Search papers, labs, and topics across Lattice.
This paper introduces D3ER, a novel framework for multi-modal recommendation that leverages gradient boosting to separately optimize modal-homogeneity and modal-heterogeneity discriminative information. By disentangling these two types of information, D3ER allows specialized models to focus on their respective strengths, enhancing overall recommendation performance. Experimental results on real-world datasets demonstrate that D3ER outperforms existing methods, addressing the limitations of joint learning in multi-modal contexts.
Disentangling modal information in multi-modal recommendation leads to significant performance boosts, with D3ER outperforming traditional methods by effectively optimizing specialized models.
Incorporating items'information shared among multiple modalities into a fused representation, multi-modal recommendation (MR) has demonstrated documented success than canonical unimodal recommendation. Although several attempts have been made to extract the discriminative information unique in each modality, existing methods suffer from a core limitation: the joint learning of modal-homogeneity discriminative information (HOI) and modal-heterogeneity discriminative information (HEI) tends to weaken their individual effectiveness. To remedy this deficiency, we propose a novel method, dubbed Disentangle and Distillation-based Dynamic Ensemble for multi-modal Recommendation (D3ER). We introduce gradient boosting into MR for the first time to formalize the optimization objective for alternately learning HOI and HEI. This design enables models dedicated to each type of information to focus on their proficient samples, thereby promoting specialized optimization. Furthermore, to mitigate the inherent high storage cost and risk of local optima in gradient boosting, we enhance our framework with knowledge distillation and a global correction regularization. Experiments on prevalent real-world datasets confirm the superiority of our proposed method on MR.
