communication-efficiency

Tag

Cards List
#communication-efficiency

Communication-Efficient Private Federated Reinforcement Learning with Post-Quantum Authentication for Vehicular Networks

arXiv cs.LG ↗ · 2026-11-02 Cached

An academic paper proposing correlated private quantization for communication-efficient, locally differentially private federated reinforcement learning in vehicular networks, coupled with post-quantum authentication; it reports 92.4% smaller authenticated uplink sizes and 14.3% lower mean travel time versus independent quantization.

0 favorites 0 likes
#communication-efficiency

TRACE: Transformer Residual Activation Codebook Encoding for Communication-efficient Distributed Edge Inference

arXiv cs.LG ↗ · 2026-10-19 Cached

论文提出 TRACE(Transformer Residual Activation Codebook Encoding),在每个 Transformer 层的后注意力残差处放置向量量化器并预计算码本索引化的键值表示,使分布式边缘设备推理中接收方通过查表直接恢复 K/V,实现通信-计算重叠;在 ViT-Base 与 ViViT-B 上相比最优 VQ 分布式推理框架最高提升 1.89% 精度与 1.27 倍端到端加速,通信开销最高降低 22,624 倍。

0 favorites 0 likes
#communication-efficiency

Adaptive Bayesian Partner Selection for Federated Clinical Centers

arXiv cs.LG ↗ · 2026-09-16 Cached

The paper proposes Adaptive Bayesian Partner Selection (ABPS), a peer-to-peer federated learning framework that adaptively selects collaboration partners using Bayesian methods to reduce communication costs while maintaining accuracy in heterogeneous healthcare settings.

0 favorites 0 likes
#communication-efficiency

Adaptive Phase-Switching for Communication-Efficient Federated LoRA Fine-Tuning

arXiv cs.LG ↗ · 2026-09-15 Cached

This paper introduces an adaptive phase-switching method for communication-efficient federated LoRA fine-tuning, achieving up to 40.5% round-trip savings in communication costs while maintaining model performance on large language models.

0 favorites 0 likes
#communication-efficiency

EMMI: Edge Multi-Modal Intelligence for Communication-Efficient MLLM Inference via Fused Representation Compression

arXiv cs.LG ↗ · 2026-09-11 Cached

EMMI proposes a method for communication-efficient multimodal large language model inference on edge devices by compressing representations, reducing communication payload by 32× while maintaining accuracy.

0 favorites 0 likes
#communication-efficiency

Byzantine-Robust Federated Fire Detection with a Rotating Coordinator

arXiv cs.LG ↗ · 2026-09-11 Cached

This paper presents a federated learning approach for indoor fire detection that addresses bandwidth constraints, Byzantine attacks, and fixed-server issues through compressed updates and a rotating coordinator.

0 favorites 0 likes
#communication-efficiency

FedSubMuon: Communication-Efficient Federated LLM Fine-Tuning via Structured Subspace Muon

arXiv cs.LG ↗ · 2026-09-10 Cached

FedSubMuon is a communication-efficient federated fine-tuning method for LLMs that optimizes compact coefficient matrices within structured subspaces to reduce upload costs while maintaining strong performance.

0 favorites 0 likes
#communication-efficiency

X-CoSD: Communication-Efficient Cross-Vocabulary Collaborative Speculative Decoding

arXiv cs.CL ↗ · 2026-09-10 Cached

This paper introduces X-CoSD, a communication-efficient cross-vocabulary collaborative speculative decoding framework that optimizes distributed LLM inference by splitting residual resampling to reduce overhead while preserving server LLM quality.

0 favorites 0 likes
#communication-efficiency

RW-LoRA: Communication-Efficient Decentralized LoRA Fine-Tuning via Random Walks

arXiv cs.LG ↗ · 2026-09-02 Cached

This paper introduces RW-LoRA, a decentralized LoRA fine-tuning method using random walks to reduce communication and computation costs while achieving competitive performance on NLP tasks.

0 favorites 0 likes
#communication-efficiency

Polar Code Based Federated Learning: Convergence Analysis and Resource Allocation

arXiv cs.LG ↗ · 2026-08-17 Cached

This paper proposes a cross-layer polar code based federated learning scheme to address communication bottlenecks and channel impairments, providing convergence analysis and resource optimization that demonstrates performance gains over uncoded and LDPC-based benchmarks.

