Recommendation Accuracy
Recommendation accuracy focuses on improving the precision and relevance of suggested items to users, aiming to maximize user satisfaction and engagement. Current research emphasizes mitigating biases (e.g., popularity bias, herding effects), enhancing model efficiency through techniques like parameter-efficient fine-tuning of large language models and optimized negative sampling, and incorporating diverse data sources (e.g., multimodal data, social networks, knowledge graphs) to improve representation learning. These advancements are crucial for improving the effectiveness of recommender systems across various applications, from e-commerce and entertainment to healthcare and personalized learning, ultimately impacting user experience and business outcomes.
Papers
Customizing Language Models with Instance-wise LoRA for Sequential Recommendation
Xiaoyu Kong, Jiancan Wu, An Zhang, Leheng Sheng, Hui Lin, Xiang Wang, Xiangnan He
Data-driven Conditional Instrumental Variables for Debiasing Recommender Systems
Zhirong Huang, Shichao Zhang, Debo Cheng, Jiuyong Li, Lin Liu, Guangquan Lu