Spatial-Temporal Perceiving: Deciphering User Hierarchical Intent in Session-Based Recommendation

Authors: Xiao Wang, Tingting Dai, Qiao Liu, Shuang Liang

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on three real-world datasets exhibit that Hear Int achieves state-of-the-art performance.
Researcher Affiliation Academia Xiao Wang , Tingting Dai , Qiao Liu and Shuang Liang University of Electronic Science and Technology of China wangxiao16@std.uestc.edu.cn, ttdai 18@outlook.com, qliu@uestc.edu.cn, shuangliang@uestc.edu.cn
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code Yes The source code and datasets are publicly available on Git Hub 1. 1https://github.com/jarviswww/Code4Hear Int
Open Datasets Yes We evaluate the proposed model on three benchmark datasets, namely Tmall 2, Retail Rocket3,Diginetica4. ... 2https://tianchi.aliyun.com/dataset/dataDetail?dataId=42 3https://www.kaggle.com/retailrocket/ecommerce-dataset 4https://competitions.codalab.org/competitions/11161
Dataset Splits No The paper describes the training and test sets but does not specify a separate validation split, its size, or the method for creating it.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details with version numbers (e.g., Python, PyTorch versions, or specific libraries).
Experiment Setup Yes For the general setting, the embedding size is 100, the batch size is 100. For Hear Int, the initial learning rate is 0.001, which will decay by 0.6 after every 1 epoch. We employ the k-means as the clustering algorithm and set the number of clusters to 100. The threshold α of cosine similarity is 0 in three datasets. Mask probability β is 0.4 for Tmall , while 0.1 is for Diginetica and Retailrocket. The θ The best number of layers in both attention and GNN encoders is 1,2,2 for Tmall, Retailrocket, and Diginetica, respectively.