CoFrNets: Interpretable Neural Architecture Inspired by Continued Fractions
Authors: Isha Puri, Amit Dhurandhar, Tejaswini Pedapati, Karthikeyan Shanmugam, Dennis Wei, Kush R. Varshney
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | On various regression and time-series forecasting tasks, we show that CoFRNets provide competitive performance when compared to other interpretable models and deep neural networks. |
| Researcher Affiliation | Academia | Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences |
| Pseudocode | No | The paper describes the architecture and its components using mathematical formulations and textual descriptions but does not include structured pseudocode or algorithm blocks. |
| Open Source Code | No | The code and data for CoFRNets will be made publicly available upon acceptance. |
| Open Datasets | Yes | We use a total of eight benchmark datasets for regression and time-series forecasting, including six UCI regression datasets (Concrete, Energy, Power Plant, Protein, Yacht, Wine) and two time-series datasets (Pollution, Electricity). |
| Dataset Splits | Yes | For all datasets, we train the models using 80% of the data for training, 10% for validation, and 10% for testing. |
| Hardware Specification | No | The paper mentions software details like PyTorch and Adam optimizer but does not provide any specific hardware details such as GPU/CPU models or other computing specifications used for experiments. |
| Software Dependencies | No | The paper states 'CoFRNets are implemented in PyTorch using the Adam optimizer' but does not provide specific version numbers for PyTorch or any other software dependencies. |
| Experiment Setup | Yes | For all datasets, we train the models using 80% of the data for training, 10% for validation, and 10% for testing. The models are trained for 200 epochs with a batch size of 64. The learning rate is initialized to 0.001 and decayed by a factor of 0.1 every 50 epochs. We use a weight decay of 0.0001 and a dropout rate of 0.1. |