Search

Dual quaternions and dual quaternion matrices have garnered widespread applications in robotic research, and its spectral theory has been extensively studied in recent years. This paper introduces the novel concept of the dual complex adjoint matrices for dual quaternion matrices. We delve into exploring the properties of this matrix, utilizing it to study eigenvalues of dual quaternion matrices and defining the concept of standard right eigenvalues. Notably, we leverage the properties of the dual complex adjoint matrix to devise a direct solution to the Hand-Eye calibration problem. Additionally, we apply this matrix to solve dual quaternion linear equations systems, thereby advancing the Rayleigh quotient iteration method for computing eigenvalues of dual quaternion Hermitian matrices, enhancing its computational efficiency. Numerical experiments have validated the correctness of our proposed method in solving the Hand-Eye calibration problem and demonstrated the effectiveness in improving the Rayleigh quotient iteration method, underscoring the promising potential of dual complex adjoint matrices in tackling dual quaternion-related challenges.

We present extensive observations and analysis of supernova (SN) 2021dbg, utilizing optical photometry and spectroscopy. For approximately 385 days following the explosion, SN 2021dbg exhibited remarkable luminosity, surpassing most SNe II. This initial high luminosity is potentially attributed to the interaction between the ejected material and the surrounding circumstellar material (CSM), as evidenced by the pronounced interaction signatures observed in its spectra. The subsequent high luminosity is primarily due to the significant $^{56}$Ni ($0.17 \pm 0.05$ M$_{\odot}$) produced in the explosion. Based on the flux of flash emission lines detected in the initial spectra, we estimate that the CSM mass near the progenitor amounted to $\sim$(1.0--2.0) $\times 10^{-3}$ M$_{\odot}$, likely resulting from intense stellar wind activity 2--3 yr preceding the explosion. Considering the bolometric light curve, nebular spectrum modeling, and mass-loss rate, we suggest that the progenitor of SN 2021dbg was a red supergiant (RSG) with a mass of $\sim 20$ M$_{\odot}$ and a radius of 1200 R$_{\odot}$. This RSG featured a thick hydrogen shell, which may have contained a region with a sharp decrease in material density, electron density, and temperature, contributing to its layered structure. This object demonstrates mixed features of SNe IIP and SNe IIL, making it as a transitional event linking the above two subclasses of SNe II.

As a kind of wavefront with helical phase, orbital angular momentum (OAM) shows the great potential to enhance the security results of wireless communications due to its unique orthogonality and central hollow electromagnetic wave structure. Therefore, in this paper we propose the reconfigurable-intelligent-surface (RIS) assisted OAM scheme, where RIS is deployed to weaken the information acquisition at eavesdroppers by adjusting the OAM beams pointed to the eavesdropper and artificial noise (AN) is applied to interfere with the eavesdropper, thus significantly increasing the secrecy rates of short-range secure communications. Aiming at obtaining the maximum secrecy rate, we develop the Riemannian manifold conjugate gradient (RMCG) based alternative optimization (AO) algorithm to assign much power to low-order OAM-modes and optimize the OAM beams direction with the programmable RIS, thus respectively enhancing and weakening the received signal strength at the legitimate receiver and the eavesdropper. Numerical results show that our proposed scheme outperforms the existing works in terms of the secrecy rate and the eavesdropper's bit error rate., Comment: arXiv admin note: text overlap with arXiv:2406.05799

Artificial intelligence and machine learning frameworks have served as computationally efficient mapping between inputs and outputs for engineering problems. These mappings have enabled optimization and analysis routines that have warranted superior designs, ingenious material systems and optimized manufacturing processes. A common occurrence in such modeling endeavors is the existence of multiple source of data, each differentiated by fidelity, operating conditions, experimental conditions, and more. Data fusion frameworks have opened the possibility of combining such differentiated sources into single unified models, enabling improved accuracy and knowledge transfer. However, these frameworks encounter limitations when the different sources are heterogeneous in nature, i.e., not sharing the same input parameter space. These heterogeneous input scenarios can occur when the domains differentiated by complexity, scale, and fidelity require different parametrizations. Towards addressing this void, a heterogeneous multi-source data fusion framework is proposed based on input mapping calibration (IMC) and latent variable Gaussian process (LVGP). In the first stage, the IMC algorithm is utilized to transform the heterogeneous input parameter spaces into a unified reference parameter space. In the second stage, a multi-source data fusion model enabled by LVGP is leveraged to build a single source-aware surrogate model on the transformed reference space. The proposed framework is demonstrated and analyzed on three engineering case studies (design of cantilever beam, design of ellipsoidal void and modeling properties of Ti6Al4V alloy). The results indicate that the proposed framework provides improved predictive accuracy over a single source model and transformed but source unaware model., Comment: 20 Pages,9 Figures, Data is available per request

