Hybrid Graph Neural Networks for Few-Shot Learning

Authors: Tianyuan Yu, Sen He, Yi-Zhe Song, Tao Xiang3179-3187

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments show that our HGNN obtains new state-of-the-art on three FSL benchmarks.
Researcher Affiliation Collaboration 1Center for Vision, Speech and Signal Processing, University of Surrey 2National University of Defense Technology 3i Fly Tek-Surrey Joint Research Centre on Artificial Intelligence
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes The code and models are available at https://github.com/Tianyuan Yu/HGNN.
Open Datasets Yes Three widely used FSL benchmarks, Mini Image Net (Vinyals et al. 2016), Tiered Image Net (Ren et al. 2018) and CUB-200-2011 (Wah et al. 2011) are used in our experiments.
Dataset Splits Yes Mini Image Net... consisting of 64 classes for training, and 16 classes and 20 classes for validation and testing respectively.
Hardware Specification No The paper does not provide specific hardware details such as GPU/CPU models or processor types used for running experiments.
Software Dependencies No The paper mentions the use of various models and networks (e.g., CNNs, GNNs) but does not provide specific software dependencies or library version numbers required for replication.
Experiment Setup No The paper describes the overall training objectives, model architecture, and general training process (e.g., use of cross-entropy losses, end-to-end training, meta-learning setup) but does not provide concrete numerical values for hyperparameters like learning rate, batch size, or number of epochs.