arXiv subjects

Yunming Liao

Publications and source records attributed to Yunming Liao.

15 recordsLinked to original sources

arXiv2026

ReLoRA: Knowledge-Reusing Adaptation for Fast Rollout of Evolving LLM Services

Large Language Models (LLMs) are increasingly deployed as continuously evolving services, where frequent base-model updates may invalidate previously deployed task-specific Low-Rank Adaptation (LoRA) adapters. For service providers managing numerous downstream model services, retraining each LoRA adapter from scratch for every updated base model is computationally prohibitive and delays service rollout. Meanwhile, the simpler alternative, i.e., naively applying the original LoRA adapter to the updated base model, often leads to degraded service quality due to adapter-backbone incompatibility. To address this problem, we propose ReLoRA, a knowledge-reusing re-adaptation framework that efficiently restores service-ready LoRA adapters for evolving LLM services while preserving or improving task performance. Specifically, ReLoRA comprises two key optimization steps: 1) Adaptive LoRA initialization leverages Bayesian optimization to construct a compatibility-aware starting point by fusing information from both the previously deployed task adapter and the base model's evolution; 2) Fine-tuning with scheduled regularization first rapidly steers the adapter to a high-quality region via strong regularization, followed by relaxed regularization for task-specific refinement. This design enables rapid service-quality recovery with reduced re-adaptation overhead. Extensive experiments demonstrate that ReLoRA reduces time-to-readiness by up to 8.9$\times$ and improves accuracy by up to 4.6\% compared to baselines.

cs.LG↗

arXiv2026

Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices

In agent-driven question answering (QA) applications, retrieval-augmented generation (RAG) is commonly introduced to enhance the response accuracy of large language models (LLMs) by providing additional context. Due to the inherent noise in retrieval results and the coarse granularity of document-level retrieval, the retrieved context often contains substantial redundant information. In this setting, the agent prompt, consisting of the user query and the associated retrieved context, leads to unnecessary computational overhead during LLM inference. Existing prompt compression methods typically rely on auxiliary small language models (SLMs) to estimate context importance. However, such approaches introduce significant memory and computational overhead, which limits their deployment on resource-constrained edge devices. In this paper, we propose CORE, a two-stage sentence-level prompt compression method that eliminates the need for SLMs. In the first stage, CORE constructs an answer set via named entity recognition (NER) and a clue set via semantic matching. In the second stage, CORE refines the clue set using an orthogonal residual retrieval strategy and designs a spatial proximity-based metric to filter the answer set. The two sets are then combined to form the final compressed context. We implement CORE on an NVIDIA Jetson AGX Orin edge device and a Huawei Nova smartphone. Experimental results demonstrate that within a 2000-token budget, CORE improves accuracy by at least 30.19% compared to state-of-the-art baselines, while reducing memory usage by at least 50.47% and achieving at least 1.94 times speedup on the edge device. Moreover, compared to the state-of-the-art LLMLingua2 method, CORE achieves a substantial energy reduction of 95.74% on the smartphone, highlighting its practicality and generalizability for mobile deployments.

cs.CL↗

arXiv2025

DySTop

Federated Learning (FL) has emerged as a potential distributed learning paradigm that enables model training on edge devices (i.e., workers) while preserving data privacy. However, its reliance on a centralized server leads to limited scalability. Decentralized federated learning (DFL) eliminates the dependency on a centralized server by enabling peer-to-peer model exchange. Existing DFL mechanisms mainly employ synchronous communication, which may result in training inefficiencies under heterogeneous and dynamic edge environments. Although a few recent asynchronous DFL (ADFL) mechanisms have been proposed to address these issues, they typically yield stale model aggregation and frequent model transmission, leading to degraded training performance on non-IID data and high communication overhead. To overcome these issues, we present DySTop, an innovative mechanism that jointly optimizes dynamic staleness control and topology construction in ADFL. In each round, multiple workers are activated, and a subset of their neighbors is selected to transmit models for aggregation, followed by local training. We provide a rigorous convergence analysis for DySTop, theoretically revealing the quantitative relationships between the convergence bound and key factors such as maximum staleness, activating frequency, and data distribution among workers. From the insights of the analysis, we propose a worker activation algorithm (WAA) for staleness control and a phase-aware topology construction algorithm (PTCA) to reduce communication overhead and handle data non-IID. Extensive evaluations through both large-scale simulations and real-world testbed experiments demonstrate that our DySTop reduces completion time by 51.8% and the communication resource consumption by 57.1% compared to state-of-the-art solutions, while maintaining the same model accuracy.

