CLEAR: Null-Space Projection for Cross-Modal De-Redundancy in Multimodal Recommendation

• URL: http://arxiv.org/abs/2603.01536v1
• Date: Mon, 02 Mar 2026 07:06:56 GMT
• Title: CLEAR: Null-Space Projection for Cross-Modal De-Redundancy in Multimodal Recommendation
• Authors: Hao Zhan, Yihui Wang, Yonghui Yang, Danyang Yue, Yu Wang, Pengyang Shao, Fei Shen, Fei Liu, Le Wu,
• Abstract summary: Multimodal recommendation has emerged as an effective paradigm for enhancing collaborative filtering by incorporating heterogeneous content modalities.<n>We propose CLEAR, a cross-modal de-redundancy approach for multimodal recommendation.<n> CLEAR reshapes the representation space by suppressing redundant cross-modal components while preserving modality-specific information.
• Score: 22.71702128773632
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multimodal recommendation has emerged as an effective paradigm for enhancing collaborative filtering by incorporating heterogeneous content modalities. Existing multimodal recommenders predominantly focus on reinforcing cross-modal consistency to facilitate multimodal fusion. However, we observe that multimodal representations often exhibit substantial cross-modal redundancy, where dominant shared components overlap across modalities. Such redundancy can limit the effective utilization of complementary information, explaining why incorporating additional modalities does not always yield performance improvements. In this work, we propose CLEAR, a lightweight and plug-and-play cross-modal de-redundancy approach for multimodal recommendation. Rather than enforcing stronger cross-modal alignment, CLEAR explicitly characterizes the redundant shared subspace across modalities by modeling cross-modal covariance between visual and textual representations. By identifying dominant shared directions via singular value decomposition and projecting multimodal features onto the complementary null space, CLEAR reshapes the multimodal representation space by suppressing redundant cross-modal components while preserving modality-specific information. This subspace-level projection implicitly regulates representation learning dynamics, preventing the model from repeatedly amplifying redundant shared semantics during training. Notably, CLEAR can be seamlessly integrated into existing multimodal recommenders without modifying their architectures or training objectives. Extensive experiments on three public benchmark datasets demonstrate that explicitly reducing cross-modal redundancy consistently improves recommendation performance across a wide range of multimodal recommendation models.

