Information-Guided Selective Modality-Interest Alignment for Multimodal Recommendation
Information Retrieval
Summary
The authors focus on improving recommendation systems that use different types of item information (like images, text, etc.). They note that not all types of information help equally and some might even confuse the system. To fix this, they created AMUR, a method that selects and aligns the parts of the item data most related to what users like, using ideas from information theory. Their tests on real data show AMUR works better than other current methods.
Authors
Wenze Ma, Chenyu Sun, Yanmin Zhu, Qiwen Gu, Xuhao Zhao
Abstract
Multimodal recommendation (MMRec) aims to enhance recommendation performance by leveraging rich item content from multiple modalities. However, directly incorporating all modality information does not necessarily lead to better preference modeling, since user interests are often more related to a subset of modality signals, while other signals may be weakly aligned with user preferences or even introduce noise. Although recent MMRec methods improve modality utilization through invariant learning, attention mechanisms, graph refinement, or contrastive learning, their alignment processes are often implicit or heuristic and lack a clear objective for selecting modality signals that better match user interests. In this paper, we propose AMUR, an information-guided selective modality-interest alignment framework for multimodal recommendation. Inspired by an information-theoretic view, AMUR aims to enhance modality information that is more related to user interests while reducing the influence of less aligned signals. Specifically, AMUR first refines modality graph structures towards user behavior, and then selectively aligns shared interest-related semantics across modalities. This enables AMUR to improve modality-interest alignment while preserving useful modality-specific complementary information. Extensive experiments on three real-world datasets demonstrate the effectiveness of AMUR over competitive baselines. The code is available at https://github.com/Wenze1/AMUR.