Intent Preference Decoupling for User Representation on Online Recommender System
Authors: Zhaoyang Liu, Haokun Chen, Fei Sun, Xu Xie, Jinyang Gao, Bolin Ding, Yanyan Shen
IJCAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conducted experiments on two public datasets and a real-world recommender system. When combining it with modern recommendation methods, significant improvements are demonstrated over strong baselines. |
| Researcher Affiliation | Collaboration | 1Alibaba Group 2Peking University 3Shanghai Jiao Tong University |
| Pseudocode | Yes | Algorithm 1 Follow the Intent and Preference Decoupling; Algorithm 2 FLIP Subroutines |
| Open Source Code | No | The paper does not contain an explicit statement about releasing source code or a link to a code repository for the described methodology. |
| Open Datasets | Yes | 1) Movie Lens1 is a widely used dataset to evaluate collaborative filtering algorithms. We adopted the version containing one million ratings from 6040 users and transformed it into a binary class dataset where the ratings above 3.5 are labeled as the positive samples while the rest are the negative ones. For each user, we sorted the interactions in chronological order and treated the behaviors during one day as a session. 2) Advertising2 is a public dataset released from Tianchi Competition3 by Alimama, ranging from 2017-05-06 to 2017-05-12. We filter out the items or users of which the interaction number is less than 5 and obtain 23.7 million ad display/click records from 0.67 million users and 0.38 million ads. The clicked and unclicked ones constitute the positive and negative samples, respectively. |
| Dataset Splits | No | The paper describes how sessions are created and interactions are sorted chronologically, and mentions positive/negative samples. It also describes support (Dtr) and query (Dval) sets for meta-learning *within* a session but does not specify explicit global training, validation, and test split percentages or counts for the entire experimental evaluation. |
| Hardware Specification | No | The paper does not provide any specific hardware details such as GPU models, CPU types, or memory used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers. |
| Experiment Setup | Yes | The analyzed hyper-parameters including the dimensionality of the intent embedding and the update frequency δ of META-UPDATE procedure. Specifically, we set the dimensionality of intent embedding as 1/8, 1/4, 1/2, and 1 proportional to that of preference embedding which we set to 64 in our experiments. As shown in Table 4, FLIP learning strategy is effective under different dimensionality settings. For Movie Lens and Advertising datasets, we observed a 1/4 dimensionality is sufficient for learning user instant intent since Movie Lens is a relatively small dataset and the number of intra-session behaviors is relatively sparse for Advertising dataset. As for Recommender datasets, a larger-sized dimensionality could further achieve better performance as more and more session browsing behaviors are introduced for model training. Considering the characteristics of three datasets, we designed different hyper-parameter settings on update frequency δ of META-UPDATE procedure. As shown in Table 5, shorter update interval can timely capture the drift of user interests and lead to better intra-session performance. |