cs.DC↗

arXiv2025

Collaborative Speculative Inference for Efficient LLM Inference Serving

Speculative inference is a promising paradigm employing small speculative models (SSMs) as drafters to generate draft tokens, which are subsequently verified in parallel by the target large language model (LLM). This approach enhances the efficiency of inference serving by reducing LLM inference latency and costs while preserving generation quality. However, existing speculative methods face critical challenges, including inefficient resource utilization and limited draft acceptance, which constrain their scalability and overall effectiveness. To overcome these obstacles, we present CoSine, a novel speculative inference system that decouples sequential speculative decoding from parallel verification, enabling efficient collaboration among multiple nodes. Specifically, CoSine routes inference requests to specialized drafters based on their expertise and incorporates a confidence-based token fusion mechanism to synthesize outputs from cooperating drafters, ensuring high-quality draft generation. Additionally, CoSine dynamically orchestrates the execution of speculative decoding and verification in a pipelined manner, employing batch scheduling to selectively group requests and adaptive speculation control to minimize idle periods. By optimizing parallel workflows through heterogeneous node collaboration, CoSine balances draft generation and verification throughput in real-time, thereby maximizing resource utilization. Experimental results demonstrate that CoSine achieves superior performance compared to state-of-the-art speculative approaches. Notably, with equivalent resource costs, CoSine achieves up to a 23.2% decrease in latency and a 32.5% increase in throughput compared to baseline methods.

cs.DC↗

arXiv2025

Cross-region Model Training with Communication-Computation Overlapping and Delay Compensation

Training large language models (LLMs) requires massive computational resources, often necessitating the aggregation of geographically distributed data centers (\ie, cross-region training). However, the high communication latency in wide-area networks severely degrades the efficiency of traditional distributed training. While methods like DiLoCo reduce communication frequency, they suffer from blocking synchronization. Streaming DiLoCo alleviates this issue via communication-computation overlapping but introduces update staleness and model inconsistency due to delayed global updates and partial synchronization. These factors impair convergence, especially when aggressive overlap is needed to mask high latency. We propose CoCoDC, a novel distributed training framework with communication-computation overlapping and delay compensation, to explicitly tackle these challenges. Within the CoCoDC framework, we specifically develop a novel Delay Compensation strategy based on Taylor expansion to effectively mitigate the staleness and an Adaptive Transmission strategy that dynamically schedules model fragment synchronization to optimize bandwidth usage and accelerate convergence. Extensive experiments highlight the superior performance of CoCoDC over both DiLoCo and Streaming DiLoCo regarding final accuracy and training speed. Specifically, CoCoDC reduces the training steps needed to reach a comparable perplexity by up to 21.0% compared to Streaming DiLoCo. Our work provides an effective solution for scalable and efficient cross-region LLM training.

cs.DC↗

arXiv2025

Resource-Efficient Federated Fine-Tuning Large Language Models for Heterogeneous Data

Fine-tuning large language models (LLMs) via federated learning, i.e., FedLLM, has been proposed to adapt LLMs for various downstream applications in a privacy-preserving way. To reduce the fine-tuning costs on resource-constrained devices, FedLoRA is proposed to fine-tune only a small subset of model parameters by integrating low-rank adaptation (LoRA) into FedLLM. However, apart from resource constraints, there is still another critical challenge, i.e., data heterogeneity, severely hindering the implementation of FedLoRA in practical applications. Herein, inspired by the previous group-based federated learning paradigm, we propose a hierarchical FedLoRA framework, termed HierFedLoRA, to address these challenges. Specifically, HierFedLoRA partitions all devices into multiple near-IID groups and adjusts the intra-group aggregation frequency for each group to eliminate the negative effects of non-IID data. Meanwhile, to reduce the computation and communication cost, HierFedLoRA dynamically assigns diverse and suitable fine-tuning depth (i.e., the number of continuous fine-tuning layers from the output) for each group. HierFedLoRA explores jointly optimizing aggregation frequency and depth upon their coupled relationship to better enhance the performance of FedLoRA. Extensive experiments are conducted on a physical platform with 80 commercial devices. The results show that HierFedLoRA improves the final model accuracy by 1.6% to 4.2%, speeding up the fine-tuning process by at least 2.1$\times$, compared to the strong baselines.

