arXiv subjects

Xu Chen

Publications and source records attributed to Xu Chen.

At least 289 records · Page 16Linked to original sources

arXiv2023

Device-Edge Cooperative Fine-Tuning of Foundation Models as a 6G Service

Foundation models (FoMos), referring to large-scale AI models, possess human-like capabilities and are able to perform competitively in the domain of human intelligence. The breakthrough in FoMos has inspired researchers to deploy such models in the sixth-generation (6G) mobile networks for automating a broad range of tasks in next-generation mobile applications. While the sizes of FoMos are reaching their peaks, their next phase is expected to focus on fine-tuning the models to specific downstream tasks. This inspires us to propose the vision of FoMo fine-tuning as a 6G service. Its key feature is the exploitation of existing parameter-efficient fine-tuning (PEFT) techniques to tweak only a small fraction of model weights for a FoMo to become customized for a specific task. To materialize the said vision, we survey the state-of-the-art PEFT and then present a novel device-edge fine-tuning (DEFT) framework for providing efficient and privacy-preserving fine-tuning services at the 6G network edge. The framework consists of the following comprehensive set of techniques: 1) Control of fine-tuning parameter sizes in different transformer blocks of a FoMo; 2) Over-the-air computation for realizing neural connections in DEFT; 3) Federated DEFT in a multi-device system by downloading a FoMo emulator or gradients; 4) On-the-fly prompt-ensemble tuning; 5) Device-to-device prompt transfer among devices. Experiments are conducted using pre-trained FoMos with up to 11 billion parameters to demonstrate the effectiveness of DEFT techniques. The article is concluded by presenting future research opportunities.

cs.NI↗

arXiv2023

Joint Localization and Communication Enhancement in Uplink Integrated Sensing and Communications System with Clock Asynchronism

In this paper, we propose a joint single-base localization and communication enhancement scheme for the uplink (UL) integrated sensing and communications (ISAC) system with asynchronism, which can achieve accurate single-base localization of user equipment (UE) and significantly improve the communication reliability despite the existence of timing offset (TO) due to the clock asynchronism between UE and base station (BS). Our proposed scheme integrates the CSI enhancement into the multiple signal classification (MUSIC)-based AoA estimation and thus imposes no extra complexity on the ISAC system. We further exploit a MUSIC-based range estimation method and prove that it can suppress the time-varying TO-related phase terms. Exploiting the AoA and range estimation of UE, we can estimate the location of UE. Finally, we propose a joint CSI and data signals-based localization scheme that can coherently exploit the data and the CSI signals to improve the AoA and range estimation, which further enhances the single-base localization of UE. The extensive simulation results show that the enhanced CSI can achieve equivalent bit error rate performance to the minimum mean square error (MMSE) CSI estimator. The proposed joint CSI and data signals-based localization scheme can achieve decimeter-level localization accuracy despite the existing clock asynchronism and improve the localization mean square error (MSE) by about 8 dB compared with the maximum likelihood (ML)-based benchmark method.

cs.IT↗

arXiv2023

DYNAMITE: Dynamic Interplay of Mini-Batch Size and Aggregation Frequency for Federated Learning with Static and Streaming Dataset

Federated Learning (FL) is a distributed learning paradigm that can coordinate heterogeneous edge devices to perform model training without sharing private data. While prior works have focused on analyzing FL convergence with respect to hyperparameters like batch size and aggregation frequency, the joint effects of adjusting these parameters on model performance, training time, and resource consumption have been overlooked, especially when facing dynamic data streams and network characteristics. This paper introduces novel analytical models and optimization algorithms that leverage the interplay between batch size and aggregation frequency to navigate the trade-offs among convergence, cost, and completion time for dynamic FL training. We establish a new convergence bound for training error considering heterogeneous datasets across devices and derive closed-form solutions for co-optimized batch size and aggregation frequency that are consistent across all devices. Additionally, we design an efficient algorithm for assigning different batch configurations across devices, improving model accuracy and addressing the heterogeneity of both data and system characteristics. Further, we propose an adaptive control algorithm that dynamically estimates network states, efficiently samples appropriate data batches, and effectively adjusts batch sizes and aggregation frequency on the fly. Extensive experiments demonstrate the superiority of our offline optimal solutions and online adaptive algorithm.

