Non-Compensatory Psychological Models for Recommender Systems
Authors: Chen Lin, Xiaolin Shen, Si Chen, Muhua Zhu, Yanghua Xiao4304-4311
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on real-world data sets validate that adopting non-compensatory rules improves recommendation performance for both rating and ranking models. |
| Researcher Affiliation | Collaboration | Chen Lin,1,3 Xiaolin Shen,1 Si Chen,1 Muhua Zhu,3 Yanghua Xiao2,3 1Department of Computer Science, Xiamen University, Xiamen, Fujian, China 2School of Computer Science, Fudan University, Shanghai, China 3Alibaba Group, Hangzhou, Zhejiang, China |
| Pseudocode | No | The information is insufficient. The paper describes the inference process and models using mathematical formulas and text, but does not provide any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The source codes are publicly available1. 1https://github.com/XMUDM/Non-Compensatory |
| Open Datasets | Yes | We use the standard benchmarks with user-item ratings. (1) Movielens2; (2) Filmtrust (Guo, Zhang, and Yorke-Smith 2013); and (3) Ciao DVD (Guo et al. 2014). (...) 2https://grouplens.org/datasets/movielens/ (...) 3https://ijcai-15.org/index.php/repeat-buyers-prediction-competition (...) 4http://2015.recsyschallenge.com |
| Dataset Splits | Yes | For each dataset, we reserve users with at least 5 ratings and randomly split 80% of the ratings as training set and 20% as test set. (...) The reported results are averaged using 5-fold cross validation. |
| Hardware Specification | No | The information is insufficient. The paper does not provide any specific details about the hardware (e.g., CPU, GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The information is insufficient. The paper does not specify any software libraries, frameworks, or their version numbers used in the implementation or for running experiments. |
| Experiment Setup | Yes | The same values of hyper-parameters are set for compensatory and non-compensatory models: for MF and MF-N K = 10, λU = λV = 0.01, Max Iter = 1000, for AMF and AMF-N K = 5, Max Iter = 100, for LLORMA and LLORMA-N K = 5, S = 50, λU = λV = 0.001, Max Iter = 100. The hyper-parameters are, K = 5, Max Iter = 100 for all models, for BPR and BPR-N λU = λV = 0.3, for FSBPR and FSBPR-N λU = λV = 0.01, for LCR and LCR-N S = 50, λU = λV = 10^-8. |