A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations

Authors: Krishna Prasad Neupane, Ervine Zheng, Yu Kong, Qi Yu7868-7876

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments over real-world data help demonstrate the effectiveness of the proposed time-sensitive cold-start recommendation model.
Researcher Affiliation Academia Rochester Institute of Technology {kpn3569, mxz5733, yu.kong, qi.yu}@rit.edu
Pseudocode Yes Algorithm 1: Model training
Open Source Code Yes Experimental settings, datasets details, and analysis of the above key properties are presented in the Appendix (Neupane et al. 2021). [...] Neupane, K.; Zheng, E.; Kong, Y.; and Yu, Q. 2021. Appendix: A Dynamic Meta-Learning Model for Time-Sensitive Cold-Start Recommendations. https://github.com/ritmininglab/A-Dynamic-Meta-Learning-Model-for-Time-Sensitive-Cold-Start-Recommendations/blob/main/Appendix.pdf.
Open Datasets Yes We conduct experiments on two movie datasets: Netflix and Movie Lens-1M that consist of users ratings of movies as explicit feedback and one music dataset: Last.fm that consists of users play counts of music tracks as implicit feedback.
Dataset Splits No The paper mentions 'meta-train' and 'meta-test' sets but does not explicitly provide the specific percentages or counts for training, validation, and test splits in the main text, deferring details to an appendix.
Hardware Specification No The paper does not provide any specific hardware details (like GPU models, CPU types, or cloud configurations) used for running its experiments.
Software Dependencies No The paper does not provide specific software dependencies or their version numbers (e.g., programming languages, libraries, or frameworks with version tags) used for implementation or experimentation.
Experiment Setup Yes Require: Hyperparameters: α, β, γ