cs.LG↗

arXiv2023

TRANSOM: An Efficient Fault-Tolerant System for Training LLMs

Large language models (LLMs) with hundreds of billions or trillions of parameters, represented by chatGPT, have achieved profound impact on various fields. However, training LLMs with super-large-scale parameters requires large high-performance GPU clusters and long training periods lasting for months. Due to the inevitable hardware and software failures in large-scale clusters, maintaining uninterrupted and long-duration training is extremely challenging. As a result, A substantial amount of training time is devoted to task checkpoint saving and loading, task rescheduling and restart, and task manual anomaly checks, which greatly harms the overall training efficiency. To address these issues, we propose TRANSOM, a novel fault-tolerant LLM training system. In this work, we design three key subsystems: the training pipeline automatic fault tolerance and recovery mechanism named Transom Operator and Launcher (TOL), the training task multi-dimensional metric automatic anomaly detection system named Transom Eagle Eye (TEE), and the training checkpoint asynchronous access automatic fault tolerance and recovery technology named Transom Checkpoint Engine (TCE). Here, TOL manages the lifecycle of training tasks, while TEE is responsible for task monitoring and anomaly reporting. TEE detects training anomalies and reports them to TOL, who automatically enters the fault tolerance strategy to eliminate abnormal nodes and restart the training task. And the asynchronous checkpoint saving and loading functionality provided by TCE greatly shorten the fault tolerance overhead. The experimental results indicate that TRANSOM significantly enhances the efficiency of large-scale LLM training on clusters. Specifically, the pre-training time for GPT3-175B has been reduced by 28%, while checkpoint saving and loading performance have improved by a factor of 20.

cs.DC↗

arXiv2023

Fine-Grained Annotation for Face Anti-Spoofing

Face anti-spoofing plays a critical role in safeguarding facial recognition systems against presentation attacks. While existing deep learning methods show promising results, they still suffer from the lack of fine-grained annotations, which lead models to learn task-irrelevant or unfaithful features. In this paper, we propose a fine-grained annotation method for face anti-spoofing. Specifically, we first leverage the Segment Anything Model (SAM) to obtain pixel-wise segmentation masks by utilizing face landmarks as point prompts. The face landmarks provide segmentation semantics, which segments the face into regions. We then adopt these regions as masks and assemble them into three separate annotation maps: spoof, living, and background maps. Finally, we combine three separate maps into a three-channel map as annotations for model training. Furthermore, we introduce the Multi-Channel Region Exchange Augmentation (MCREA) to diversify training data and reduce overfitting. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches in both intra-dataset and cross-dataset evaluations.

cs.CV↗

arXiv2023

Integrated Sensing and Communication enabled Sensing Base Station: System Design, Beamforming, Interference Cancellation and Performance Analysis

This paper studies the sensing base station (SBS) that has great potential to improve the safety of vehicles and pedestrians on roads. It can detect the targets on the road with communication signals using the integrated sensing and communication (ISAC) technique. Compared with vehicle-mounted radar, SBS has a better sensing field due to its higher deployment position, which can help solve the problem of sensing blind areas. In this paper, key technologies of SBS are studied, including the beamforming algorithm, beam scanning scheme, and interference cancellation algorithm. To transmit and receive ISAC signals simultaneously, a double-coupling antenna array is applied. The free detection beam and directional communication beam are proposed for joint communication and sensing to meet the requirements of beamwidth and pointing directions. The joint time-space-frequency domain division multiple access algorithm is proposed to cancel the interference of SBS, including multiuser interference and duplex interference between sensing and communication. Finally, the sensing and communication performance of SBS under the industrial scientific medical power limitation is analyzed and simulated. Simulation results show that the communication rate of SBS can reach over 100 Mbps and the range of sensing and communication can reach about 500 m.

math.NA↗

arXiv2023

Integrated Sensing and Communication Neighbor Discovery for MANET with Gossip Mechanism

