arXiv subjects

Bing Luo

Publications and source records attributed to Bing Luo.

At least 37 records · Page 2Linked to original sources

arXiv2025

Cognitive Insights and Stable Coalition Matching for Fostering Multi-Agent Cooperation

Cognitive abilities, such as Theory of Mind (ToM), play a vital role in facilitating cooperation in human social interactions. However, our study reveals that agents with higher ToM abilities may not necessarily exhibit better cooperative behavior compared to those with lower ToM abilities. To address this challenge, we propose a novel matching coalition mechanism that leverages the strengths of agents with different ToM levels by explicitly considering belief alignment and specialized abilities when forming coalitions. Our proposed matching algorithm seeks to find stable coalitions that maximize the potential for cooperative behavior and ensure long-term viability. By incorporating cognitive insights into the design of multi-agent systems, our work demonstrates the potential of leveraging ToM to create more sophisticated and human-like coordination strategies that foster cooperation and improve overall system performance.

cs.MA↗

arXiv2025

Strategic Prompt Pricing for AIGC Services: A User-Centric Approach

The rapid growth of AI-generated content (AIGC) services has created an urgent need for effective prompt pricing strategies, yet current approaches overlook users' strategic two-step decision-making process in selecting and utilizing generative AI models. This oversight creates two key technical challenges: quantifying the relationship between user prompt capabilities and generation outcomes, and optimizing platform payoff while accounting for heterogeneous user behaviors. We address these challenges by introducing prompt ambiguity, a theoretical framework that captures users' varying abilities in prompt engineering, and developing an Optimal Prompt Pricing (OPP) algorithm. Our analysis reveals a counterintuitive insight: users with higher prompt ambiguity (i.e., lower capability) exhibit non-monotonic prompt usage patterns, first increasing then decreasing with ambiguity levels, reflecting complex changes in marginal utility. Experimental evaluation using a character-level GPT-like model demonstrates that our OPP algorithm achieves up to 31.72% improvement in platform payoff compared to existing pricing mechanisms, validating the importance of user-centric prompt pricing in AIGC services.

cs.AI↗

arXiv2025

Autonomous Radiotherapy Treatment Planning Using DOLA: A Privacy-Preserving, LLM-Based Optimization Agent

Radiotherapy treatment planning is a complex and time-intensive process, often impacted by inter-planner variability and subjective decision-making. To address these challenges, we introduce Dose Optimization Language Agent (DOLA), an autonomous large language model (LLM)-based agent designed for optimizing radiotherapy treatment plans while rigorously protecting patient privacy. DOLA integrates the LLaMa3.1 LLM directly with a commercial treatment planning system, utilizing chain-of-thought prompting, retrieval-augmented generation (RAG), and reinforcement learning (RL). Operating entirely within secure local infrastructure, this agent eliminates external data sharing. We evaluated DOLA using a retrospective cohort of 18 prostate cancer patients prescribed 60 Gy in 20 fractions, comparing model sizes (8 billion vs. 70 billion parameters) and optimization strategies (No-RAG, RAG, and RAG+RL) over 10 planning iterations. The 70B model demonstrated significantly improved performance, achieving approximately 16.4% higher final scores than the 8B model. The RAG approach outperformed the No-RAG baseline by 19.8%, and incorporating RL accelerated convergence, highlighting the synergy of retrieval-based memory and reinforcement learning. Optimal temperature hyperparameter analysis identified 0.4 as providing the best balance between exploration and exploitation. This proof of concept study represents the first successful deployment of locally hosted LLM agents for autonomous optimization of treatment plans within a commercial radiotherapy planning system. By extending human-machine interaction through interpretable natural language reasoning, DOLA offers a scalable and privacy-conscious framework, with significant potential for clinical implementation and workflow improvement.

physics.med-ph↗

arXiv2025

Enhanced dynamo drive for the sawtooth relaxation process due to non-uniform resistivity distribution in a reversed field pinch

