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 [1].
Information-Theoretic Generalization Bounds for Transductive Learning and its Applications
Authors: Huayi Tang, Yong Liu
JMLR 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Lastly, we use the theoretical results to derive upper bounds for adaptive optimization algorithms under the transductive learning setting. We also apply them to semi-supervised learning and transductive graph learning scenarios, meanwhile validating the derived bounds by experiments on synthetic and real-world datasets. |
| Researcher Affiliation | Academia | Huayi Tang EMAIL Gaoling School of Artificial Intelligence Renmin University of China Beijing, 100872, China Yong Liu EMAIL Gaoling School of Artificial Intelligence Renmin University of China Beijing, 100872, China |
| Pseudocode | No | The paper describes methods and procedures through mathematical derivations and textual explanations, but no explicit pseudocode blocks or algorithms are presented. |
| Open Source Code | No | The paper does not contain any explicit statements or links indicating the release of source code for the described methodology. |
| Open Datasets | Yes | For semi-supervised learning, we select image classification on the MNIST and CIFAR-10 datasets as learning tasks... Specifically, we use c SBMs (Deshpande et al., 2018) as synthetic data and Cora, Cite Seer (Sen et al., 2008; Yang et al., 2016), Actor, and Chameleon as real-world data. |
| Dataset Splits | Yes | Recall that the number of training data points is defined by m n k+1. To ensure that m N+, we set k = 1 for Cora and Actor, and k = 2 for Cite Seer and Chameleon. |
| Hardware Specification | No | The paper does not provide specific details about the hardware used for running the experiments, such as GPU or CPU models. It only mentions using 'Public Computing Cloud' in the acknowledgements, which is not specific enough. |
| Software Dependencies | No | The paper mentions using the 'Adam optimizer' and 'Re LU' activation function, and refers to models like 'GAT' and 'GPR-GNN', but it does not specify any software libraries or frameworks with their version numbers (e.g., PyTorch 1.x, TensorFlow 2.x, Python 3.x). |
| Experiment Setup | Yes | For both datasets, we train the model for 1000 iterations using the Adam optimizer. The learning rate is set to 0.001, and each mini-batch contains 128 images. |