With the rapid development of artificial intelligence (AI), large language models (LLMs) such as GPT-4 have garnered significant attention in the scientific community, demonstrating great potential in advancing scientific discovery. This progress raises a critical question: are these LLMs well-aligned with real-world physicochemical principles? Current evaluation strategies largely emphasize fact-based knowledge, such as material property prediction or name recognition, but they often lack an understanding of fundamental physicochemical mechanisms that require logical reasoning. To bridge this gap, our study developed a benchmark consisting of 775 multiple-choice questions focusing on the mechanisms of gold nanoparticle synthesis. By reflecting on existing evaluation metrics, we question whether a direct true-or-false assessment merely suggests conjecture. Hence, we propose a novel evaluation metric, the confidence-based score (c-score), which probes the output logits to derive the precise probability for the correct answer. Based on extensive experiments, our results show that in the context of gold nanoparticle synthesis, LLMs understand the underlying physicochemical mechanisms rather than relying on conjecture. This study underscores the potential of LLMs to grasp intrinsic scientific mechanisms and sets the stage for developing more reliable and effective AI tools across various scientific domains.

We propose a unified object-aware temporal learning framework for multi-view 3D detection and tracking tasks. Having observed that the efficacy of the temporal fusion strategy in recent multi-view perception methods may be weakened by distractors and background clutters in historical frames, we propose a cyclic learning mechanism to improve the robustness of multi-view representation learning. The essence is constructing a backward bridge to propagate information from model predictions (e.g., object locations and sizes) to image and BEV features, which forms a circle with regular inference. After backward refinement, the responses of target-irrelevant regions in historical frames would be suppressed, decreasing the risk of polluting future frames and improving the object awareness ability of temporal fusion. We further tailor an object-aware association strategy for tracking based on the cyclic learning model. The cyclic learning model not only provides refined features, but also delivers finer clues (e.g., scale level) for tracklet association. The proposed cycle learning method and association module together contribute a novel and unified multi-task framework. Experiments on nuScenes show that the proposed model achieves consistent performance gains over baselines of different designs (i.e., dense query-based BEVFormer, sparse query-based SparseBEV and LSS-based BEVDet4D) on both detection and tracking evaluation., Comment: Accepted by IJCV

Text-to-image (T2I) generation using diffusion models has become a blockbuster service in today's AI cloud. A production T2I service typically involves a serving workflow where a base diffusion model is augmented with various "add-on" modules, notably ControlNet and LoRA, to enhance image generation control. Compared to serving the base model alone, these add-on modules introduce significant loading and computational overhead, resulting in increased latency. In this paper, we present SwiftDiffusion, a system that efficiently serves a T2I workflow through a holistic approach. SwiftDiffusion decouples ControNet from the base model and deploys it as a separate, independently scaled service on dedicated GPUs, enabling ControlNet caching, parallelization, and sharing. To mitigate the high loading overhead of LoRA serving, SwiftDiffusion employs a bounded asynchronous LoRA loading (BAL) technique, allowing LoRA loading to overlap with the initial base model execution by up to k steps without compromising image quality. Furthermore, SwiftDiffusion optimizes base model execution with a novel latent parallelism technique. Collectively, these designs enable SwiftDiffusion to outperform the state-of-the-art T2I serving systems, achieving up to 7.8x latency reduction and 1.6x throughput improvement in serving SDXL models on H800 GPUs, without sacrificing image quality.

Oscillations are ubiquitous in sunspots and the associated higher atmospheres. However, it is still unclear whether these oscillations are driven by the external acoustic waves (p-modes) or generated by the internal magnetoconvection. To obtain clues about the driving source of umbral waves in sunspots, we analyzed the spiral wave patterns (SWPs) in two sunspots registered by IRIS MgII 2796 {\AA} slit-jaw images. By tracking the motion of the SWPs, we find for the first time that two one-armed SWPs coexist in the umbra, and they can rotate either in the same or opposite directions. Furthermore, by analyzing the spatial distribution of the oscillation centers of the one-armed SWPs within the umbra (the oscillation center is defined as the location where the SWP first appears), we find that the chromospheric umbral waves repeatedly originate from the regions with high oscillation power and most of the umbral waves occur in the dark nuclei and strong magnetic field regions of the umbra. Our study results indicate that the chromospheric umbral waves are likely excited by the p-mode oscillations.

