COT: Contextual Operating Tensor for Context-Aware Recommender Systems
Authors: Qiang Liu, Shu Wu, Liang Wang
AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results show that the proposed COT model yields significant improvements over the competitive compared methods on three typical datasets, i.e., Food, Adom and Movielens-1M datasets. |
| Researcher Affiliation | Academia | Qiang Liu, Shu Wu, Liang Wang Center for Research on Intelligent Perception and Computing, National Laboratory of Pattern Recognition Institute of Automation, Chinese Academy of Sciences, China {qiang.liu, shu.wu, wangliang}@nlpr.ia.ac.cn |
| Pseudocode | No | The paper provides mathematical formulations and equations for its model and parameter inference, but no explicit pseudocode or algorithm blocks are present. |
| Open Source Code | No | The paper provides links to third-party resources (datasets and Lib FM) used in their experiments, but does not include any statement or link indicating that the authors' own source code for the COT model is openly available. |
| Open Datasets | Yes | Our experiments are conducted on three real datasets. Food dataset (Ono et al. 2009)... Adom dataset (Adomavicius et al. 2005)... Movielens-1M is collected from a movie recommender system Movielens2. |
| Dataset Splits | No | The paper specifies 'All Users' and 'Cold Start' splitting methodologies into train and test sets, with 90% for train and 10% for test. However, it does not explicitly define a separate 'validation' dataset split for hyperparameter tuning or early stopping during training. |
| Hardware Specification | No | The paper does not provide specific details on the hardware used for running experiments, such as GPU or CPU models, memory, or cloud computing instance types. |
| Software Dependencies | No | The paper mentions using 'Lib FM' for implementation but does not specify its version number or any other software dependencies with their respective versions. |
| Experiment Setup | Yes | We use the most popular metrics, Root Mean Square Error (RMSE) and Mean Average Precision (MAE)... λ is a parameter to control the regularizations, which can be determined using 5-fold cross validation... The value of RMSE decreases at first, then stays nearly stable after d = 5 and dc = 3... we only illustrate the results with d = 8 and dc = 4 on three datasets for simplicity. |