Interpolation Consistency Training for Semi-supervised Learning

Authors: Vikas Verma, Alex Lamb, Juho Kannala, Yoshua Bengio, David Lopez-Paz

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments show that ICT achieves state-of-the-art performance when applied to standard neural network architectures on the CIFAR-10 and SVHN benchmark datasets.
Researcher Affiliation Collaboration 1Aalto University, Finland 2 Montreal Institute for Learning Algorithms (MILA) 3Facebook Artificial Intelligence Research (FAIR)
Pseudocode Yes Algorithm 1 The Interpolation Consistency Training (ICT) Algorithm
Open Source Code Yes 1Code available at https://github.com/vikasverma1077/ICT
Open Datasets Yes We follow the common practice in semi-supervised learning literature [...] and conduct experiments using the CIFAR-10 and SVHN datasets
Dataset Splits Yes The CIFAR-10 dataset consists of 60000 color images each of size 32 32, split between 50K training and 10K test images. [...] We select the best hyperparameter using a validation set of 5000 and 1000 labeled samples for CIFAR-10 and SVHN respectively.
Hardware Specification No The paper does not provide any specific details about the hardware (e.g., GPU, CPU models, or memory) used for running the experiments.
Software Dependencies No The paper mentions using SGD with Nesterov momentum optimizer and MSE loss but does not provide specific software names with version numbers for frameworks, libraries, or programming languages.
Experiment Setup Yes We used the SGD with nesterov momentum optimizer for all of our experiments. For the experiments in Table 1 and Table 2, we run the experiments for 400 epochs. [...] The initial learning rate was set to 0.1, [...] The momentum parameter was set to 0.9. We used an L2 regularization coefficient 0.0001 and a batch-size of 100 in our experiments.