In this work, we use the three-dimensional resistive MHD code NIMROD to investigate the impact of resistivity inhomogeneity on the sawtooth process of an reversed field pinch (RFP) plasma. The simulation employs a non-uniform resistivity profile similar to experiments, which monotonically increases from the core to the edge as the temperature decreases. The resistivity inhomogeneity introduces an additional electric field in the plasma, which accelerates the inward diffusion of magnetic flux and changing the self sustained reversal state, hence significantly enhances the dynamo effect and the sawtooth process in the RFP plasma.

physics.plasm-ph↗

arXiv2025

Ten Challenging Problems in Federated Foundation Models

Federated Foundation Models (FedFMs) represent a distributed learning paradigm that fuses general competences of foundation models as well as privacy-preserving capabilities of federated learning. This combination allows the large foundation models and the small local domain models at the remote clients to learn from each other in a teacher-student learning setting. This paper provides a comprehensive summary of the ten challenging problems inherent in FedFMs, encompassing foundational theory, utilization of private data, continual learning, unlearning, Non-IID and graph data, bidirectional knowledge transfer, incentive mechanism design, game mechanism design, model watermarking, and efficiency. The ten challenging problems manifest in five pivotal aspects: ``Foundational Theory," which aims to establish a coherent and unifying theoretical framework for FedFMs. ``Data," addressing the difficulties in leveraging domain-specific knowledge from private data while maintaining privacy; ``Heterogeneity," examining variations in data, model, and computational resources across clients; ``Security and Privacy," focusing on defenses against malicious attacks and model theft; and ``Efficiency," highlighting the need for improvements in training, communication, and parameter efficiency. For each problem, we offer a clear mathematical definition on the objective function, analyze existing methods, and discuss the key challenges and potential solutions. This in-depth exploration aims to advance the theoretical foundations of FedFMs, guide practical implementations, and inspire future research to overcome these obstacles, thereby enabling the robust, efficient, and privacy-preserving FedFMs in various real-world applications.

cs.LG↗

arXiv2024

Fed-MUnet: Multi-modal Federated Unet for Brain Tumor Segmentation

Deep learning-based techniques have been widely utilized for brain tumor segmentation using both single and multi-modal Magnetic Resonance Imaging (MRI) images. Most current studies focus on centralized training due to the intrinsic challenge of data sharing across clinics. To mitigate privacy concerns, researchers have introduced Federated Learning (FL) methods to brain tumor segmentation tasks. However, currently such methods are focusing on single modal MRI, with limited study on multi-modal MRI. The challenges include complex structure, large-scale parameters, and overfitting issues of the FL based methods using multi-modal MRI. To address the above challenges, we propose a novel multi-modal FL framework for brain tumor segmentation (Fed-MUnet) that is suitable for FL training. We evaluate our approach with the BraTS2022 datasets, which are publicly available. The experimental results demonstrate that our framework achieves FL nature of distributed learning and privacy preserving. For the enhancing tumor, tumor core and whole tumor, the mean of five major metrics were 87.5%, 90.6% and 92.2%, respectively, which were higher than SOTA methods while preserving privacy. In terms of parameters count, quantity of floating-point operations (FLOPs) and inference, Fed-MUnet is Pareto optimal compared with the state-of-the-art segmentation backbone while achieves higher performance and tackles privacy issue. Our codes are open-sourced at https://github.com/Arnold-Jun/Fed-MUnet.

cs.CV↗

arXiv2024

Demo: FedCampus: A Real-world Privacy-preserving Mobile Application for Smart Campus via Federated Learning & Analytics

In this demo, we introduce FedCampus, a privacy-preserving mobile application for smart \underline{campus} with \underline{fed}erated learning (FL) and federated analytics (FA). FedCampus enables cross-platform on-device FL/FA for both iOS and Android, supporting continuously models and algorithms deployment (MLOps). Our app integrates privacy-preserving processed data via differential privacy (DP) from smartwatches, where the processed parameters are used for FL/FA through the FedCampus backend platform. We distributed 100 smartwatches to volunteers at Duke Kunshan University and have successfully completed a series of smart campus tasks featuring capabilities such as sleep tracking, physical activity monitoring, personalized recommendations, and heavy hitters. Our project is opensourced at https://github.com/FedCampus/FedCampus_Flutter. See the FedCampus video at https://youtu.be/k5iu46IjA38.

