Semi-supervised User Profiling with Heterogeneous Graph Attention Networks

Authors: Weijian Chen, Yulong Gu, Zhaochun Ren, Xiangnan He, Hongtao Xie, Tong Guo, Dawei Yin, Yongdong Zhang

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on a real-world e-commerce dataset verify the effectiveness and rationality of our HGAT for user profiling.
Researcher Affiliation Collaboration 1 University of Science and Technology of China, Hefei, China 2 JD.com, China 3 Shandong University, China
Pseudocode No The paper describes various operations but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating that the source code for their methodology is open-source or publicly available.
Open Datasets No To evaluate our proposed method in user profiling, we collect a large scale real-world dataset from JD.com , one of the most popular e-commerce portals in China.
Dataset Splits Yes In the experiment, we randomly split labeled users into training set, validation set and test set with the ratio 75:12.5:12.5 following previous works [Qiu et al., 2018].
Hardware Specification No The paper does not provide any specific hardware details such as GPU or CPU models used for running the experiments.
Software Dependencies No The paper mentions using Fast Text and Adam optimizer but does not provide specific version numbers for these or any other software dependencies.
Experiment Setup Yes In the Mini Heterogeneous Graph Sampling procedure, the number of neighborhood samples is set as follows: k = 2, Lu1 = 10, Lu2 = 4 for User-User mini graph, Li = 10 for Item-User mini graph, Lt = 10 for Attribute-Item mini graph. [...] The learning rate, dropout rate, mini-batch size, are set to 0.005, 0.6, 64 for gender prediction and 0.1, 0.2, 32 for age prediction, respectively.