Research map / Federated learning and privacy / Personalized and heterogeneous FL
Federated Vision-Language-Recommendation with Personalized Fusion
Zhiwei Li, Guodong Long, Jing Jiang, Chengqi Zhang, Qiang Yang
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 FedVLR personalized fusion | FedRAP · Beauty | HR@50: 23.72 -> 38.34 | Improved |
| add FedVLR personalized fusion | FedAvg · KU | HR@50: 11.27 -> 54.90 | Improved |
| add FedVLR personalized fusion | FedNCF · KU | HR@50: 11.76 -> 43.63 | Improved |
| add FedVLR personalized fusion | FedNCF · ML | HR@50: 3.93 -> 11.31 | Improved |
| replace BLFM with generic MLP fusion (ablation) | FedVLR · Beauty | HR@50: FCF: 37.15 -> 41.11 | Mixed |
| replace BLFM with generic MLP fusion (ablation) | FedVLR on FedRAP · Cards | HR@50: 73.74 -> 64.19 | Hurt |
| naive federated VBPR instead of BLFM (ablation) | FedAvg · larger datasets | HR@50 | Hurt |
| remove ID, text or vision features (ablation) | FedVLR · KU | HR@50 | Improved |
| add Gaussian gradient noise | FedVLR · KU, FedNCF | HR@50: 19.61 -> 16.80 | Hurt |
| add Gaussian gradient noise | FedVLR · KU, FedRAP | HR@50: 38.24 -> 37.25 | Hurt |
| use FedVLR instead of centralized models | FedRAP + FedVLR · Beauty | HR@50: 29.25 (MGCN) -> 38.34 | Improved |
| use FedVLR instead of centralized models | FedRAP + FedVLR · Food | HR@50: 36.16 (PGL) -> 11.42 | Hurt |
Closest papers by meaning
- BLEND: Balancing Personalization vs. Generalization in Federated Vision–Language Models (NeurIPS 2026 · similarity 0.88)
- Harmonizing Generalization and Personalization in Federated Prompt Learning (ICML 2024 · similarity 0.86)
- F^3OCUS - Federated Finetuning of Vision-Language Foundation Models with Optimal Client Layer Updating Strategy via Multi-objective Meta-Heuristics (CVPR 2025 · similarity 0.85)
- Personalized Federated Collaborative Filtering: A Variational AutoEncoder Approach (AAAI 2025 · similarity 0.84)
- MMPB: It’s Time for Multi-Modal Personalization (NeurIPS 2025 · similarity 0.84)
- Harnessing Multimodal Large Language Models for Multimodal Sequential Recommendation (AAAI 2025 · similarity 0.84)
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.
