Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
KDDC: Knowledge-Driven Disentangled Causal Metric Learning for Pre-Travel Out-of-Town Recommendation
Authors: Yinghui Liu, Guojiang Shen, Chengyong Cui, Zhenzhen Zhao, Xiao Han, Jiaxin Du, Xiangyu Zhao, Xiangjie Kong
IJCAI 2024 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on two real-world nationwide datasets display the consistent superiority of our KDDC over state-of-the-art baselines. |
| Researcher Affiliation | Academia | 1Zhejiang University of Technology 2City University of Hong Kong EMAIL, EMAIL, EMAIL, EMAIL, EMAIL |
| Pseudocode | No | No section or figure explicitly labeled “Pseudocode” or “Algorithm”. |
| Open Source Code | Yes | The code for the implementation of KDDC is available for reproducibility3. 3https://github.com/Yinghui-Liu/KDDC |
| Open Datasets | Yes | We chose two nationwide travel behavior datasets, Foursquare1 and Yelp2, to evaluate our framework. 1https://sites.google.com/site/yangdingqi/home/foursquaredataset 2https://www.yelp.com.tw/dataset |
| Dataset Splits | Yes | The two datasets are randomly partitioned based on users into three sets for training, validation, and testing following the proportions: 80%, 10% and 10%. |
| Hardware Specification | No | The paper mentions “We implemented our KDDC and experimented with Pytorch.” but does not specify any hardware details like GPU/CPU models or memory. |
| Software Dependencies | No | The paper mentions “We implemented our KDDC and experimented with Pytorch.” However, it does not provide specific version numbers for Pytorch or any other software, which is required for reproducibility. |
| Experiment Setup | Yes | the number of dimensions of all latent representations was set to 128. In the Knowledge Graph Segmented Pre-Training, n was 8 for Foursquare and 4 was for Yelp. In the optimization stage, λ1 and λ2 were set as 1, the optimizer was chosen as Adam with an initial learning rate of 0.001 and an L2 regularization with a weight of 10-5. |