Mobile Ad hoc Network (MANET), supporting Machine-Type Communication(MTC), has a strong demand for rapid networking. Neighbor Discovery (ND) is a key initial step in configuring MANETs and faces a serious challenge in decreasing convergence time. Integrated Sensing and Communication (ISAC), as one of the potential key technologies in the 6th Generation (6G) mobile networks, can obtain the sensing data as the priori information to accelerate ND convergence. In order to further reduce the convergence time of ND, this paper introduces the ISAC-enabled gossip mechanism into the ND algorithm. The prior information acquired by ISAC reduces the information redundancy brought by the gossip mechanism and thus decreases the probability of collision, which further improves convergence speed. The average number of discovered nodes within a given period is derived, which is applied as the critical metric to evaluate the performance of ND algorithms. The simulation results confirm the correctness of the theoretical derivation and show that the interplay between the prior mechanisms and the gossip mechanism significantly reduces the convergence time. In addition, to solve the problem of imperfect sensing information, reinforcement learning is applied. Under the constraints of the convergence condition, the non-Reply and non-Stop Algorithm based on Gossip and Q-learning (GQ-nRnS) proposed in this paper not only ensures the completeness of ND, but also maintains a high convergence speed of ND. Compared with the Q-learning-based ND algorithm (Q-ND), the average convergence time of the GQ-nRnS algorithm is reduced by about 66.4%.

eess.SY↗

arXiv2023

Integrated Communication, Sensing, and Computation Framework for 6G Networks

In the sixth generation (6G) era, intelligent machine network (IMN) applications, such as intelligent transportation, require collaborative machines with communication, sensing, and computation (CSC) capabilities. This article proposes an integrated communication, sensing, and computation (ICSAC) framework for 6G to achieve the reciprocity among CSC functions to enhance the reliability and latency of communication, accuracy and timeliness of sensing information acquisition, and privacy and security of computing to realize the IMN applications. Specifically, the sensing and communication functions can merge into unified platforms using the same transmit signals, and the acquired real-time sensing information can be exploited as prior information for intelligent algorithms to enhance the performance of communication networks. This is called the computing-empowered integrated sensing and communications (ISAC) reciprocity. Such reciprocity can further improve the performance of distributed computation with the assistance of networked sensing capability, which is named the sensing-empowered integrated communications and computation (ICAC) reciprocity. The above ISAC and ICAC reciprocities can enhance each other iteratively and finally lead to the ICSAC reciprocity. To achieve these reciprocities, we explore the potential enabling technologies for the ICSAC framework. Finally, we present the evaluation results of crucial enabling technologies to show the feasibility of the ICSAC framework.

cs.NI↗

arXiv2023

Superconducting Properties of La$_2$(Cu$_{1-x}$Ni_x)$_5$As$_3$O$_2$: A $\rm μ$SR Study

We report the results of muon spin rotation and relaxation ($\rm μ$SR) measurements on the recently discovered layered Cu-based superconducting material La$_{2}($Cu$_{1-x}$Ni$_{x}$)$_{5}$As$_{3}$O$_{2}$ ($x =$ 0.40, 0.45). Transverse-field $\rm μ$SR experiments on both samples show that the temperature dependence of superfluid density is best described by a two-band model. The absolute values of zero-temperature magnetic penetration depth $λ_{\rm ab}(0)$ were found to be 427(1.7) nm and 422(1.5) nm for $x =$ 0.40 and 0.45, respectively. Both compounds are located between the unconventional and the standard BCS superconductors in the Uemura plot. No evidence of time-reversal symmetry (TRS) breaking in the superconducting state is suggested by zero-field $\rm μ$SR measurements.

