Tag
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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.
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%.
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.
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。
This paper presents an adaptive joint compression and synchronization mechanism for federated split learning to reduce communication overhead in IoT rainfall prediction, achieving significant traffic reduction without major loss in predictive quality.
This paper introduces PACT, a method for structuring agent-to-agent communication in multi-agent LLM systems that uses compact action-state records to reduce token consumption while maintaining or improving task performance, with demonstrated gains on SWE-agent and OpenHands.