Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data
Authors: Lan-Zhe Guo, Zhen-Yu Zhang, Yuan Jiang, Yu-Feng Li, Zhi-Hua Zhou
ICML 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | To validate the effectiveness of the proposed method, we conduct experiments on two standard MNIST and CIFAR benchmarks for semi-supervised image classification using deep convolutional neural networks (CNNs). |
| Researcher Affiliation | Academia | 1National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China. |
| Pseudocode | Yes | Algorithm 1 The DS3L Learning Framework |
| Open Source Code | Yes | The code for the work is readily available and freely downloaded at https://www.lamda.nju.edu.cn/code DS3L.ashx. |
| Open Datasets | Yes | To validate the effectiveness of the proposed method, we conduct experiments on two standard MNIST and CIFAR benchmarks for semi-supervised image classification using deep convolutional neural networks (CNNs). |
| Dataset Splits | No | The paper describes the construction of labeled and unlabeled training data, and refers to a 'test' set, but does not explicitly provide information about a separate 'validation' dataset split or percentage. |
| Hardware Specification | No | The paper does not provide specific hardware details such as GPU models, CPU types, or cloud instance specifications used for running experiments. |
| Software Dependencies | No | The paper mentions popular deep learning frameworks like Pytorch and Tensorflow but does not specify their version numbers or other ancillary software dependencies with versions. |
| Experiment Setup | Yes | The networks are trained using stochastic gradient descent (SGD) methods with a learning rate 1e 3. We train the model for 200,000 updates with a batch size of 100. |