CADMR: Cross-Attention and Disentangled Learning for Multimodal Recommender Systems

• URL: http://arxiv.org/abs/2412.02295v1
• Date: Tue, 03 Dec 2024 09:09:52 GMT
• Title: CADMR: Cross-Attention and Disentangled Learning for Multimodal Recommender Systems
• Authors: Yasser Khalafaoui, Martino Lovisetto, Basarab Matei, Nistor Grozavu,
• Abstract summary: We propose CADMR, a novel autoencoder-based multimodal recommender system framework. We evaluate CADMR on three benchmark datasets, demonstrating significant performance improvements over state-of-the-art methods.
• Score: 0.6037276428689637
• License:
• Abstract: The increasing availability and diversity of multimodal data in recommender systems offer new avenues for enhancing recommendation accuracy and user satisfaction. However, these systems must contend with high-dimensional, sparse user-item rating matrices, where reconstructing the matrix with only small subsets of preferred items for each user poses a significant challenge. To address this, we propose CADMR, a novel autoencoder-based multimodal recommender system framework. CADMR leverages multi-head cross-attention mechanisms and Disentangled Learning to effectively integrate and utilize heterogeneous multimodal data in reconstructing the rating matrix. Our approach first disentangles modality-specific features while preserving their interdependence, thereby learning a joint latent representation. The multi-head cross-attention mechanism is then applied to enhance user-item interaction representations with respect to the learned multimodal item latent representations. We evaluate CADMR on three benchmark datasets, demonstrating significant performance improvements over state-of-the-art methods.

Related papers

• Learning ID-free Item Representation with Token Crossing for Multimodal Recommendation [26.737971605928358]
  We propose an ID-free MultimOdal TOken Representation scheme named MOTOR. We first employ product quantization to discretize each item's multimodal features into discrete token IDs. We then interpret the token embeddings corresponding to these token IDs as implicit item features. The resulting representations can replace the original ID embeddings and transform the original multimodal recommender into ID-free system.
  arXiv  Detail & Related papers  (2024-10-25T03:06:10Z)
• A Unified Graph Transformer for Overcoming Isolations in Multi-modal Recommendation [9.720586396359906]
  We argue that existing multi-modal recommender systems typically use isolated processes for both feature extraction and modality modelling. We propose a novel model, called Unified Multi-modal Graph Transformer (UGT), which leverages a multi-way transformer to extract aligned multi-modal features. We show that the UGT model can achieve significant effectiveness gains, especially when jointly optimised with the commonly-used multi-modal recommendation losses.
  arXiv  Detail & Related papers  (2024-07-29T11:04:31Z)
• MMGRec: Multimodal Generative Recommendation with Transformer Model [81.61896141495144]
  MMGRec aims to introduce a generative paradigm into multimodal recommendation. We first devise a hierarchical quantization method Graph CF-RQVAE to assign Rec-ID for each item from its multimodal information. We then train a Transformer-based recommender to generate the Rec-IDs of user-preferred items based on historical interaction sequences.
  arXiv  Detail & Related papers  (2024-04-25T12:11:27Z)
• AlignRec: Aligning and Training in Multimodal Recommendations [29.995007279325947]
  multimodal recommendations can leverage rich contexts beyond interactions. Existing methods mainly regard multimodal information as an auxiliary, using them to help learn ID features. There exist semantic gaps among multimodal content features and ID-based features, for which directly using multimodal information as an auxiliary would lead to misalignment in representations of users and items.
  arXiv  Detail & Related papers  (2024-03-19T02:49:32Z)
• BiVRec: Bidirectional View-based Multimodal Sequential Recommendation [55.87443627659778]
  We propose an innovative framework, BivRec, that jointly trains the recommendation tasks in both ID and multimodal views. BivRec achieves state-of-the-art performance on five datasets and showcases various practical advantages.
  arXiv  Detail & Related papers  (2024-02-27T09:10:41Z)
• Feature Decoupling-Recycling Network for Fast Interactive Segmentation [79.22497777645806]
  Recent interactive segmentation methods iteratively take source image, user guidance and previously predicted mask as the input. We propose the Feature Decoupling-Recycling Network (FDRN), which decouples the modeling components based on their intrinsic discrepancies.
  arXiv  Detail & Related papers  (2023-08-07T12:26:34Z)
• Choosing the Best of Both Worlds: Diverse and Novel Recommendations through Multi-Objective Reinforcement Learning [68.45370492516531]
  We introduce Scalarized Multi-Objective Reinforcement Learning (SMORL) for the Recommender Systems (RS) setting. SMORL agent augments standard recommendation models with additional RL layers that enforce it to simultaneously satisfy three principal objectives: accuracy, diversity, and novelty of recommendations. Our experimental results on two real-world datasets reveal a substantial increase in aggregate diversity, a moderate increase in accuracy, reduced repetitiveness of recommendations, and demonstrate the importance of reinforcing diversity and novelty as complementary objectives.
  arXiv  Detail & Related papers  (2021-10-28T13:22:45Z)
• Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation [56.12499090935242]
  This work proposes a Knowledge-Enhanced Hierarchical Graph Transformer Network (KHGT) to investigate multi-typed interactive patterns between users and items in recommender systems. KHGT is built upon a graph-structured neural architecture to capture type-specific behavior characteristics. We show that KHGT consistently outperforms many state-of-the-art recommendation methods across various evaluation settings.
  arXiv  Detail & Related papers  (2021-10-08T09:44:00Z)
• Lightweight Self-Attentive Sequential Recommendation [30.048184102259494]
  We introduce a novel lightweight self-attentive network (LSAN) for sequential recommendation. To aggressively compress the original embedding matrix, LSAN leverages the notion of compositional embeddings. To account for the intrinsic dynamics of each item, we propose a temporal context-aware embedding composition scheme.
  arXiv  Detail & Related papers  (2021-08-25T16:46:47Z)
• Federated Multi-view Matrix Factorization for Personalized Recommendations [53.74747022749739]
  We introduce the federated multi-view matrix factorization method that extends the federated learning framework to matrix factorization with multiple data sources. Our method is able to learn the multi-view model without transferring the user's personal data to a central server.
  arXiv  Detail & Related papers  (2020-04-08T21:07:50Z)

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.