Exploring Implicit Hierarchical Structures for Recommender Systems

Authors: Suhang Wang, Jiliang Tang, Yilin Wang, Huan Liu

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on two real world datasets demonstrate the effectiveness of the proposed framework. In Section 4, we show empirical evaluation with discussion.
Researcher Affiliation Academia Suhang Wang, Jiliang Tang, Yilin Wang and Huan Liu School of Computing, Informatics, and Decision Systems Engineering Arizona State University, USA {suhang.wang, jiliang.tang, yilin.wang.1, huan.liu}@asu.edu
Pseudocode Yes Algorithm 1 The Optimization Algorithm for the Proposed Framework HSR.
Open Source Code Yes The code can be downloaded from http://www.public.asu.edu/~swang187/
Open Datasets Yes The experiments are conducted on two publicly available benchmark datasets, i.e., Movie Lens100K 4 and Douban 5. ... 4http://grouplens.org/datasets/movielens/ 5http://dl.dropbox.com/u/17517913/Douban.zip
Dataset Splits No The paper mentions "We random select x% as training set and the remaining 1 x% as testing set" but does not specify a separate validation dataset split. While it states parameters are determined via cross-validation, it doesn't describe the splits for it.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments (e.g., CPU, GPU models, memory).
Software Dependencies No The paper does not list specific software dependencies with version numbers (e.g., Python 3.x, specific library versions).
Experiment Setup Yes We only show results with p = 2 and q = 2, i.e., W X W (U1U2V2V1) with U1 Rn n1, U2 Rn1 d, V1 Rd m1, and V2 Rm1 m, since we have similar observations with other settings of p and q. We fix d to be 20 and vary the value of n1 as {100, 200, 300, 400, 500} and the value of m1 as {200, 400, 600, 800, 1000}.