A Knowledge-Aware Attentional Reasoning Network for Recommendation
Authors: Qiannan Zhu, Xiaofei Zhou, Jia Wu, Jianlong Tan, Li Guo6999-7006
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct experiment on Amazon review dataset, and the experimental results demonstrate the superiority and effectiveness of our proposed KARN model. |
| Researcher Affiliation | Academia | Qiannan Zhu,1,2 Xiaofei Zhou, 1,2 Jia Wu,3 Jianlong Tan,1,2 Li Guo1,2 1Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China 2School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China 3Department of Computing, Macquarie University, Sydney, Australia |
| Pseudocode | No | The paper describes the model architecture and training process using text and mathematical equations, but it does not include any explicitly labeled 'Pseudocode' or 'Algorithm' blocks. |
| Open Source Code | No | The paper does not contain any statement about releasing source code or provide a link to a code repository for the described methodology. |
| Open Datasets | Yes | We conduct experiment on Amazon review dataset...Amazon review dataset (Mc Auley et al. 2015; He and Mc Auley 2016)...1http://jmcauley.ucsd.edu/data/amazon/ |
| Dataset Splits | Yes | For each category data, we randomly sampled 80%, 10% and 10% of the samples as the training, valid and test data. |
| Hardware Specification | No | The paper does not provide specific details about the hardware (e.g., CPU, GPU models, memory, or cloud instances) used to run the experiments. |
| Software Dependencies | No | The paper describes the model's components and operations (e.g., convolution, LSTM, attention) but does not list specific software dependencies with version numbers (e.g., TensorFlow, PyTorch, Python versions). |
| Experiment Setup | Yes | Parameter Setting In training stage, we set the number of filters as F = 5, the maximum length of a path and clicked sequence as q = 8 and t = 10, the maximum number of the path set as n = 6. We also apply a grid search to find out the best settings of hyper-parameters, i.e., we select the dimensions of entity embeddings d, word embeddings d and hidden states m from {50, 100, 200, 250, 300}, the aspects of self-attention s2 from {1, 3, 5, 7, 9}, the batch size B from {500, 1000, 1500, 2000}, and the learning rate η from {0.1, 0.01, 0.001, 0.0001}. We train our model 1000 epochs and the best optimal parameter configurations are d = d = m = 100, s2 = 5, B = 1000, η = 0.001. |