cs.LG↗

arXiv2025

A Novel Hat-Shaped Device-Cloud Collaborative Inference Framework for Large Language Models

Recent advancements in large language models (LLMs) have catalyzed a substantial surge in demand for LLM services. While traditional cloud-based LLM services satisfy high-accuracy requirements, they fall short in meeting critical demands for low delay and enhanced privacy. To address these limitations, we propose HAT, a novel device-cloud collaborative inference framework that leverages the complementary strengths of U-shaped inference and speculative decoding. HAT partitions the LLM into three submodels, and the input and output submodels, stacked with a lightweight adapter network, are deployed as a small language model (SLM) on each end device. Meanwhile, the middle submodel, encompassing the majority of the LLM's decoder layers, is hosted in the cloud to perform speculative decoding with on-device SLMs. During inference, HAT exchanges hidden states (rather than raw tokens) of input or draft tokens between devices and the cloud, thereby incurring substantial communication delays. Besides, processing hidden states of long prompts will exacerbate computation delays in the cloud, further compromising inference efficiency. To improve efficiency, we introduce a prompt chunking mechanism that segments long prompts into shorter chunks, enabling parallel transmission and processing. Furthermore, HAT is implemented to dynamically determine optimal chunk sizes for devices handling long prompts, thereby improving overall inference speed. Extensive experiments are conducted on a physical testbed comprising 30 NVIDIA Jetson devices and a server with 8 NVIDIA A6000 GPUs. Experimental results demonstrate that HAT achieves promising performance improvements, reducing TTFT by 41% to 54% and TBT by 41% to 77% compared to the baselines.

cs.LG↗

arXiv2025

Lightweight and Post-Training Structured Pruning for On-Device Large Lanaguage Models

Considering the hardware-friendly characteristics and broad applicability, structured pruning has emerged as an efficient solution to reduce the resource demands of large language models (LLMs) on resource-constrained devices. Traditional structured pruning methods often need fine-tuning to recover performance loss, which incurs high memory overhead and substantial data requirements, rendering them unsuitable for on-device applications. Additionally, post-training structured pruning techniques typically necessitate specific activation functions or architectural modifications, thereby limiting their scope of applications. Herein, we introduce COMP, a lightweight post-training structured pruning method that employs a hybrid-granularity pruning strategy. COMP initially prunes selected model layers based on their importance at a coarse granularity, followed by fine-grained neuron pruning within the dense layers of each remaining model layer. To more accurately evaluate neuron importance, COMP introduces a new matrix condition-based metric. Subsequently, COMP utilizes mask tuning to recover accuracy without the need for fine-tuning, significantly reducing memory consumption. Experimental results demonstrate that COMP improves performance by 6.13\% on the LLaMA-2-7B model with a 20\% pruning ratio compared to LLM-Pruner, while simultaneously reducing memory overhead by 80\%.