0 favorites 0 likes
#communication-efficiency

Dynamic Coalition Formation and Communication Pricing in Skill-Based Agentic AI Systems

arXiv cs.AI ↗ · 2026-08-11 Cached

This paper formalizes agent coalition formation and inter-agent communication as a cooperative game, proposing marginal-value activation rules and Shapley-based online routing to reduce token costs and improve efficiency in multi-agent LLM systems, with theoretical guarantees and synthetic simulation results.

0 favorites 0 likes
#communication-efficiency

Theoretical Foundations of Communication-Efficient, Robust, and Practical Distributed and Federated Optimization

arXiv cs.LG ↗ · 2026-08-10 Cached

This thesis tackles seven challenges in distributed and federated optimization, introducing methods like ProxSkip and Variance Reduced ProxSkip, and establishing theoretical foundations for communication-efficient, robust, and practical algorithms.

0 favorites 0 likes
#communication-efficiency

DG-FedReuse: Proxy-Gradient-Gated Cached-Update Reuse with Matched Sparse Uplink Accounting

arXiv cs.LG ↗ · 2026-08-07 Cached

Presents DG-FedReuse, a federated learning mechanism that reuses age-decayed cached client updates under a proxy-gradient threshold to reduce uplink communication, achieving significant modeled savings with minimal accuracy loss on image classification benchmarks.

0 favorites 0 likes
#communication-efficiency

QFedPolyp: A Communication- and Inference-Efficient Federated Learning Framework for Polyp Segmentation

arXiv cs.LG ↗ · 2026-07-28 Cached

QFedPolyp proposes a federated learning framework for polyp segmentation that uses quantization-aware training to reduce communication costs and achieve faster inference while preserving privacy.

0 favorites 0 likes
#communication-efficiency

Variance-Reduced Q-Learning over Static and Time-Varying Networks

arXiv cs.LG ↗ · 2026-07-27 Cached

Introduces VRDQ, a decentralized Q-learning algorithm for multi-agent reinforcement learning over static and time-varying networks, with finite-time convergence guarantees that achieve linear speedups in sample complexity with only Õ(1) communication.

0 favorites 0 likes
#communication-efficiency

Federated Lightweight Fine-Tuning

arXiv cs.LG ↗ · 2026-07-22 Cached

This paper introduces FLITE (Federated Low-rank Iterative Training Engine), a method for federated fine-tuning that reduces per-client communication to 1,280 floats per round (about 5KB) — an 8718× reduction over full-weight FedAvg — by using a frozen affine mapping network that generates weights from a small trainable latent and a low-rank seed-regenerable factorization, achieving accuracy within 0.5 percentage points of full-weight FedAvg on CIFAR-100 with ResNet-18.

0 favorites 0 likes
#communication-efficiency

PFAdapter: Hierarchical LoRA Decomposition for Personalized Federated MLLMs

arXiv cs.LG ↗ · 2026-07-15 Cached

This paper introduces PFAdapter, a communication-efficient framework for personalized federated fine-tuning of Multimodal Large Language Models (MLLMs). It uses hierarchical LoRA decomposition to separate adapter parameters into global-shared and local-private components, achieving near 50% reduction in communication costs while improving personalization through orthogonality regularization.

0 favorites 0 likes
#communication-efficiency

SCAPE: Accurate and Efficient LLM Training with Extreme Sparse Communication

arXiv cs.LG ↗ · 2026-07-03 Cached

SCAPE is a communication-efficient distributed optimizer that leverages first-moment statistics to enable extreme sparsification for LLM training, preserving accuracy while reducing wall-clock time by up to 43.3%.

0 favorites 0 likes
#communication-efficiency

TallyTrain: Communication-Efficient Federated Distillation

arXiv cs.LG ↗ · 2026-07-02 Cached

This paper introduces TallyTrain, a communication-efficient federated distillation method that transmits only the argmax class index per probe (hard-label consensus) instead of full softmax vectors, reducing bandwidth by up to three orders of magnitude while matching or surpassing the performance of soft-label distillation and Pareto-dominating standard federated learning baselines like FedAvg, FedProx, and FedDF.

0 favorites 0 likes
#communication-efficiency

Expected Gain-based Escalation in Vertical Federated Learning

arXiv cs.LG ↗ · 2026-07-01 Cached

本文研究垂直联邦学习中的选择性升级问题,提出一种基于期望增益的评分方法,在低成本的本地预测和高成本的嵌入融合之间进行路由,以优化通信-准确率权衡。

0 favorites 0 likes
Next →
← Back to home

Submit Feedback