Few-Shot Learning with Graph Neural Networks

Authors: Victor Garcia Satorras, Joan Bruna Estrach

ICLR 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We validate experimentally the model on few-shot image classification, matching state-of-the-art performance with considerably fewer parameters, and demonstrate applications to semi-supervised and active learning setups. ... 6 EXPERIMENTS For the few-shot, semi-supervised and active learning experiments we used the Omniglot dataset presented by Lake et al. (2015) and Mini-Imagenet dataset introduced by Vinyals et al. (2016) which is a small version of ILSVRC-12 Krizhevsky et al. (2012).
Researcher Affiliation Academia Victor Garcia Amsterdam Machine Learning Lab University of Amsterdam Amsterdam, 1098 XH, NL v.garciasatorras@uva.nl Joan Bruna Courant Institute of Mathematical Sciences New York University New York City, NY, 10010, USA bruna@cims.nyu.edu
Pseudocode No The paper describes methods and architectures but does not include a clearly labeled pseudocode or algorithm block.
Open Source Code Yes Code available at: https://github.com/vgsatorras/few-shot-gnn
Open Datasets Yes For the few-shot, semi-supervised and active learning experiments we used the Omniglot dataset presented by Lake et al. (2015) and Mini-Imagenet dataset introduced by Vinyals et al. (2016)...
Dataset Splits Yes We used the splits proposed by Ravi & Larochelle (2016) of 64 classes for training, 16 for validation and 20 for testing. Using 64 classes for training, and the 16 validation classes only for early stopping and parameter tuning.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies with version numbers (e.g., Python, PyTorch, TensorFlow versions).
Experiment Setup No The paper describes the model architecture and data augmentation, but it lacks specific numerical hyperparameters such as learning rate, batch size, number of epochs, or detailed optimizer settings for reproducibility.