cs.LG↗

arXiv2025

Efficient Deployment of Large Language Models on Resource-constrained Devices

Deploying Large Language Models (LLMs) on resource-constrained (or weak) devices presents significant challenges due to limited resources and heterogeneous data distribution. To address the data concern, it is necessary to fine-tune LLMs using on-device private data for various downstream tasks. While Federated Learning (FL) offers a promising privacy-preserving solution, existing fine-tuning methods retain the original LLM size, leaving issues of high inference latency and excessive memory demands unresolved. Hence, we design FedSpine, an FL framework that combines Parameter- Efficient Fine-Tuning (PEFT) with structured pruning for efficient deployment of LLMs on resource-constrained devices. Specifically, FedSpine introduces an iterative process to prune and tune the parameters of LLMs. To mitigate the impact of device heterogeneity, an online Multi-Armed Bandit (MAB) algorithm is employed to adaptively determine different pruning ratios and LoRA ranks for heterogeneous devices without any prior knowledge of their computing and communication capabilities. As a result, FedSpine maintains higher inference accuracy while improving fine-tuning efficiency. Experimental results conducted on a physical platform with 80 devices demonstrate that FedSpine can speed up fine-tuning by 1.4$\times$-6.9$\times$ and improve final accuracy by 0.4%-4.5% under the same sparsity level compared to other baselines.

cs.LG↗

arXiv2024

Adaptive Parameter-Efficient Federated Fine-Tuning on Heterogeneous Devices

Federated fine-tuning (FedFT) has been proposed to fine-tune the pre-trained language models in a distributed manner. However, there are two critical challenges for efficient FedFT in practical applications, i.e., resource constraints and system heterogeneity. Existing works rely on parameter-efficient fine-tuning methods, e.g., low-rank adaptation (LoRA), but with major limitations. Herein, based on the inherent characteristics of FedFT, we observe that LoRA layers with higher ranks added close to the output help to save resource consumption while achieving comparable fine-tuning performance. Then we propose a novel LoRA-based FedFT framework, termed LEGEND, which faces the difficulty of determining the number of LoRA layers (called, LoRA depth) and the rank of each LoRA layer (called, rank distribution). We analyze the coupled relationship between LoRA depth and rank distribution, and design an efficient LoRA configuration algorithm for heterogeneous devices, thereby promoting fine-tuning efficiency. Extensive experiments are conducted on a physical platform with 80 commercial devices. The results show that LEGEND can achieve a speedup of 1.5-2.8$\times$ and save communication costs by about 42.3% when achieving the target accuracy, compared to the advanced solutions.

cs.DC↗

arXiv2024

Collaborative Inference for Large Models with Task Offloading and Early Exiting

In 5G smart cities, edge computing is employed to provide nearby computing services for end devices, and the large-scale models (e.g., GPT and LLaMA) can be deployed at the network edge to boost the service quality. However, due to the constraints of memory size and computing capacity, it is difficult to run these large-scale models on a single edge node. To meet the resource constraints, a large-scale model can be partitioned into multiple sub-models and deployed across multiple edge nodes. Then tasks are offloaded to the edge nodes for collaborative inference. Additionally, we incorporate the early exit mechanism to further accelerate inference. However, the heterogeneous system and dynamic environment will significantly affect the inference efficiency. To address these challenges, we theoretically analyze the coupled relationship between task offloading strategy and confidence thresholds, and develop a distributed algorithm, termed DTO-EE, based on the coupled relationship and convex optimization. DTO-EE enables each edge node to jointly optimize its offloading strategy and the confidence threshold, so as to achieve a promising trade-off between response delay and inference accuracy. The experimental results show that DTO-EE can reduce the average response delay by 21%-41% and improve the inference accuracy by 1%-4%, compared to the baselines.

cs.DC↗

arXiv2024

ParallelSFL: A Novel Split Federated Learning Framework Tackling Heterogeneity Issues

Mobile devices contribute more than half of the world's web traffic, providing massive and diverse data for powering various federated learning (FL) applications. In order to avoid the communication bottleneck on the parameter server (PS) and accelerate the training of large-scale models on resourceconstraint workers in edge computing (EC) system, we propose a novel split federated learning (SFL) framework, termed ParallelSFL. Concretely, we split an entire model into a bottom submodel and a top submodel, and divide participating workers into multiple clusters, each of which collaboratively performs the SFL training procedure and exchanges entire models with the PS. However, considering the statistical and system heterogeneity in edge systems, it is challenging to arrange suitable workers to specific clusters for efficient model training. To address these challenges, we carefully develop an effective clustering strategy by optimizing a utility function related to training efficiency and model accuracy. Specifically, ParallelSFL partitions workers into different clusters under the heterogeneity restrictions, thereby promoting model accuracy as well as training efficiency. Meanwhile, ParallelSFL assigns diverse and appropriate local updating frequencies for each cluster to further address system heterogeneity. Extensive experiments are conducted on a physical platform with 80 NVIDIA Jetson devices, and the experimental results show that ParallelSFL can reduce the traffic consumption by at least 21%, speed up the model training by at least 1.36x, and improve model accuracy by at least 5% in heterogeneous scenarios, compared to the baselines.

