Improving Top-N Recommendation with Heterogeneous Loss

Authors: Feipeng Zhao, Yuhong Guo

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

Reproducibility Variable Result LLM Response
Research Type Experimental We evaluate the proposed approach on a set of personalized top-N recommendation tasks. The experimental results show the proposed approach outperforms a number of state-of-the-art methods on top-N recommendation. 4 Experimental Results In this section, we first present the experimental setting and then report the empirical results.
Researcher Affiliation Academia Feipeng Zhao and Yuhong Guo Department of Computer and Information Sciences Temple University, Philadelphia, PA 19122, USA {feipeng.zhao, yuhong}@temple.edu
Pseudocode Yes Algorithm 1 Projected Stochastic Gradient Descent
Open Source Code No The paper does not provide any links or explicit statements about releasing its source code.
Open Datasets Yes Datasets. We used five datasets in our experiments: Yahoo! music ratings v1.0 dataset, Yahoo! movie ratings v1.0 dataset, Movie Lens 100k (ml-100k) dataset, Movie Lens 1M (ml-1m) dataset and Netflix dataset. ... For ml-1m and Netflix we used the same datasets as [Aiolli, 2014].
Dataset Splits No For each dataset, we split it into a training set and a test set. For each user, we randomly selected ten feedbacks and placed them into the test set and the rest were used as training set. No mention of a separate validation split.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments.
Software Dependencies No The paper does not list specific software dependencies with version numbers.
Experiment Setup Yes Parameters Selection. For the proposed method, we have two parameters, and β. We selected the weight control parameter from {10, 100, 1000, 5000, 10000} and selected the regularization parameter β from {0.001, 0.01, 0.1, 1, 10, 100, 1000}. For WRMF, the latent factor dimension f is selected from {10, 20, 50, 100, 200, 500, 1000} and the regularization parameter λ is selected from {0.1, 1, 10, 100, 1000}.