Related papers

• Orthogonalized Multimodal Contrastive Learning with Asymmetric Masking for Structured Representations [4.67724003380452]
  Multimodal learning seeks to integrate information from heterogeneous sources, where signals may be shared across modalities, specific to individual modalities, or emerge only through their interaction.<n>While self-supervised multimodal contrastive learning has achieved remarkable progress, most existing methods predominantly capture redundant cross-modal signals, often neglecting modality-specific (unique) and interaction-driven (synergistic) information.<n>Recent extensions broaden this perspective, yet they either fail to explicitly model synergistic interactions or learn different information components in an entangled manner, leading to incomplete representations and potential information leakage.<n>We introduce textbfCOrAL, a principled framework
  arXiv  Detail & Related papers  (2026-02-16T18:06:53Z)
• When Gradient Optimization Is Not Enough: $\dagger$ Dispersive and Anchoring Geometric Regularizer for Multimodal Learning [7.598111859541752]
  We identify representation geometry as a missing control axis in multimodal learning and propose regName, a lightweight geometry-aware regularization framework.<n>regName enforces two complementary constraints on intermediate embeddings: an intra-modal dispersive regularization that promotes representation diversity, and an inter-modal anchoring regularization that bounds sample-level cross-modal drift without rigid alignment.<n>Experiments across multiple multimodal benchmarks demonstrate consistent improvements in both multimodal and unimodal performance, showing that explicitly regulating representation geometry effectively mitigates modality trade-offs.
  arXiv  Detail & Related papers  (2026-01-29T13:03:50Z)
• From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation [59.27094165576015]
  We propose a novel learning paradigm (UniMod) that transitions from sparse decision-making to dense reasoning traces.<n>By constructing structured trajectories encompassing evidence grounding, modality assessment, risk mapping, policy decision, and response generation, we reformulate monolithic decision tasks into a multi-dimensional boundary learning process.<n>We introduce specialized optimization strategies to decouple task-specific parameters and rebalance training dynamics, effectively resolving interference between diverse objectives in multi-task learning.
  arXiv  Detail & Related papers  (2026-01-28T09:29:40Z)
• NExT-OMNI: Towards Any-to-Any Omnimodal Foundation Models with Discrete Flow Matching [64.10695425442164]
  We introduce NExT-OMNI, an open-source omnimodal foundation model that achieves unified modeling through discrete flow paradigms.<n>Trained on large-scale interleaved text, image, video, and audio data, NExT-OMNI delivers competitive performance on multimodal generation and understanding benchmarks.<n>To advance further research, we release training details, data protocols, and open-source both the code and model checkpoints.
  arXiv  Detail & Related papers  (2025-10-15T16:25:18Z)
• UniAlignment: Semantic Alignment for Unified Image Generation, Understanding, Manipulation and Perception [54.53657134205492]
  UniAlignment is a unified multimodal generation framework within a single diffusion transformer.<n>It incorporates both intrinsic-modal semantic alignment and cross-modal semantic alignment, thereby enhancing the model's cross-modal consistency and instruction-following robustness.<n>We present SemGen-Bench, a new benchmark specifically designed to evaluate multimodal semantic consistency under complex textual instructions.
  arXiv  Detail & Related papers  (2025-09-28T09:11:30Z)
• Multimodal Representation-disentangled Information Bottleneck for Multimodal Recommendation [36.338586087343806]
  We propose a novel framework, the Multimodal Representation-disentangled Information Bottleneck (MRdIB)<n>Concretely, we first employ a Multimodal Information Bottleneck to compress the input representations.<n>Then, we decompose the information based on its relationship with the recommendation target into unique, redundant, and synergistic components.
  arXiv  Detail & Related papers  (2025-09-24T15:18:32Z)
• FindRec: Stein-Guided Entropic Flow for Multi-Modal Sequential Recommendation [57.577843653775]
  We propose textbfFindRec (textbfFlexible unified textbfinformation textbfdisentanglement for multi-modal sequential textbfRecommendation)<n>A Stein kernel-based Integrated Information Coordination Module (IICM) theoretically guarantees distribution consistency between multimodal features and ID streams.<n>A cross-modal expert routing mechanism that adaptively filters and combines multimodal features based on their contextual relevance.
  arXiv  Detail & Related papers  (2025-07-07T04:09:45Z)
• DecAlign: Hierarchical Cross-Modal Alignment for Decoupled Multimodal Representation Learning [18.066105354135058]
  Multimodal representation learning aims to capture both shared and complementary semantic information across multiple modalities.<n>We introduce DecAlign, a novel hierarchical cross-modal alignment framework designed to decouple multimodal representations into modality-unique (heterogeneous) and modality-common (homogeneous) features.<n>Our experiments on four widely used multimodal benchmarks demonstrate that DecAlign consistently outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-03-14T21:47:48Z)
• Towards Bridging the Cross-modal Semantic Gap for Multi-modal Recommendation [12.306686291299146]
  Multi-modal recommendation greatly enhances the performance of recommender systems. Most existing multi-modal recommendation models exploit multimedia information propagation processes to enrich item representations. We propose a novel framework to bridge the semantic gap between modalities and extract fine-grained multi-view semantic information.
  arXiv  Detail & Related papers  (2024-07-07T15:56:03Z)
• U3M: Unbiased Multiscale Modal Fusion Model for Multimodal Semantic Segmentation [63.31007867379312]
  We introduce U3M: An Unbiased Multiscale Modal Fusion Model for Multimodal Semantics. We employ feature fusion at multiple scales to ensure the effective extraction and integration of both global and local features. Experimental results demonstrate that our approach achieves superior performance across multiple datasets.
  arXiv  Detail & Related papers  (2024-05-24T08:58:48Z)
• Unified Multi-modal Unsupervised Representation Learning for Skeleton-based Action Understanding [62.70450216120704]
  Unsupervised pre-training has shown great success in skeleton-based action understanding. We propose a Unified Multimodal Unsupervised Representation Learning framework, called UmURL. UmURL exploits an efficient early-fusion strategy to jointly encode the multi-modal features in a single-stream manner.
  arXiv  Detail & Related papers  (2023-11-06T13:56:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.