GroupTransfer: User Group Transferability Metric Driven by Social Identity Theory

Effective knowledge transfer from source to target users is essential for enhancing prediction performance in data-sparse scenarios, particularly in consumer electronics applications such as personalized recommendations and health monitoring. However, existing approaches often suffer from excessive complexity and lack theoretical grounding, resulting in inefficiency and negative transfer. While some transferability metrics consider the relationship between source and target users, they fail to account for interactions within the source user group, limiting their ability to assess group-level transferability accurately. To address these limitations, this paper introduces GroupTrans, a novel transferability metric grounded in social identity theory, that simultaneously captures source-target relevance and intragroup interactions through dual modeling of consistency and diversity. Additionally, we introduce a similarity-guided incremental search algorithm to identify an optimal source user set, alleviating knowledge redundancy and enhancing transfer performance. Extensive experiments on both sparse and dense datasets demonstrate that GroupTrans effectively captures group dynamics and outperforms existing methods. The strong theoretical foundation and practical effectiveness of this framework have successfully addressed key challenges in personalized service applications, making it particularly valuable for data-sparse consumer electronics systems.