FPAdaMetric: False-Positive-Aware Adaptive Metric Learning for Session-Based Recommendation
Authors: Jongwon Jeong, Jeong Choi, Hyunsouk Cho, Sehee Chung4039-4047
AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We verify that FP-Ada Metric improves several session-based recommendation models performances in terms of Hit Rate (HR), MRR, and NDCG on datasets from different domains including music, movie, and game. Furthermore, we show that the adaptive module plays a much more crucial role in FP-Ada Metric model than in other baselines. Experiment Setting Datasets To verify our proposed method on the various data types, we evaluate the model on four different datasets: Last FM, Spotify, Amazon Movie and FUSER. |
| Researcher Affiliation | Collaboration | Jongwon Jeong1, Jeong Choi2, Hyunsouk Cho3* , Sehee Chung1 1 Knowledge AI Lab, NCSOFT Corp., Republic of Korea 2 NAVER Corp., Republic of Korea 3 Ajou University, Republic of Korea |
| Pseudocode | No | The paper describes the model and methods but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | All implementations of the experiments are available in https: //github.com/jongwon Jeong/FPAda Metric. It will be appeared after company s permission |
| Open Datasets | Yes | Datasets To verify our proposed method on the various data types, we evaluate the model on four different datasets: Last FM, Spotify, Amazon Movie and FUSER. The detailed statistics of each dataset are summarized in table 1. We split each dataset into 80% of train, 10% of validation, and 10% of test sets. The more detailed information is provided in the appendix. |
| Dataset Splits | Yes | We split each dataset into 80% of train, 10% of validation, and 10% of test sets. |
| Hardware Specification | No | The paper does not provide specific details regarding the hardware used for running the experiments, such as GPU models, CPU types, or memory specifications. |
| Software Dependencies | No | The paper does not specify the version numbers of any software dependencies, libraries, or frameworks used for the experiments. |
| Experiment Setup | No | The paper describes the general experimental setup, including datasets, baselines, and evaluation metrics, but it does not provide specific hyperparameter values (e.g., learning rate, batch size, number of epochs) or detailed training configurations for reproducibility. |