paper-with-me

홈 › Papers

pFedNavi: Structure-Aware Personalized Federated Vision-Language Navigation for Embodied AI

2026-02-16 · Qingqian Yang, Hao Wang, Sai Qian Zhang, Jian Li, Yang Hua, Miao Pan, Tao Song, Zhengwei Qi, Haibing Guan arxiv

Vision-Language Navigation VLN requires large-scale trajectory instruction data from private indoor environments, raising significant privacy concerns. Federated Learning FL mitigates this by keeping data on-device, but vanilla FL struggles under VLNs' extreme cross-client heterogeneity in environments and instruction styles, making a single global model suboptimal. This paper proposes pFedNavi, a structure-aware and dynamically adaptive personalized federated learning framework tailored for VLN. Our key idea is to personalize where it matters: pFedNavi adaptively identifies client-specific layers via layer-wise mixing coefficients, and performs fine-grained parameter fusion on the selected components (e.g., the encoder-decoder projection and environment-sensitive decoder layers) to balance global knowledge sharing with local specialization. We evaluate pFedNavi on two standard VLN benchmarks, R2R and RxR, using both ResNet and CLIP visual representations. Across all metrics, pFedNavi consistently outperforms the FedAvg-based VLN baseline, achieving up to 7.5% improvement in navigation success rate and up to 7.8% gain in trajectory fidelity, while converging 1.38x faster under non-IID conditions.

📄 PDF Abstract BibTeX arXiv:2602.14401

Code (0)

등록된 구현이 없습니다.

Tasks

Personalized Federated LearningVision-Language Navigation

Similar Papers 제목 키워드 기반

Frugal Federated Learning for Violence Detection: A Comparison of LoRA-Tuned VLMs and Personalized CNNs

2025-10-20 · Sébastien Thuau, Siba Haidar, Ayush Bajracharya, Rachid Chelouah arxiv

We examine frugal federated learning approaches to violence detection by comparing two complementary strategies: (i) zero-shot and federated fine-tuning of vision-language models (VLMs), and (ii) personalized training of…

Federated Learning

DPFNAS: Differential Privacy-Enhanced Federated Neural Architecture Search for 6G Edge Intelligence

2025-09-27 · Yang Lv, Jin Cao, Ben Niu, Zhe Sun 외 arxiv

The Sixth-Generation (6G) network envisions pervasive artificial intelligence (AI) as a core goal, enabled by edge intelligence through on-device data utilization. To realize this vision, federated learning (FL) has emer…

Neural Architecture SearchFederated Learning

SAFL: Structure-Aware Personalized Federated Learning via Client-Specific Clustering and SCSI-Guided Model Pruning

2025-01-30 · Nan Li, Xiaolu Wang, Xiao Du, Puyu Cai 외

Federated Learning (FL) enables clients to collaboratively train machine learning models without sharing local data, preserving privacy in diverse environments. While traditional FL approaches preserve privacy, they ofte…

Federated LearningPersonalized Federated Learning

Energizing Federated Learning via Filter-Aware Attention

2023-11-18 · Ziyuan Yang, Zerui Shao, Huijie Huangfu, Hui Yu 외

Federated learning (FL) is a promising distributed paradigm, eliminating the need for data sharing but facing challenges from data heterogeneity. Personalized parameter generation through a hypernetwork proves effective,…

Federated Learning

ML Mule: Mobile-Driven Context-Aware Collaborative Learning

2025-01-13 · Haoxiang Yu, Javier Berrocal, Christine Julien

Artificial intelligence has been integrated into nearly every aspect of daily life, powering applications from object detection with computer vision to large language models for writing emails and compact models for use …

object-detectionObject Detection