Towards Unbiased Information Extraction and Adaptation in Cross-Domain Recommendation
Yibo Wang, Yingchun Jian, Wenhao Yang, Shiyin Lu, Lei Shen, Bing Wang, Xiaoyi Zeng, Lijun Zhang
Abstract
Cross-Domain Recommendation (CDR) leverages additional knowledge from auxiliary domains to address the long-standing data sparsity issue. However, existing methods typically acquire this knowledge by minimizing the average loss over all domains, overlooking the fact that different domains possess different user-preference distributions. As a result, the acquired knowledge may contain biased information from data-rich domains, leading to performance degradation in data-scarce domains. In this paper, we propose a novel CDR method, which takes domain distinctions into consideration to extract and adapt unbiased information. Specifically, our method consists of two key components: Unbiased Information Extraction (UIE) and Unbiased Information Adaptation (UIA). In the UIE, inspired by distributionally robust optimization, we optimize the worst-case performance across all domains to extract domain-invariant information, preventing the potential bias from auxiliary domains. In the UIA, we introduce a new user-item attention module, which employs domain-specific information from historically interacted items to attend the adaptation of domain-invariant information. To verify the effectiveness of our method, we conduct extensive experiments on three real-world datasets, each of which contains three extremely sparse domains. Experimental results demonstrate the considerable superiority of our proposed method compared to baselines.
BibTeX
@article{Wang_Jian_Yang_Lu_Shen_Wang_Zeng_Zhang_2025, title={Towards Unbiased Information Extraction and Adaptation in Cross-Domain Recommendation}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/33391}, DOI={10.1609/aaai.v39i12.33391}, abstractNote={Cross-Domain Recommendation (CDR) leverages additional knowledge from auxiliary domains to address the long-standing data sparsity issue. However, existing methods typically acquire this knowledge by minimizing the average loss over all domains, overlooking the fact that different domains possess different user-preference distributions. As a result, the acquired knowledge may contain biased information from data-rich domains, leading to performance degradation in data-scarce domains. In this paper, we propose a novel CDR method, which takes domain distinctions into consideration to extract and adapt unbiased information. Specifically, our method consists of two key components: Unbiased Information Extraction (UIE) and Unbiased Information Adaptation (UIA). In the UIE, inspired by distributionally robust optimization, we optimize the worst-case performance across all domains to extract domain-invariant information, preventing the potential bias from auxiliary domains. In the UIA, we introduce a new user-item attention module, which employs domain-specific information from historically interacted items to attend the adaptation of domain-invariant information. To verify the effectiveness of our method, we conduct extensive experiments on three real-world datasets, each of which contains three extremely sparse domains. Experimental results demonstrate the considerable superiority of our proposed method compared to baselines.}, number={12}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Wang, Yibo and Jian, Yingchun and Yang, Wenhao and Lu, Shiyin and Shen, Lei and Wang, Bing and Zeng, Xiaoyi and Zhang, Lijun}, year={2025}, month={Apr.}, pages={12757-12765} }