cs.CR↗

arXiv2024

Formation of quasi-single helicity state from a paramagnetic pinch in KTX regime

The formation of quasi-single helicity (QSH) state from a paramagnetic pinch in the KTX-RFP regime has been observed in recent NIMROD simulations. The quasi-single helicity state has a dominant helical component of the magnetic field that is known to improve the RFP confinement. For the initial paramagnetic pinch, linear calculations indicate that the tearing mode growth rate decreases with the plasma $β$. The initial QSH state arises from the dominant linear instability of the initial force-free paramagnetic pinch. The plasma's self-organization towards the second QSH state after the relaxation of the initial QSH state is found to depend on $β$. Specifically, when $β<4\%$, the plasma relaxes to an MH state; when $4\% \leq β\leq 8\%$, the plasma first transitions from a double axis (DAx) to a single helical axis (SHAx) state, and eventually return to the DAx state. The existence of such an optimal $β$ regime that is beneficial to the formation and maintenance of the QSH state, suggests an experimental scheme for the QSH formation based on $β$ tuning and control.

physics.plasm-ph↗

arXiv2024

Social Welfare Maximization for Federated Learning with Network Effects

A proper mechanism design can help federated learning (FL) to achieve good social welfare by coordinating self-interested clients through the learning process. However, existing mechanisms neglect the network effects of client participation, leading to suboptimal incentives and social welfare. This paper addresses this gap by exploring network effects in FL incentive mechanism design. We establish a theoretical model to analyze FL model performance and quantify the impact of network effects on heterogeneous client participation. Our analysis reveals the non-monotonic nature of FL network effects. To leverage such effects, we propose a model trading and sharing (MTS) framework that allows clients to obtain FL models through participation or purchase. To tackle heterogeneous clients' strategic behaviors, we further design a socially efficient model trading and sharing (SEMTS) mechanism. Our mechanism achieves social welfare maximization solely through customer payments, without additional incentive costs. Experimental results on an FL hardware prototype demonstrate up to 148.86% improvement in social welfare compared to existing mechanisms.

cs.GT↗

arXiv2024

Hybrid Student-Teacher Large Language Model Refinement for Cancer Toxicity Symptom Extraction

Large Language Models (LLMs) offer significant potential for clinical symptom extraction, but their deployment in healthcare settings is constrained by privacy concerns, computational limitations, and operational costs. This study investigates the optimization of compact LLMs for cancer toxicity symptom extraction using a novel iterative refinement approach. We employ a student-teacher architecture, utilizing Zephyr-7b-beta and Phi3-mini-128 as student models and GPT-4o as the teacher, to dynamically select between prompt refinement, Retrieval-Augmented Generation (RAG), and fine-tuning strategies. Our experiments on 294 clinical notes covering 12 post-radiotherapy toxicity symptoms demonstrate the effectiveness of this approach. The RAG method proved most efficient, improving average accuracy scores from 0.32 to 0.73 for Zephyr-7b-beta and from 0.40 to 0.87 for Phi3-mini-128 during refinement. In the test set, both models showed an approximate 0.20 increase in accuracy across symptoms. Notably, this improvement was achieved at a cost 45 times lower than GPT-4o for Zephyr and 79 times lower for Phi-3. These results highlight the potential of iterative refinement techniques in enhancing the capabilities of compact LLMs for clinical applications, offering a balance between performance, cost-effectiveness, and privacy preservation in healthcare settings.

