Mingyi Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mingyi Li has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Dongxiao Yu
Shandong University
4 shared publications - Xiao Zhang
Shandong University
4 shared publications - Yuan Yuan
Shandong University
3 shared publications - Fuzhen Zhuang
School of Artificial Intelligence, Beihang University, Beijing, China
2 shared publications Dongxiao Yu
1 shared publication- Feng Chen
School of Computer Science and Technology, Shandong University, Qingdao, China
1 shared publication
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2674-2685
DeMIC: Decentralized Meta In-Context Learning with Refiner-Guided Adaptation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 2674-2685
Open AccessDeMIC: Decentralized Meta In-Context Learning with Refiner-Guided Adaptation
- 29 July 2026
- Published by Elsevier in Journal of Systems Architecture
- Vol. 179
Resource-aware collaborative learning with improved generalization on edge devices
- 29 July 2026
- Published by Elsevier in Journal of Systems Architecture
- Vol. 179
Resource-aware collaborative learning with improved generalization on edge devices
- 5 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (6) , 4221-4233
TAMO:Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent With Multi-Modality Observation Data in Cloud-Native Systems
Implementing large language models (LLMs)-driven root cause analysis (RCA) in cloud-native systems has become a key topic of modern software operations and maintenance. However, existing LLM-based approaches face three key challenges: multi-modality input constraint, context window limitation, and dynamic dependence graph. To address these issues, we propose a tool-assisted LLM agent with multi-modality observation data for fine-grained RCA, namely TAMO, including multi-modality alignment tool, root cause localization tool, and fault types classification tool. In detail, TAMO unifies multi-modal observation data into time-aligned representations for cross-modal feature consistency. Based on the unified representations, TAMO then invokes its specialized root cause localization tool and fault types classification tool for further identifying root cause and fault type underlying system context. This approach overcomes the limitations of LLMs in processing real-time raw observational data and dynamic service dependencies, guiding the model to generate repair strategies that align with system context through structured prompt design. Experiments on two benchmark datasets demonstrate that TAMO outperforms state-of-the-art (SOTA) approaches with comparable performance.
- 5 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Services Computing
- Vol. 18 (6) , 4221-4233
TAMO:Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent With Multi-Modality Observation Data in Cloud-Native Systems
Implementing large language models (LLMs)-driven root cause analysis (RCA) in cloud-native systems has become a key topic of modern software operations and maintenance. However, existing LLM-based approaches face three key challenges: multi-modality input constraint, context window limitation, and dynamic dependence graph. To address these issues, we propose a tool-assisted LLM agent with multi-modality observation data for fine-grained RCA, namely TAMO, including multi-modality alignment tool, root cause localization tool, and fault types classification tool. In detail, TAMO unifies multi-modal observation data into time-aligned representations for cross-modal feature consistency. Based on the unified representations, TAMO then invokes its specialized root cause localization tool and fault types classification tool for further identifying root cause and fault type underlying system context. This approach overcomes the limitations of LLMs in processing real-time raw observational data and dynamic service dependencies, guiding the model to generate repair strategies that align with system context through structured prompt design. Experiments on two benchmark datasets demonstrate that TAMO outperforms state-of-the-art (SOTA) approaches with comparable performance.
- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (3) , 3051-3067
Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models With Structured Pruning in Resource-Limited Clients
In this work, we study to release the potential of massive heterogeneous weak computing power to collaboratively train large-scale models on dispersed datasets. In order to improve both efficiency and accuracy in resource-adaptive collaborative learning, we take the first step to consider the unstructured pruning, varying submodel architectures, knowledge loss, and straggler challenges simultaneously. We propose a novel semi-asynchronous collaborative training framework, namely${Co\text{-}S}^{2}{P}$ , with data distribution-aware structured pruning and cross-block knowledge transfer mechanism to address the above concerns. Furthermore, we provide theoretical proof that${Co\text{-}S}^{2}{P}$ can achieve asymptotic optimal convergence rate of$O(1/\sqrt{N^{*}EQ})$ . Finally, we conduct extensive experiments on two types of tasks with a real-world hardware testbed including diverse IoT devices. The experimental results demonstrate that$Co\text{-}S^{2}P$ improves accuracy by up to 8.8% and resource utilization by up to 1.2× compared to state-of-the-art methods, while reducing memory consumption by approximately 22% and training time by about 24% on all resource-limited devices.- 22 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 25 (3) , 3051-3067
Unity is Power: Semi-Asynchronous Collaborative Training of Large-Scale Models With Structured Pruning in Resource-Limited Clients
In this work, we study to release the potential of massive heterogeneous weak computing power to collaboratively train large-scale models on dispersed datasets. In order to improve both efficiency and accuracy in resource-adaptive collaborative learning, we take the first step to consider the unstructured pruning, varying submodel architectures, knowledge loss, and straggler challenges simultaneously. We propose a novel semi-asynchronous collaborative training framework, namely${Co\text{-}S}^{2}{P}$ , with data distribution-aware structured pruning and cross-block knowledge transfer mechanism to address the above concerns. Furthermore, we provide theoretical proof that${Co\text{-}S}^{2}{P}$ can achieve asymptotic optimal convergence rate of$O(1/\sqrt{N^{*}EQ})$ . Finally, we conduct extensive experiments on two types of tasks with a real-world hardware testbed including diverse IoT devices. The experimental results demonstrate that$Co\text{-}S^{2}P$ improves accuracy by up to 8.8% and resource utilization by up to 1.2× compared to state-of-the-art methods, while reducing memory consumption by approximately 22% and training time by about 24% on all resource-limited devices.- Open Access
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2444-2455
Theoretical Convergence Guaranteed Resource-Adaptive Federated Learning with Mixed Heterogeneity
In this paper, we propose an adaptive learning paradigm for resource-constrained cross-device federated learning, in which heterogeneous local submodels with varying resources can be jointly trained to produce a global model. Different from existing studies, the submodel structures of different clients are formed by arbitrarily assigned neurons according to their local resources. Along this line, we first design a general resource-adaptive federated learning algorithm, namely RA-Fed, and rigorously prove its convergence with asymptotically optimal rate O(1/√Γ*TQ) under loose assumptions. Furthermore, to address both submodels heterogeneity and data heterogeneity challenges under non-uniform training, we come up with a new server aggregation mechanism RAM-Fed with the same theoretically proved convergence rate. Moreover, we shed light on several key factors impacting convergence, such as minimum coverage rate, data heterogeneity level, submodel induced noises. Finally, we conduct extensive experiments on two types of tasks with three widely used datasets under different experimental settings. Compared with the state-of-the-arts, our methods improve the accuracy up to 10% on average. Particularly, when submodels jointly train with 50% parameters, RAM-Fed achieves comparable accuracy to FedAvg trained with the full model.
- 4 August 2023
- Published by Association for Computing Machinery (ACM)
- p. 2444-2455
Open AccessTheoretical Convergence Guaranteed Resource-Adaptive Federated Learning with Mixed Heterogeneity
In this paper, we propose an adaptive learning paradigm for resource-constrained cross-device federated learning, in which heterogeneous local submodels with varying resources can be jointly trained to produce a global model. Different from existing studies, the submodel structures of different clients are formed by arbitrarily assigned neurons according to their local resources. Along this line, we first design a general resource-adaptive federated learning algorithm, namely RA-Fed, and rigorously prove its convergence with asymptotically optimal rate O(1/√Γ*TQ) under loose assumptions. Furthermore, to address both submodels heterogeneity and data heterogeneity challenges under non-uniform training, we come up with a new server aggregation mechanism RAM-Fed with the same theoretically proved convergence rate. Moreover, we shed light on several key factors impacting convergence, such as minimum coverage rate, data heterogeneity level, submodel induced noises. Finally, we conduct extensive experiments on two types of tasks with three widely used datasets under different experimental settings. Compared with the state-of-the-arts, our methods improve the accuracy up to 10% on average. Particularly, when submodels jointly train with 50% parameters, RAM-Fed achieves comparable accuracy to FedAvg trained with the full model.