Multi-output Polynomial Networks and Factorization Machines
Authors: Mathieu Blondel, Vlad Niculae, Takuma Otsuka, Naonori Ueda
NeurIPS 2017 | Venue 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 EMAIL Vlad Niculae Cornell University Ithaca, NY EMAIL Takuma Otsuka NTT Communication Science Laboratories Kyoto, Japan EMAIL Naonori Ueda NTT Communication Science Laboratories RIKEN Kyoto, Japan EMAIL |
| 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. |