Dual-Scale Interest Extraction Framework with Self-Supervision for Sequential Recommendation

no code implementations • 16 Oct 2023 • Liangliang Chen, Hongzhan Lin, Jinshan Ma, Guang Chen

Nevertheless, the existing approaches just extract each interest independently for the corresponding sub-sequence while ignoring the global correlation of the entire interaction sequence, which may fail to capture the user's inherent preference for the potential interests generalization and unavoidably make the recommended items homogeneous with the historical behaviors.

Contrastive Learning Sequential Recommendation