Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedVLN: Privacy-Preserving Federated Vision-and-Language Navigation
Kaiwen Zhou, Xin Eric Wang
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 federated training (FedEnvdrop) instead of centralized training | Envdrop · R2R val-unseen | SR: 44.5 -> 47.5 | Improved |
| add federated training (FedCLIP-ViL) instead of centralized training | CLIP-ViL · R2R val-unseen | SR: 53.6 -> 53.4 | No clear effect |
| add federated training instead of centralized training | Envdrop and CLIP-ViL · R2R/RxR val-seen | SR: average 2.8% SR gap | Hurt |
| add federated training instead of centralized training | Envdrop · RxR val-unseen | SR: 35.0 -> 34.4 | No clear effect |
| add augmented data to federated training | FedEnvdrop · R2R val-unseen | SR: 47.5 -> 51.3 | Improved |
| add augmented data to federated training | FedCLIP-ViL · R2R val-unseen | SR: 53.4 -> 56.9 | Improved |
| add federated speaker instead of centralized speaker for augmentation | CLIP speaker · R2R val-unseen | BLEU2: 30.2 -> 31.6 | Improved |
| add federated speaker instead of centralized speaker for augmentation | CLIP speaker · R2R val-seen | BLEU2: 33.5 -> 31.3 | Hurt |
| share only the language encoder instead of full model in federated pre-exploration (ablation) | Envdrop · R2R unseen val | SR: 62.4 -> 67.2 | Improved |
| share only the language encoder instead of full model in federated pre-exploration (ablation) | CLIP-ViT · R2R unseen val | SR: 65.8 -> 69.1 | Improved |
| add seen environments to federated language encoder pre-exploration (ablation) | Envdrop · R2R unseen val | SR: 67.2 -> 68.3 | Improved |
| add seen environments to federated language encoder pre-exploration (ablation) | CLIP-ViT · R2R unseen val | SR: 69.1 -> 69.5 | Improved |
Closest papers by meaning
- Measuring Physical-World Privacy Awareness of Large Language Models: An Evaluation Benchmark (ICLR 2026 · similarity 0.85)
- AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents (NeurIPS 2025 · similarity 0.85)
- Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor (NeurIPS 2024 · similarity 0.85)
- Theoretically Unmasking Inference Attacks Against LDP-Protected Clients in Federated Vision Models (ICML 2025 · similarity 0.85)
- Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning (NeurIPS 2024 · similarity 0.84)
- PrivAct: Internalizing Contextual Privacy Preservation via Multi-Agent Preference Training (ICML 2026 · 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.
