Matrix Factorization+ for Movie Recommendation

Authors: Lili Zhao, Zhongqi Lu, Sinno Jialin Pan, Qiang Yang

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on real world datasets show that our approach leads to significant improvement over several state-of-the-art methods.
Researcher Affiliation Academia Hong Kong University of Science and Technology, Hong Kong Nanyang Technological University, Singapore
Pseudocode No The paper describes algorithmic steps for parameter updates but does not present them in a formally labeled pseudocode or algorithm block.
Open Source Code No The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available.
Open Datasets Yes We evaluate on the Netflix and Douban datasets. Since the two original datasets do not have movie posters and still frames, we crawled these data from web. Commonly used datasets (Movie Lens2, Netflix, Each Movie3) only contain rating data and some provide with meta data about movie and user attributes.
Dataset Splits No The paper states, "We split each dataset by assigning 80% to training set and the rest 20% to a test set." While it mentions parameters were "tuned on Douban data," it does not explicitly define a separate validation split or its size within the reported 80/20 train/test split.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments (e.g., GPU models, CPU types, memory).
Software Dependencies No The paper mentions using "Caffe [Jia et al., 2014]" for extracting features but does not specify the version number of Caffe or any other software dependencies with their versions.
Experiment Setup Yes The parameters of our model, i.e., the number of latent factors k and the number of iterations T are tuned on Douban data, and fixed to the others. Here, T = 30, and k =20.