Explainable Recommendation through Attentive Multi-View Learning
Authors: Jingyue Gao, Xiting Wang, Yasha Wang, Xing Xie3622-3629
AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results show that our model outperforms state-of-the-art methods in terms of both accuracy and explainability. |
| Researcher Affiliation | Collaboration | 1Peking University, {gaojingyue1997, wangyasha}@pku.edu.cn 2Microsoft Research Asia, {xitwan, xingx}@microsoft.com |
| Pseudocode | No | The paper describes algorithms (e.g., dynamic programming) but does not present them in structured pseudocode blocks or labeled algorithm figures. |
| Open Source Code | No | Footnote 4 links to a CSV file of explanations, not the source code for the methodology described in the paper. No other explicit statement about open-sourcing the code is provided. |
| Open Datasets | Yes | We use three datasets from different domains for evaluation. Table 1 summarizes the statistics of the datasets. Toys and Games is the part of the Amazon dataset2 that focuses on Toys and Games. ... Digital Music is also from the Amazon 5-core dataset. ... Yelp consists of restaurant reviews from Yelp Challenge 20183. ... 2http://jmcauley.ucsd.edu/data/amazon 3https://www.yelp.com/dataset/challenge |
| Dataset Splits | Yes | We randomly split the dataset into training (70%), validation (15%) and test (15%) sets. |
| Hardware Specification | No | The paper does not specify the hardware (e.g., CPU, GPU models, memory) used for running the experiments. |
| Software Dependencies | No | The paper mentions using the "Adam optimizer (Kingma and Ba 2014)" but does not provide version numbers for any software dependencies, libraries, or programming languages used. |
| Experiment Setup | Yes | The number of latent factors k for algorithms is searched in [8,16,32,64,128]. After parameter tuning, we set k = 8 for NMF, PMF and HFT, and k = 16 for SVD++. We set k = 32 for EFM, CKE, Deep Co NN, NARRE and DEAML. We set d1, d2, d3, λv, and λa to 20, 10, 10, 10.0, and 3.0, respectively. |