Experiment Setup No The paper describes the loss function and optimization problem with trade-off parameters but does not provide concrete hyperparameter values (e.g., learning rate, batch size, specific values for λ1, λ2, or σ) in the main text, instead referring to an appendix for setup details.