A Hybrid Bandit Framework for Diversified Recommendation

Authors: Qinxu Ding, Yong Liu, Chunyan Miao, Fei Cheng, Haihong Tang4036-4044

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on real datasets are performed to demonstrate the effectiveness of the proposed LMDB framework in balancing the recommendation accuracy and diversity.
Researcher Affiliation Collaboration Qinxu Ding,1 Yong Liu,1,2 Chunyan Miao,3 Fei Cheng,4 Haihong Tang4 1 Alibaba-NTU Singapore Joint Research Institute 2 Joint NTU-UBC Research Centre of Excellence in Active Living for the Elderly (LILY) 3School of Computer Science and Engineering, Nanyang Technological University 4Alibaba Group
Pseudocode Yes Algorithm 1 Modular Dispersion Greedy Search
Open Source Code No The paper does not provide any explicit statements or links indicating that the source code for the described methodology is publicly available.
Open Datasets Yes The experiments are performed on the following datasets: Movielens-100K, Movielens-1M1, and Anime2. 1https://grouplens.org/datasets/movielens/ 2https://www.kaggle.com/Cooper Union/animerecommendations-database
Dataset Splits Yes Firstly, we randomly split each dataset into two non-overlapping sets. Specifically, 80% of the users are used for training, and the remaining 20% users are used for testing.
Hardware Specification No The paper describes the experiments but does not provide specific details about the hardware (e.g., GPU or CPU models, memory) used for running them.
Software Dependencies No The paper mentions the use of BPRMF but does not specify version numbers for any software, libraries, or frameworks used in the experiments.
Experiment Setup Yes Empirically, we set the dimensionality of the item embeddings to 10. [...] We set the size of At to 10 for all methods. The hyper-parameter settings for each method are summarized in Appendix.