The rotation of electron vortex beams (EVBs) presents a complex interplay of the Gouy phase characterizing free-space behavior and Landau states or Larmor rotation observed in magnetic fields. Despite being studied separately, these phenomena manifest within a single beam during its propagation in magnetic fields, lacking a comprehensive description. We address this by utilizing exact solutions of the relativistic paraxial equation in magnetic fields, termed "paraxial Landau modes". The paraxial Landau modes describe the quantum states of EVBs in magnetic fields. Our study of rotation angles demonstrates consistency with experimental data, supporting the practical presence of these modes. We provide a unified description of different regimes under generalized Gouy rotation, linking the Gouy phase to EVB rotation angles. This connection enhances our understanding of the Gouy phase and can be extended to nonuniform magnetic fields. Our theoretical analysis is validated through numerical simulations using the Chebyshev method. This work offers new insights into the dynamics of EVBs in magnetic fields and suggests practical applications in beam manipulation and beam optics of vortex particles.

The fracture characteristics of LuPO4 rare-earth phosphate environmental barrier coating (EBC) material under molten calcium-magnesium aluminosilicate (CMAS) corrosion is quantified. EBCs are crucial for protecting SiC-based ceramic matrix composite components in the hot section of gas turbine engines. Recent research has highlighted the potential of rare-earth phosphates as better EBC materials than third-generation rare-earth silicates for CMAS corrosion resistance. However, the fracture of EBCs under CMAS corrosion during service remains a significant concern. This work investigates the fracture behavior of LuPO4 using mesoscale simulation and experiments. The model uses micrographs taken from fabricated EBC samples for mesoscale fracture simulations. The simulation results are compared with experimental fracture toughness data and validated using statistical tests (p<0.01). The simulation results and experimental observations demonstrate that LuPO4 may exhibit higher fracture resistance than Lu2SiO5 rare-earth silicate under similar CMAS corrosion conditions, offering potential insights for future EBC design and development.

Generating fine-grained video descriptions is a fundamental challenge in video understanding. In this work, we introduce Tarsier, a family of large-scale video-language models designed to generate high-quality video descriptions. Tarsier employs CLIP-ViT to encode frames separately and then uses an LLM to model temporal relationships. Despite its simple architecture, we demonstrate that with a meticulously designed two-stage training procedure, the Tarsier models exhibit substantially stronger video description capabilities than any existing open-source model, showing a $+51.4\%$ advantage in human side-by-side evaluation over the strongest model. Additionally, they are comparable to state-of-the-art proprietary models, with a $+12.3\%$ advantage against GPT-4V and a $-6.7\%$ disadvantage against Gemini 1.5 Pro. When upgraded to Tarsier2 by building upon SigLIP and Qwen2-7B, it further improves significantly with a $+4.8\%$ advantage against GPT-4o. Besides video description, Tarsier proves to be a versatile generalist model, achieving new state-of-the-art results across nine public benchmarks, including multi-choice VQA, open-ended VQA, and zero-shot video captioning. Our second contribution is the introduction of a new benchmark -- DREAM-1K (https://tarsier-vlm.github.io/) for evaluating video description models, consisting of a new challenging dataset featuring videos from diverse sources and varying complexity, along with an automatic method specifically designed to assess the quality of fine-grained video descriptions. We make our models and evaluation benchmark publicly available at https://github.com/bytedance/tarsier.

We propose UAD, a method for vision-based end-to-end autonomous driving (E2EAD), achieving the best open-loop evaluation performance in nuScenes, meanwhile showing robust closed-loop driving quality in CARLA. Our motivation stems from the observation that current E2EAD models still mimic the modular architecture in typical driving stacks, with carefully designed supervised perception and prediction subtasks to provide environment information for oriented planning. Although achieving groundbreaking progress, such design has certain drawbacks: 1) preceding subtasks require massive high-quality 3D annotations as supervision, posing a significant impediment to scaling the training data; 2) each submodule entails substantial computation overhead in both training and inference. To this end, we propose UAD, an E2EAD framework with an unsupervised proxy to address all these issues. Firstly, we design a novel Angular Perception Pretext to eliminate the annotation requirement. The pretext models the driving scene by predicting the angular-wise spatial objectness and temporal dynamics, without manual annotation. Secondly, a self-supervised training strategy, which learns the consistency of the predicted trajectories under different augment views, is proposed to enhance the planning robustness in steering scenarios. Our UAD achieves 38.7% relative improvements over UniAD on the average collision rate in nuScenes and surpasses VAD for 41.32 points on the driving score in CARLA's Town05 Long benchmark. Moreover, the proposed method only consumes 44.3% training resources of UniAD and runs 3.4 times faster in inference. Our innovative design not only for the first time demonstrates unarguable performance advantages over supervised counterparts, but also enjoys unprecedented efficiency in data, training, and inference. Code and models will be released at https://github.com/KargoBot_Research/UAD., Comment: 17 pages, 10 figures and 15 tables

