On the Representation Power of Set Pooling Networks

Authors: Christian Bueno, Alan Hylton

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our theoretical findings are supported by empirical results on various set learning tasks. Finally, we empirically validate our theoretical findings through experiments on diverse set learning tasks, including set classification, set anomaly detection, and point cloud classification.
Researcher Affiliation Academia The authors are listed as "Anonymous Authors", therefore, no clear institutional affiliations are provided to classify the affiliation type.
Pseudocode No The paper describes theoretical constructions and experimental procedures but does not include structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement or link for the open-source code of the methodology described.
Open Datasets Yes Datasets: We use the following datasets: MNIST digits subsets, KDD99, ModelNet40.
Dataset Splits Yes We use a standard train-validation-test split (80/10/10) for all datasets.
Hardware Specification Yes All experiments are run on a single NVIDIA V100 GPU.
Software Dependencies No The paper mentions using the Adam optimizer, but does not provide specific version numbers for software dependencies or libraries used for implementation.
Experiment Setup Yes Models are trained using the Adam optimizer with a learning rate of 0.001 and a batch size of 64. Training runs for 100 epochs.