cs.LGcs.AIcs.CRcs.DC
UMEDA: Unified Multi-modal Efficient Data Fusion for Privacy-Preserving Graph Federated Learning via Spectral-Gated Attention and Diffusion-Based Operator Alignment
May 8, 2026
UMEDA introduces a novel graph federated learning framework that uses spectral signal processing and diffusion models to enable privacy-preserving, robust localization across clients with highly heterogeneous sensor modalities and data distributions.
Device-free localization trains models from heterogeneous wireless and visual sensors (e.g., Wi-Fi, LiDAR) distributed across edge devices. Federated learning offers a privacy-respecting framework, but is brittle when clients differ in sensor modality and resolution, when their data distributions drift, and when privacy noise destroys the structural signal needed for localization. We propose UMEDA, a graph federated learning framework in which clients form nodes of a global graph that share a continuous integral operator, and aggregation is reformulated as spectral signal processing on this operator. Each client encodes its local sensors with a linear-attention layer whose kernel spectrum is low-rank filtered, suppressing modality-specific residuals so clients with different sensors align in a common low-rank subspace. The server then aggregates client updates via a diffusion model over the kernel's spectral coefficients, treating updates as discretizations of a shared operator rather than topology-bound weights -- this absorbs varying graph sizes and missing modalities without node-wise correspondence. To balance privacy and utility, we add an anisotropic differential-privacy mechanism that projects noise preferentially into the null space of the signal subspace, preserving dominant eigendirections while ensuring formal $(ε, δ)$-DP under gradient clipping. On MM-Fi and the RELI11D out-of-distribution benchmark, UMEDA outperforms state-of-the-art federated baselines in accuracy, convergence, and communication efficiency, particularly under high modality heterogeneity and tight privacy budgets.
DDP-SA: Scalable Privacy-Preserving Federated Learning via Distributed Differential Privacy and Secu…
DDP-SA is a novel federated learning framework that combines local differential…
Secure and Privacy-Preserving Vertical Federated Learning
The paper proposes an optimized, end-to-end privacy-preserving framework for ver…
PrivFedTalk: Privacy-Aware Federated Diffusion with Identity-Stable Adapters for Personalized Talkin…
PrivFedTalk introduces a privacy-aware federated framework for personalized talk…
PAC-DP: Personalized Adaptive Clipping for Differentially Private Federated Learning
The paper proposes PAC-DP, a personalized adaptive clipping framework that dynam…
FedFG: Privacy-Preserving and Robust Federated Learning via Flow-Matching Generation
FedFG introduces a robust federated learning framework using flow-matching gener…
FedDetox: Robust Federated SLM Alignment via On-Device Data Sanitization
FedDetox introduces a robust framework that sanitizes toxic data on edge devices…
EPDQ: Efficient and Privacy-Preserving Exact Distance Query on Encrypted Graphs
The paper proposes EPDQ, a tensor-based scheme that efficiently and privately co…
Evaluating Differential Privacy Against Membership Inference in Federated Learning: Insights from th…
This paper empirically evaluates the effectiveness of Differential Privacy (DP)…