GraphSR: A Data Augmentation Algorithm for Imbalanced Node Classification

Authors: Mengting Zhou, Zhiguo Gong

AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments demonstrate the proposed approach outperforms the state-of-the-art baselines on various class-imbalanced datasets.
Researcher Affiliation Academia Mengting Zhou1,2, Zhiguo Gong1,2* 1State Key Laboratory of Internet of Things for Smart City, University of Macau, Macao 2 Guangdong-Macau Joint Laboratory for Advanced and Intelligent Computing
Pseudocode No The paper describes the methodology verbally and with equations but does not include any explicitly labeled or formatted pseudocode or algorithm blocks.
Open Source Code No The paper does not include an unambiguous statement about releasing code or a link to a source code repository for the described methodology.
Open Datasets Yes We evaluate Graph SR on several widely-used public datasets for node classification task: Cora, Cite Seer, Pub Med for citation networks (Sen et al. 2008).
Dataset Splits Yes All majority classes maintain 20 nodes in the training set, and the numbers for minority classes are 20 ρ, where ρ is the imbalanced ratio. When validating and testing, we sample the same numbers of nodes for all classes to make the validation and test set balanced.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper mentions models and techniques (GNNs, GCN, Graph SAGE, PPO, MLP) but does not provide specific software library names with version numbers (e.g., PyTorch 1.9, TensorFlow 2.x) that are needed to replicate the experiment.
Experiment Setup No The paper discusses general experimental settings like the imbalance ratio and components of the proposed method but does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs, optimizer settings) or detailed system-level training configurations.