cs.DC↗

arXiv2024

SemiSFL: Split Federated Learning on Unlabeled and Non-IID Data

Federated Learning (FL) has emerged to allow multiple clients to collaboratively train machine learning models on their private data at the network edge. However, training and deploying large-scale models on resource-constrained devices is challenging. Fortunately, Split Federated Learning (SFL) offers a feasible solution by alleviating the computation and/or communication burden on clients. However, existing SFL works often assume sufficient labeled data on clients, which is usually impractical. Besides, data non-IIDness poses another challenge to ensure efficient model training. To our best knowledge, the above two issues have not been simultaneously addressed in SFL. Herein, we propose a novel Semi-supervised SFL system, termed SemiSFL, which incorporates clustering regularization to perform SFL with unlabeled and non-IID client data. Moreover, our theoretical and experimental investigations into model convergence reveal that the inconsistent training processes on labeled and unlabeled data have an influence on the effectiveness of clustering regularization. To mitigate the training inconsistency, we develop an algorithm for dynamically adjusting the global updating frequency, so as to improve training performance. Extensive experiments on benchmark models and datasets show that our system provides a 3.8x speed-up in training time, reduces the communication cost by about 70.3% while reaching the target accuracy, and achieves up to 5.8% improvement in accuracy under non-IID scenarios compared to the state-of-the-art baselines.

cs.LG↗

arXiv2024

MergeSFL: Split Federated Learning with Feature Merging and Batch Size Regulation

Recently, federated learning (FL) has emerged as a popular technique for edge AI to mine valuable knowledge in edge computing (EC) systems. To mitigate the computing/communication burden on resource-constrained workers and protect model privacy, split federated learning (SFL) has been released by integrating both data and model parallelism. Despite resource limitations, SFL still faces two other critical challenges in EC, i.e., statistical heterogeneity and system heterogeneity. To address these challenges, we propose a novel SFL framework, termed MergeSFL, by incorporating feature merging and batch size regulation in SFL. Concretely, feature merging aims to merge the features from workers into a mixed feature sequence, which is approximately equivalent to the features derived from IID data and is employed to promote model accuracy. While batch size regulation aims to assign diverse and suitable batch sizes for heterogeneous workers to improve training efficiency. Moreover, MergeSFL explores to jointly optimize these two strategies upon their coupled relationship to better enhance the performance of SFL. Extensive experiments are conducted on a physical platform with 80 NVIDIA Jetson edge devices, and the experimental results show that MergeSFL can improve the final model accuracy by 5.82% to 26.22%, with a speedup by about 1.74x to 4.14x, compared to the baselines.

cs.LG↗

arXiv2022

Adaptive Configuration for Heterogeneous Participants in Decentralized Federated Learning

Data generated at the network edge can be processed locally by leveraging the paradigm of edge computing (EC). Aided by EC, decentralized federated learning (DFL), which overcomes the single-point-of-failure problem in the parameter server (PS) based federated learning, is becoming a practical and popular approach for machine learning over distributed data. However, DFL faces two critical challenges, \ie, system heterogeneity and statistical heterogeneity introduced by edge devices. To ensure fast convergence with the existence of slow edge devices, we present an efficient DFL method, termed FedHP, which integrates adaptive control of both local updating frequency and network topology to better support the heterogeneous participants. We establish a theoretical relationship between local updating frequency and network topology regarding model training performance and obtain a convergence upper bound. Upon this, we propose an optimization algorithm, that adaptively determines local updating frequencies and constructs the network topology, so as to speed up convergence and improve the model accuracy. Evaluation results show that the proposed FedHP can reduce the completion time by about 51% and improve model accuracy by at least 5% in heterogeneous scenarios, compared with the baselines.

cs.NI↗