Modality-Aware Identity Construction and Counterfactual Structure Learning for ID-Free Multimodal Recommendation
For researchers in multimodal recommendation, this work addresses the limitations of static ID representations and popularity bias, offering a novel approach that yields significant performance improvements.
MAIL improves ID-free multimodal recommendation by dynamically constructing content-aware identity representations and using counterfactual structure learning to mitigate popularity bias, achieving average gains of 7.81% in Recall@10 and 12.81% in NDCG@10 over baselines on five Amazon datasets.
Multimodal recommendation has attracted extensive attention by leveraging heterogeneous modality information to alleviate data sparsity and improve recommendation accuracy. Existing methods have attempted to replace ID embeddings with multimodal features and have achieved promising preliminary results. However, these methods still exhibit the following two limitations: (1) the reconstructed ID representations remain relatively static and fail to fully exploit multimodal semantics; and (2) the graph learning process is insufficient in mining latent long-tail semantic relations and is easily affected by popularity bias. To address these issues, we propose a novel method named Modality-Aware Identity Construction and Counterfactual Structure Learning for ID-free Multimodal Recommendation (MAIL). Specifically, we design a modality-aware identity construction module that dynamically modulates positional encodings with multimodal semantics to construct content-aware ID-free identity representations. Then, we propose a counterfactual structure learning paradigm that mines low-exposure semantic neighbors via popularity penalization and alleviates popularity bias. Extensive experiments are conducted on five public Amazon datasets. Experimental results show that MAIL achieves average improvements of 7.81% in Recall@10 and 12.81% in NDCG@10 compared with the baseline models. Our code is available at https://github.com/HubuKG/MAIL.