Beyond Client Clustering: Fine-Grained Preference Alignment in Federated RLHF via Self-Evolving Routing
· 0 citations
· 35 references
Similar papers
Preprint
Aug 2026
MoE Router-Guided Clustering for Heterogeneous Federated Instruction Tuning
Experimental results show that routing-aware collaboration consistently improves personalized performance compared to conventional federated averaging and local training, while maintaining the same communication cost, and shows that client-centric and expert-centric clustering provides an effective and scalable approach for personalized federated instruction fine-tuning of sparse MoE LLMs.
Ankita Sharma, B. Farahani, S. Moosavi et al.
· 0 citations
Book
Open access
Aug 2026
Disagreement-Aware Subgraph Federated Learning via Uncertainty-Guided Local-Global Alignment
FedDUA is proposed, a novel disagreement-aware and uncertainty-guided framework for subgraph FL that first models cross-client semantic disagreement via a lightweight semantic anchor graph and derives adaptive aggregation weights for reliable global federated knowledge.
Keao Xi, Nannan Wu, Yiming Zhao et al.
· Proceedings of the 32nd ACM... · 0 citations
Breaking the Structural Identity: Personalized Federated LoRA Fine-tuning under Rank Heterogeneity
Large Language Models (LLMs) have achieved remarkable success across diverse domains, but their adaptation to privacy-sensitive, distributed datasets remains a challenge. While Federated Learning (FL) combined with Low-Rank Adaptation (LoRA) provides a resource-efficient paradigm for collaborative fine-tuning, practical deployments are hindered by the dual challenges of resource heterogeneity and data heterogeneity. Existing rank-heterogeneous methods primarily focus on bridging dimension mismatches for aggregation but typically provide a unified global model for all clients sharing the same rank, failing to capture client-specific features in non-IID scenarios. In this paper, we propose FedRoRA (Federated Rank-wise Personalized LoRA), a novel framework that enables fine-grained personalization within rank-heterogeneous federations. FedRoRA decouples adaptation into shared global directions and personalized rank-wise magnitudes governed by learnable diagonal scales. On the server side, it extracts a global subspace via singular value decomposition (SVD) and redistributes client-specific initializations through a personalized projection and top-$k$ selection mechanism. Extensive experiments on NLU and NLG benchmarks demonstrate that FedRoRA consistently outperforms state-of-the-art methods.
Lei Wang, Jieming Bian, Letian Zhang et al.
· 0 citations
Jul 2026
FedTopo: Relation-Level Topology Sharing for Model-Heterogeneous Federated Learning
FedTopo is proposed, a relation-level framework that encodes global knowledge as class relation topology, capturing how classes relate within each client rather than where they lie in feature space.
Zhaoyang Ma, Zhihao Wu, Xin Gao et al.
· arXiv.org · 0 citations
Jul 2026
Federated Foundation Models Fine-Tuning with Heterogeneous Compressed Clients
FedSLM, a parameter-centric framework for federated fine-tuning with heterogeneous compressed clients, is proposed, which provides theoretical guarantees for adapter-level aggregation, subspace-alignment bounds for cross-group fusion, and a characterization of how the confidence loss mitigates weak-supervision noise.
Shengkun Zhu, Jinshan Zeng, Zhihua Allen-Zhao et al.
· arXiv.org · 0 citations
Coordination on a Budget: Federated Active Learning with Few Labels
A new FAL framework is proposed that utilizes federated representation learning to align client data in a shared embedding space that achieves performance that surpasses existing FAL methods even when they are given substantially larger annotation budgets, demonstrating the value of centralized coordination under privacy constraints.
Liam Mohr, D. Weinshall
· 0 citations