Enhancing Interpretability and Effectiveness in Recommendation with Numerical Features via Learning to Contrast the Counterfactual samples
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911136752861184 |
|---|---|
| author | Xu, Xiaoxiao Wu, Hao Yu, Wenhui Hu, Lantao Jiang, Peng Gai, Kun |
| author_facet | Xu, Xiaoxiao Wu, Hao Yu, Wenhui Hu, Lantao Jiang, Peng Gai, Kun |
| contents | We propose a general model-agnostic Contrastive learning framework with Counterfactual Samples Synthesizing (CCSS) for modeling the monotonicity between the neural network output and numerical features which is critical for interpretability and effectiveness of recommender systems. CCSS models the monotonicity via a two-stage process: synthesizing counterfactual samples and contrasting the counterfactual samples. The two techniques are naturally integrated into a model-agnostic framework, forming an end-to-end training process. Abundant empirical tests are conducted on a publicly available dataset and a real industrial dataset, and the results well demonstrate the effectiveness of our proposed CCSS. Besides, CCSS has been deployed in our real large-scale industrial recommender, successfully serving over hundreds of millions users. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03187 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhancing Interpretability and Effectiveness in Recommendation with Numerical Features via Learning to Contrast the Counterfactual samples Xu, Xiaoxiao Wu, Hao Yu, Wenhui Hu, Lantao Jiang, Peng Gai, Kun Information Retrieval Machine Learning We propose a general model-agnostic Contrastive learning framework with Counterfactual Samples Synthesizing (CCSS) for modeling the monotonicity between the neural network output and numerical features which is critical for interpretability and effectiveness of recommender systems. CCSS models the monotonicity via a two-stage process: synthesizing counterfactual samples and contrasting the counterfactual samples. The two techniques are naturally integrated into a model-agnostic framework, forming an end-to-end training process. Abundant empirical tests are conducted on a publicly available dataset and a real industrial dataset, and the results well demonstrate the effectiveness of our proposed CCSS. Besides, CCSS has been deployed in our real large-scale industrial recommender, successfully serving over hundreds of millions users. |
| title | Enhancing Interpretability and Effectiveness in Recommendation with Numerical Features via Learning to Contrast the Counterfactual samples |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2509.03187 |