Multi-output Polynomial Networks and Factorization Machines

Authors: Mathieu Blondel, Vlad Niculae, Takuma Otsuka, Naonori Ueda

NeurIPS 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 6 Experimental results
Researcher Affiliation Collaboration Mathieu Blondel NTT Communication Science Laboratories Kyoto, Japan mathieu@mblondel.org Vlad Niculae Cornell University Ithaca, NY vlad@cs.cornell.edu Takuma Otsuka NTT Communication Science Laboratories Kyoto, Japan otsuka.takuma@lab.ntt.co.jp Naonori Ueda NTT Communication Science Laboratories RIKEN Kyoto, Japan ueda.naonori@lab.ntt.co.jp
Pseudocode Yes Algorithm 1 Multi-output PN/FM training
Open Source Code No The paper does not contain an explicit statement that the authors are releasing their code or a direct link to a source code repository for the methodology described.
Open Datasets Yes For our multi-class experiments, we use four publicly-available datasets: segment (7 classes), vowel (11 classes), satimage (6 classes) and letter (26 classes) [12]. For our recommendation system experiments, we use the Movie Lens 100k and 1M datasets [14].
Dataset Splits Yes Throughout our experiments, we use 50% of the data for training, 25% for validation, and 25% for evaluation.
Hardware Specification No The paper does not provide specific hardware details (exact GPU/CPU models, processor types with speeds, memory amounts, or detailed computer specifications) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment.
Experiment Setup No The paper mentions using a multi-class logistic loss and that hyperparameters were chosen to maximize validation accuracy, but it does not provide concrete hyperparameter values, training configurations, or system-level settings.