Research map / Vision-language and multimodal / Cross-modal learning
DHMRec: Collaboration-Guided Multimodal Disentanglement and Hierarchical Fusion for Recommendation
Xiaohan Zhan, Yuliang Shi, Jihu Wang, Shijun Liu, Fanyu Kong, Zhiyong Chen
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add attention-aware fusion (vs averaging) (ablation) | DHMRec · Amazon Clothing | Recall@20: 0.0824 -> 0.0931 | Improved |
| add attention-aware fusion (vs averaging) (ablation) | DHMRec · Amazon Baby | Recall@20: 0.0980 -> 0.1016 | Improved |
| add item-item graph learning (ablation) | DHMRec · Amazon Clothing | Recall@20: 0.0698 -> 0.0931 | Improved |
| add item-item graph learning (ablation) | DHMRec · Amazon Baby | Recall@20: 0.0887 -> 0.1016 | Improved |
| add modality disentanglement module (ablation) | DHMRec · Amazon Clothing | Recall@20: 0.0901 -> 0.0931 | Improved |
| add modality disentanglement module (ablation) | DHMRec · Amazon Baby | Recall@20: 0.1016 -> 0.1016 | No clear effect |
| use pos-neg attention instead of standard attention (ablation) | DHMRec · Amazon Clothing | NDCG@20: 0.0388 -> 0.0417 | Improved |
| use pos-neg attention instead of standard attention (ablation) | DHMRec · Amazon Sports | NDCG@20: 0.0502 -> 0.0502 | No clear effect |
| add KL alignment between multimodal and ID distributions (ablation) | DHMRec · Amazon Clothing | Recall@20: 0.0874 -> 0.0931 | Improved |
| set multimodal fusion weight alpha_mm to 0 (ID only) (ablation) | DHMRec · Amazon Baby/Sports/Clothing | performance | Hurt |
Closest papers by meaning
- MENTOR: Multi-level Self-supervised Learning for Multimodal Recommendation (AAAI 2025 · similarity 0.90)
- Curriculum Conditioned Diffusion for Multimodal Recommendation (AAAI 2025 · similarity 0.89)
- LGMRec: Local and Global Graph Learning for Multimodal Recommendation (AAAI 2024 · similarity 0.89)
- Seeing Beyond Noise: Joint Graph Structure Evaluation and Denoising for Multimodal Recommendation (AAAI 2025 · similarity 0.89)
- DOGE: LLMs-Enhanced Hyper-Knowledge Graph Recommender for Multimodal Recommendation (AAAI 2025 · similarity 0.88)
- Beyond Graph Convolution: Multimodal Recommendation with Topology-aware MLPs (AAAI 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
