MLP4Rec: A Pure MLP Architecture for Sequential Recommendations
Authors: Muyang Li, Xiangyu Zhao, Chuan Lyu, Minghao Zhao, Runze Wu, Ruocheng Guo
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments demonstrate the effectiveness of MLP4Rec over various representative baselines upon two benchmark datasets. |
| Researcher Affiliation | Collaboration | 1University of Sydney 2City University of Hong Kong 3Zhejiang University 4Fuxi AI Lab, Netease 5Bytedance AI Lab |
| Pseudocode | No | No structured pseudocode or algorithm blocks were found. |
| Open Source Code | Yes | The implementation code is available online3. 3https://github.com/Li-Muyang/MLP4Rec |
| Open Datasets | Yes | (1) Movie Lens1: Movie Lens is a site for recommending movies to users given their historical ratings, which is now one of the most commonly used benchmarks across the field of recommender system. We use Movie Lens-100k in our experiments. (2) Amazon Beauty2: The online reviews and ratings of Amazon. We use the Beauty category in our experiments. 1https://grouplens.org/datasets/movielens/100k/ 2http://jmcauley.ucsd.edu/data/amazon/ |
| Dataset Splits | Yes | For dataset splitting, the next-item prediction task uses the last item in an interaction sequence as the test set, the item before as the validation set, and the rest of the items will be used as the training set. |
| Hardware Specification | No | No specific hardware details (e.g., GPU/CPU models, memory) used for running experiments were mentioned. |
| Software Dependencies | No | The paper mentions 'Rec Bole s library' and 'Adam optimizer' but does not provide specific version numbers for these or any other software dependencies like Python or PyTorch. |
| Experiment Setup | Yes | We tune the hyper-parameters based on original papers recommendations. If original papers did not provide detailed hyper-parameters, we perform hyper-parameter tuning via cross-validation with Adam optimizer [Kingma and Ba, 2014] and early stop strategy. |