cond-mat.supr-con↗

arXiv2023

Text-to-Image Generation for Abstract Concepts

Recent years have witnessed the substantial progress of large-scale models across various domains, such as natural language processing and computer vision, facilitating the expression of concrete concepts. Unlike concrete concepts that are usually directly associated with physical objects, expressing abstract concepts through natural language requires considerable effort, which results from their intricate semantics and connotations. An alternative approach is to leverage images to convey rich visual information as a supplement. Nevertheless, existing Text-to-Image (T2I) models are primarily trained on concrete physical objects and tend to fail to visualize abstract concepts. Inspired by the three-layer artwork theory that identifies critical factors, intent, object and form during artistic creation, we propose a framework of Text-to-Image generation for Abstract Concepts (TIAC). The abstract concept is clarified into a clear intent with a detailed definition to avoid ambiguity. LLMs then transform it into semantic-related physical objects, and the concept-dependent form is retrieved from an LLM-extracted form pattern set. Information from these three aspects will be integrated to generate prompts for T2I models via LLM. Evaluation results from human assessments and our newly designed metric concept score demonstrate the effectiveness of our framework in creating images that can sufficiently express abstract concepts.

cs.CV↗

arXiv2023

Chained-DP: Can We Recycle Privacy Budget?

Privacy-preserving vector mean estimation is a crucial primitive in federated analytics. Existing practices usually resort to Local Differentiated Privacy (LDP) mechanisms that inject random noise into users' vectors when communicating with users and the central server. Due to the privacy-utility trade-off, the privacy budget has been widely recognized as the bottleneck resource that requires well-provisioning. In this paper, we explore the possibility of privacy budget recycling and propose a novel Chained-DP framework enabling users to carry out data aggregation sequentially to recycle the privacy budget. We establish a sequential game to model the user interactions in our framework. We theoretically show the mathematical nature of the sequential game, solve its Nash Equilibrium, and design an incentive mechanism with provable economic properties. We further derive a differentially privacy-guaranteed protocol to alleviate potential privacy collusion attacks to avoid holistic exposure. Our numerical simulation validates the effectiveness of Chained-DP, showing that it can significantly save privacy budget and lower estimation error compared to the traditional LDP mechanism.

cs.CR↗

arXiv2023

A small scale structure model of jet based on the observation of microvariability

We developed a multi-region radiation model for the evolution of flux and spectral index with time. In this model, each perturbation component in the jet produces an independent flare. The model can be used to study the decomposition of microvariability, the structural scale of the perturbed components, and the physical parameters of the acceleration processes. Based on the shock acceleration model in relativistic jet, the influence of acceleration parameters on multiband flare parameters is calculated. We present the results of multiband optical microvariability of the blazar BL Lacertae observed performed during 89 nights in the period from 2009 to 2021, and use them as a sample for model fitting. The results show that both the amplitude and duration of flares decomposed from the microvariability light curves confirm a lognormal distribution. The time delays between the optical bands follow the normal distribution and amount to several minutes, that corroborates with both predictions from the theoretical model and the calculation of the discrete correlation function (DCF). Using the spectral index evolution and the simultaneous fitting of the multiband variability curves, we obtain the acceleration and radiation parameters to constrain and distinguish the origins of different flares. Based on the flare decomposition, we can well reproduce the time-domain evolution trends of the optical variation and energy spectrum, and explain the various redder-when-brighter (RWB) and/or bluer-when-brighter (BWB) behavior.

astro-ph.HE↗

arXiv2023

Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption

Training a generative model with limited number of samples is a challenging task. Current methods primarily rely on few-shot model adaption to train the network. However, in scenarios where data is extremely limited (less than 10), the generative network tends to overfit and suffers from content degradation. To address these problems, we propose a novel phasic content fusing few-shot diffusion model with directional distribution consistency loss, which targets different learning objectives at distinct training stages of the diffusion model. Specifically, we design a phasic training strategy with phasic content fusion to help our model learn content and style information when t is large, and learn local details of target domain when t is small, leading to an improvement in the capture of content, style and local details. Furthermore, we introduce a novel directional distribution consistency loss that ensures the consistency between the generated and source distributions more efficiently and stably than the prior methods, preventing our model from overfitting. Finally, we propose a cross-domain structure guidance strategy that enhances structure consistency during domain adaptation. Theoretical analysis, qualitative and quantitative experiments demonstrate the superiority of our approach in few-shot generative model adaption tasks compared to state-of-the-art methods. The source code is available at: https://github.com/sjtuplayer/few-shot-diffusion.