cs.CL↗

arXiv2024

Federated Unlearning: a Perspective of Stability and Fairness

This paper explores the multifaceted consequences of federated unlearning (FU) with data heterogeneity. We introduce key metrics for FU assessment, concentrating on verification, global stability, and local fairness, and investigate the inherent trade-offs. Furthermore, we formulate the unlearning process with data heterogeneity through an optimization framework. Our key contribution lies in a comprehensive theoretical analysis of the trade-offs in FU and provides insights into data heterogeneity's impacts on FU. Leveraging these insights, we propose FU mechanisms to manage the trade-offs, guiding further development for FU mechanisms. We empirically validate that our FU mechanisms effectively balance trade-offs, confirming insights derived from our theoretical analysis.

cs.AI↗

arXiv2024

Adaptive Federated Learning in Heterogeneous Wireless Networks with Independent Sampling

Federated Learning (FL) algorithms commonly sample a random subset of clients to address the straggler issue and improve communication efficiency. While recent works have proposed various client sampling methods, they have limitations in joint system and data heterogeneity design, which may not align with practical heterogeneous wireless networks. In this work, we advocate a new independent client sampling strategy to minimize the wall-clock training time of FL, while considering data heterogeneity and system heterogeneity in both communication and computation. We first derive a new convergence bound for non-convex loss functions with independent client sampling and then propose an adaptive bandwidth allocation scheme. Furthermore, we propose an efficient independent client sampling algorithm based on the upper bounds on the convergence rounds and the expected per-round training time, to minimize the wall-clock time of FL, while considering both the data and system heterogeneity. Experimental results under practical wireless network settings with real-world prototype demonstrate that the proposed independent sampling scheme substantially outperforms the current best sampling schemes under various training models and datasets.

cs.LG↗

arXiv2024

Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks

Federated learning (FL) algorithms usually sample a fraction of clients in each round (partial participation) when the number of participants is large and the server's communication bandwidth is limited. Recent works on the convergence analysis of FL have focused on unbiased client sampling, e.g., sampling uniformly at random, which suffers from slow wall-clock time for convergence due to high degrees of system heterogeneity and statistical heterogeneity. This paper aims to design an adaptive client sampling algorithm for FL over wireless networks that tackles both system and statistical heterogeneity to minimize the wall-clock convergence time. We obtain a new tractable convergence bound for FL algorithms with arbitrary client sampling probability. Based on the bound, we analytically establish the relationship between the total learning time and sampling probability with an adaptive bandwidth allocation scheme, which results in a non-convex optimization problem. We design an efficient algorithm for learning the unknown parameters in the convergence bound and develop a low-complexity algorithm to approximately solve the non-convex problem. Our solution reveals the impact of system and statistical heterogeneity parameters on the optimal client sampling design. Moreover, our solution shows that as the number of sampled clients increases, the total convergence time first decreases and then increases because a larger sampling number reduces the number of rounds for convergence but results in a longer expected time per-round due to limited wireless bandwidth. Experimental results from both hardware prototype and simulation demonstrate that our proposed sampling scheme significantly reduces the convergence time compared to several baseline sampling schemes.

cs.DC↗

arXiv2024

Privacy-Preserving Federated Heavy Hitter Analytics for Non-IID Data

Federated heavy-hitter analytics involves the identification of the most frequent items within distributed data. Existing methods for this task often encounter challenges such as compromising privacy or sacrificing utility. To address these issues, we introduce a novel privacy-preserving algorithm that exploits the hierarchical structure to discover local and global heavy hitters in non-IID data by utilizing perturbation and similarity techniques. We conduct extensive evaluations on both synthetic and real datasets to validate the effectiveness of our approach. We also present FedCampus, a demonstration application to showcase the capabilities of our algorithm in analyzing population statistics.

cs.DC↗

arXiv2024

FedKit: Enabling Cross-Platform Federated Learning for Android and iOS

We present FedKit, a federated learning (FL) system tailored for cross-platform FL research on Android and iOS devices. FedKit pipelines cross-platform FL development by enabling model conversion, hardware-accelerated training, and cross-platform model aggregation. Our FL workflow supports flexible machine learning operations (MLOps) in production, facilitating continuous model delivery and training. We have deployed FedKit in a real-world use case for health data analysis on university campuses, demonstrating its effectiveness. FedKit is open-source at https://github.com/FedCampus/FedKit.

