Decentralized Unsupervised Learning of Visual Representations

Authors: Yawen Wu, Zhepeng Wang, Dewen Zeng, Meng Li, Yiyu Shi, Jingtong Hu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments show the effectiveness of the proposed framework. It outperforms other methods by 11% on IID data and matches the performance of centralized learning.
Researcher Affiliation Collaboration Yawen Wu1 , Zhepeng Wang2 , Dewen Zeng3 , Meng Li4 , Yiyu Shi3 and Jingtong Hu1 1University of Pittsburgh 2George Mason University 3University of Notre Dame 4Facebook
Pseudocode No The paper describes the proposed methods using natural language and mathematical equations but does not include any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any statement about making its source code available, nor does it provide a link to a code repository.
Open Datasets Yes We evaluate the proposed approaches on three datasets, including CIFAR-10 [Krizhevsky et al., 2009], CIFAR-100 [Krizhevsky et al., 2009], and Fashion-MNIST [Xiao et al., 2017].
Dataset Splits No The paper mentions training on "100% labeled dataset" for linear evaluation and "10% or 1% labeled data" for semi-supervised learning. It also states "The detailed collaborative learning settings and training details can be found in the Appendix." However, the provided text does not explicitly specify the training, validation, and test splits (e.g., 80/10/10) for the main self-supervised learning phase or how the subsets of labeled data are partitioned for validation within the provided text.
Hardware Specification No The paper does not specify any hardware details such as GPU models, CPU types, or memory used for running the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python, PyTorch, CUDA versions).
Experiment Setup Yes We use Res Net-18 as the base encoder and use a 2-layer MLP to project the representations to 128-dimensional feature space [Chen et al., 2020a; He et al., 2020]. The classifier is trained for 100 epochs by the SGD optimizer following the hyper-parameters from [He et al., 2020]. Then we append a linear classifier to the encoder and finetune the whole model on 10% or 1% labeled data for 20 epochs with SGD optimizer following the hyper-parameters from [Caron et al., 2020]. The detailed collaborative learning settings and training details can be found in the Appendix.