cs.CV↗

arXiv2023

Roulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks

Deep learning classifiers are crucial in the age of artificial intelligence. The device-edge-based collaborative inference has been widely adopted as an efficient framework for promoting its applications in IoT and 5G/6G networks. However, it suffers from accuracy degradation under non-i.i.d. data distribution and privacy disclosure. For accuracy degradation, direct use of transfer learning and split learning is high cost and privacy issues remain. For privacy disclosure, cryptography-based approaches lead to a huge overhead. Other lightweight methods assume that the ground truth is non-sensitive and can be exposed. But for many applications, the ground truth is the user's crucial privacy-sensitive information. In this paper, we propose a framework of Roulette, which is a task-oriented semantic privacy-preserving collaborative inference framework for deep learning classifiers. More than input data, we treat the ground truth of the data as private information. We develop a novel paradigm of split learning where the back-end DNN is frozen and the front-end DNN is retrained to be both a feature extractor and an encryptor. Moreover, we provide a differential privacy guarantee and analyze the hardness of ground truth inference attacks. To validate the proposed Roulette, we conduct extensive performance evaluations using realistic datasets, which demonstrate that Roulette can effectively defend against various attacks and meanwhile achieve good model accuracy. In a situation where the non-i.i.d. is very severe, Roulette improves the inference accuracy by 21\% averaged over benchmarks, while making the accuracy of discrimination attacks almost equivalent to random guessing.

cs.LG↗

arXiv2023

FedDD: Toward Communication-efficient Federated Learning with Differential Parameter Dropout

Federated Learning (FL) requires frequent exchange of model parameters, which leads to long communication delay, especially when the network environments of clients vary greatly. Moreover, the parameter server needs to wait for the slowest client (i.e., straggler, which may have the largest model size, lowest computing capability or worst network condition) to upload parameters, which may significantly degrade the communication efficiency. Commonly-used client selection methods such as partial client selection would lead to the waste of computing resources and weaken the generalization of the global model. To tackle this problem, along a different line, in this paper, we advocate the approach of model parameter dropout instead of client selection, and accordingly propose a novel framework of Federated learning scheme with Differential parameter Dropout (FedDD). FedDD consists of two key modules: dropout rate allocation and uploaded parameter selection, which will optimize the model parameter uploading ratios tailored to different clients' heterogeneous conditions and also select the proper set of important model parameters for uploading subject to clients' dropout rate constraints. Specifically, the dropout rate allocation is formulated as a convex optimization problem, taking system heterogeneity, data heterogeneity, and model heterogeneity among clients into consideration. The uploaded parameter selection strategy prioritizes on eliciting important parameters for uploading to speedup convergence. Furthermore, we theoretically analyze the convergence of the proposed FedDD scheme. Extensive performance evaluations demonstrate that the proposed FedDD scheme can achieve outstanding performances in both communication efficiency and model convergence, and also possesses a strong generalization capability to data of rare classes.

cs.LG↗

arXiv2023

BeeFlow: Behavior Tree-based Serverless Workflow Modeling and Scheduling for Resource-Constrained Edge Clusters

Serverless computing has gained popularity in edge computing due to its flexible features, including the pay-per-use pricing model, auto-scaling capabilities, and multi-tenancy support. Complex Serverless-based applications typically rely on Serverless workflows (also known as Serverless function orchestration) to express task execution logic, and numerous application- and system-level optimization techniques have been developed for Serverless workflow scheduling. However, there has been limited exploration of optimizing Serverless workflow scheduling in edge computing systems, particularly in high-density, resource-constrained environments such as system-on-chip clusters and single-board-computer clusters. In this work, we discover that existing Serverless workflow scheduling techniques typically assume models with limited expressiveness and cause significant resource contention. To address these issues, we propose modeling Serverless workflows using behavior trees, a novel and fundamentally different approach from existing directed-acyclic-graph- and state machine-based models. Behavior tree-based modeling allows for easy analysis without compromising workflow expressiveness. We further present observations derived from the inherent tree structure of behavior trees for contention-free function collections and awareness of exact and empirical concurrent function invocations. Based on these observations, we introduce BeeFlow, a behavior tree-based Serverless workflow system tailored for resource-constrained edge clusters. Experimental results demonstrate that BeeFlow achieves up to 3.2X speedup in a high-density, resource-constrained edge testbed and 2.5X speedup in a high-profile cloud testbed, compared with the state-of-the-art.