cs.LG↗

arXiv2023

Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation

Incentive mechanism is crucial for federated learning (FL) when rational clients do not have the same interests in the global model as the server. However, due to system heterogeneity and limited budget, it is generally impractical for the server to incentivize all clients to participate in all training rounds (known as full participation). The existing FL incentive mechanisms are typically designed by stimulating a fixed subset of clients based on their data quantity or system resources. Hence, FL is performed only using this subset of clients throughout the entire training process, leading to a biased model because of data heterogeneity. This paper proposes a game theoretic incentive mechanism for FL with randomized client participation, where the server adopts a customized pricing strategy that motivates different clients to join with different participation levels (probabilities) for obtaining an unbiased and high performance model. Each client responds to the server's monetary incentive by choosing its best participation level, to maximize its profit based on not only the incurred local cost but also its intrinsic value for the global model. To effectively evaluate clients' contribution to the model performance, we derive a new convergence bound which analytically predicts how clients' arbitrary participation levels and their heterogeneous data affect the model performance. By solving a non-convex optimization problem, our analysis reveals that the intrinsic value leads to the interesting possibility of bidirectional payment between the server and clients. Experimental results using real datasets on a hardware prototype demonstrate the superiority of our mechanism in achieving higher model performance for the server as well as higher profits for the clients.

cs.GT↗

arXiv2023

Selective thermal evolution of native oxide layer in Nb and Nb3Sn-coated SRF grade Nb: An in-situ angular XPS study

This contribution discusses the results of an in-situ angular XPS study on the thermal evolution of the native oxide layer on Nb3Sn and pure Nb. XPS data were recorded with conventional spectrometers using an AlK(alpha) X-ray source for spectra collected up to 600 C, and an MgK(Alpha) X-rays source for temperatures above 600 C. The effect of the thickness, composition, and thermal stability of that oxide layer is relevant to understanding the functional properties of superconducting radiofrequency (SRF) cavities used in particle accelerators. There is a consensus that oxide plays a role in surface resistance (Rs). The focus of this study is Nb3Sn, which is a promising material that is used in the manufacturing of superconducting radiofrequency (SRF) cavities as well as in quantum sensing, and pure Nb, which was included in the study for comparison. The thermal evolution of the oxide layer in these two materials is found to be quite different, which is ascribed to the influence of the Sn atom on the reactivity of the Nb atom in Nb3Sn films. Nb and Sn atoms in this intermetallic solid have different electronegativity, and the Sn atom can reduce electron density around neighbouring Nb atoms in the solid, thus reducing their reactivity for oxygen. This is shown in the thickness, composition, and thermal stability of the oxide layer formed on Nb3Sn. The XPS spectra were complemented by grazing incident XRD patterns collected using the ESRF synchrotron radiation facility. The results discussed herein shed light on oxide evolution in the Nb3Sn compound and guide its processing for potential applications of the Nb3Sn-based SRF cavities in accelerators and other superconducting devices.

cond-mat.mtrl-sci↗

arXiv2023

Optimization Design for Federated Learning in Heterogeneous 6G Networks

With the rapid advancement of 5G networks, billions of smart Internet of Things (IoT) devices along with an enormous amount of data are generated at the network edge. While still at an early age, it is expected that the evolving 6G network will adopt advanced artificial intelligence (AI) technologies to collect, transmit, and learn this valuable data for innovative applications and intelligent services. However, traditional machine learning (ML) approaches require centralizing the training data in the data center or cloud, raising serious user-privacy concerns. Federated learning, as an emerging distributed AI paradigm with privacy-preserving nature, is anticipated to be a key enabler for achieving ubiquitous AI in 6G networks. However, there are several system and statistical heterogeneity challenges for effective and efficient FL implementation in 6G networks. In this article, we investigate the optimization approaches that can effectively address the challenging heterogeneity issues from three aspects: incentive mechanism design, network resource management, and personalized model optimization. We also present some open problems and promising directions for future research.

cs.LG↗