Hybrid contrastive multi-scenario learning for multi-task sequential-dependence recommendation

Abstract

Multi-scenario and multi-task learning are crucial in industrial recommendation systems to deliver high-quality recommendations across diverse scenarios with minimal computational overhead. However, conventional models often fail to effectively leverage cross-scenario information, limiting their representational capabilities. Additionally, multi-step conversion tasks in real-world applications face challenges from sequential dependencies and increased data sparsity, particularly in later stages. To address these issues, we propose a Hybrid Contrastive Multi-scenario learning framework for Multi-task Sequential-dependence Recommendation (HCM${}^2$SR). In the scenario layer, hybrid contrastive learning captures both shared and scenario-specific information, while a scenario-aware multi-gate network enhances representations by evaluating cross-scenario relevance. In the task layer, an adaptive multi-task network transfers knowledge across sequential stages, mitigating data sparsity in long-path conversions. Extensive experiments on two public datasets and one industrial dataset validate the effectiveness of HCM${}^2$SR, with ablation studies confirming the contribution of each component.