cs.DC↗

arXiv2023

Measurement of the Gamma-Ray Energy Spectrum beyond 100 TeV from the HESS J1843$-$033 Region

HESS J1843$-$033 is a very-high-energy gamma-ray source whose origin remains unidentified. This work presents, for the first time, the energy spectrum of gamma rays beyond $100\, {\rm TeV}$ from the HESS J1843$-$033 region using the data recorded by the Tibet air shower array and its underground muon detector array. A gamma-ray source with an extension of $0.34^{\circ} \pm 0.12^{\circ}$ is successfully detected above $25\, {\rm TeV}$ at $(α,\, δ) = (281.09^{\circ}\pm 0.10^{\circ},\, -3.76^{\circ}\pm 0.09^{\circ})$ near HESS J1843$-$033 with a statistical significance of $6.2\, σ$, and the source is named TASG J1844$-$038. The position of TASG J1844$-$038 is consistent with those of HESS J1843$-$033, eHWC J1842$-$035, and LHAASO J1843$-$0338. The measured gamma-ray energy spectrum in $25\, {\rm TeV} < E < 130\, {\rm TeV}$ is described with ${\rm d}N/{\rm d}E = (9.70\pm 1.89)\times 10^{-16} (E/40\, {\rm TeV})^{-3.26\pm 0.30}\, {\rm TeV}^{-1} {\rm cm}^{-2} {\rm s}^{-1}$, and the spectral fit to the combined spectra of HESS J1843$-$033, LHAASO J1843$-$0338, and TASG J1844$-$038 implies the existence of a cutoff at $49.5\pm 9.0\, {\rm TeV}$. Associations of TASG J1844-038 with SNR G28.6$-$0.1 and PSR J1844-0346 are also discussed in detail for the first time.

astro-ph.HE↗

arXiv2023

Observation of gamma rays up to 320 TeV from the middle-aged TeV pulsar wind nebula HESS J1849$-$000

Gamma rays from HESS J1849$-$000, a middle-aged TeV pulsar wind nebula (PWN), are observed by the Tibet air shower array and the muon detector array. The detection significance of gamma rays reaches $4.0\, σ$ and $4.4\, σ$ levels above 25 TeV and 100 TeV, respectively, in units of Gaussian standard deviation $σ$. The energy spectrum measured between $40\, {\rm TeV} < E < 320\, {\rm TeV}$ for the first time is described with a simple power-law function of ${\rm d}N/{\rm d}E = (2.86 \pm 1.44) \times 10^{-16}(E/40\, {\rm TeV})^{-2.24 \pm 0.41}\, {\rm TeV}^{-1}\, {\rm cm}^{-2}\, {\rm s}^{-1}$. The gamma-ray energy spectrum from the sub-TeV ($E < 1\, {\rm TeV}$) to sub-PeV ($100\, {\rm TeV} < E < 1\, {\rm PeV}$) ranges including the results of previous studies can be modeled with the leptonic scenario, inverse Compton scattering by high-energy electrons accelerated by the PWN of PSR J1849$-$0001. On the other hand, the gamma-ray energy spectrum can also be modeled with the hadronic scenario in which gamma rays are generated from the decay of neutral pions produced by collisions between accelerated cosmic-ray protons and the ambient molecular cloud found in the gamma-ray emitting region. The cutoff energy of cosmic-ray protons $E_{\rm p\, cut}$, cut is estimated at ${\rm log}_{10}(E_{\rm p,\, cut}/{\rm TeV}) = 3.73^{+2.98}_{-0.66}$, suggesting that protons are accelerated up to the PeV energy range. Our study thus proposes that HESS J1849$-$000 should be further investigated as a new candidate for a Galactic PeV cosmic-ray accelerator, PeVatron.

astro-ph.HE↗