CaIRec: Calibrated Modality Imputation for Incomplete Multimodal Recommendation

2026-07-29

AI Summary

This work addresses the challenges of cross-modal structural distortion and preference misalignment caused by missing modalities in real-world multimodal recommendation systems. To tackle these issues, the authors propose a two-stage calibration framework: first, structured modality completion with cross-modal correspondence supervision ensures consistency in the imputed content; second, preference-guided representation calibration aligns the completed features with the recommendation ranking objective. A completion-aware item graph is further constructed by integrating the imputed modalities with collaborative signals. The approach innovatively jointly optimizes cross-modal structural consistency and task-oriented representation alignment, incorporating mechanisms such as structural regularization and pseudo-missing data augmentation. Extensive experiments demonstrate that the proposed method significantly outperforms existing approaches across multiple datasets and missing-modality settings, exhibiting both strong effectiveness and robustness.

Abstract

Real-world multimodal recommender systems often face incomplete modality observations, where items lack images, text, or other content features. Such incompleteness weakens item representations and degrades recommendation performance. Existing modality imputation methods estimate missing representations from available item content, but two challenges remain. First, they optimize the recovered representation itself without explicitly considering its relations with other modalities of the same item. The completed modalities may therefore form inconsistent cross-modal relations, causing Cross-modal Structural Distortion. Second, even structurally coherent recovered information may remain ineffective for personalized ranking. Recovered representations receive limited ranking-oriented guidance, while modality missingness disrupts the item neighborhoods required for preference propagation, resulting in a Preference Adaptation Gap. To address these challenges, we propose Calibrated Imputation for Incomplete Multimodal Recommendation (CaIRec), a two-stage framework. Structural Imputation Calibration (SIC) estimates missing-modality representations from shared information inferred from available modalities and calibrates their cross-modal organization through structural regularization and correspondence supervision from observed modality pairs. Preference-oriented Representation Calibration (PRC) performs recommendation-specific adaptation at both the representation and relation levels. It constructs pseudo-missing instances to align recovered representations with observed counterparts shaped by ranking supervision in the recommendation space. It further builds completion-aware item graphs by integrating completed content relations with collaborative evidence. Extensive experiments on three datasets under different modality-missing settings demonstrate the effectiveness and robustness of CaIRec.

Problem

• incomplete multimodal recommendation
• modality imputation
• cross-modal structural distortion
• preference adaptation gap

Innovation

• modality imputation
• cross-modal consistency
• preference adaptation
• multimodal recommendation
• representation calibration