Children with Autism Spectrum Disorder (ASD) often misunderstand social situations and struggle to participate in daily routines. Social Stories are traditionally crafted by psychology experts under strict constraints to address these challenges but are costly and limited in diversity. As Large Language Models (LLMs) advance, there's an opportunity to develop more automated, affordable, and accessible methods to generate Social Stories in real-time with broad coverage. However, adapting LLMs to meet the unique and strict constraints of Social Stories is a challenging issue. To this end, we propose \textbf{SS-GEN}, a \textbf{S}ocial \textbf{S}tory \textbf{GEN}eration framework with LLMs. Firstly, we develop a constraint-driven sophisticated strategy named \textbf{\textsc{StarSow}} to hierarchically prompt LLMs to generate Social Stories at scale, followed by rigorous human filtering to build a high-quality dataset. Additionally, we introduce \textbf{quality assessment criteria} to evaluate the effectiveness of these generated stories. Considering that powerful closed-source large models require very complex instructions and expensive API fees, we finally fine-tune smaller language models with our curated high-quality dataset, achieving comparable results at lower costs and with simpler instruction and deployment. This work marks a significant step in leveraging AI to personalize Social Stories cost-effectively for autistic children at scale, which we hope can encourage future research. The prompt, code and data will release in the \texttt{Technical Appendix} and \texttt{Code \& Data Appendix} at \url{https://github.com/MIMIFY/SS-GEN}.

It was shown in literature that speech representations extracted by self-supervised pre-trained models exhibit similarities with brain activations of human for speech perception and fine-tuning speech representation models on downstream tasks can further improve the similarity. However, it still remains unclear if this similarity can be used to optimize the pre-trained speech models. In this work, we therefore propose to use the brain activations recorded by fMRI to refine the often-used wav2vec2.0 model by aligning model representations toward human neural responses. Experimental results on SUPERB reveal that this operation is beneficial for several downstream tasks, e.g., speaker verification, automatic speech recognition, intent classification.One can then consider the proposed method as a new alternative to improve self-supervised speech models., Comment: accpeted by Interspeech2024

Voice anonymization has been developed as a technique for preserving privacy by replacing the speaker's voice in a speech signal with that of a pseudo-speaker, thereby obscuring the original voice attributes from machine recognition and human perception. In this paper, we focus on altering the voice attributes against machine recognition while retaining human perception. We referred to this as the asynchronous voice anonymization. To this end, a speech generation framework incorporating a speaker disentanglement mechanism is employed to generate the anonymized speech. The speaker attributes are altered through adversarial perturbation applied on the speaker embedding, while human perception is preserved by controlling the intensity of perturbation. Experiments conducted on the LibriSpeech dataset showed that the speaker attributes were obscured with their human perception preserved for 60.71% of the processed utterances., Comment: accpeted by Interspeech2024

We present early-time, hour-to-day cadence spectroscopy of the nearby type II supernova (SN II) 2024ggi, which was discovered at a phase when the SN shock just emerged from the red-supergiant (RSG) progenitor star. Over the first few days after the first light, SN 2024ggi exhibited prominent narrow emission lines formed through intense and persistent photoionization of the nearby circumstellar material (CSM). In the first 63 hours, spectral lines of He, C, N, and O revealed a rapid rise in ionization, as a result of the progressive sweeping-up of the CSM by the shock. The duration of the IIn-like spectra indicates a dense and relatively confined CSM distribution extending up to $\sim 4 \times 10^{14}$ cm. Spectral modeling reveals a CSM mass loss rate at this region exceeding $5 \times 10^{-3}{\rm M}_{\odot}$ yr$^{-1}$ is required to reproduce low-ionization emissions, which dramatically exceeds that of an RSG. Analyzing H$\alpha$ emission shift implies the velocity of the unshocked outer CSM to be between 20 and 40 km s$^{-1}$, matching the typical wind velocity of an RSG. The differences between the inner and outer layers of the CSM and an RSG progenitor highlight a complex mass loss history before the explosion of SN 2024ggi., Comment: 10 pages and 5 figures in the main text (16 pages and 9 figures in total). https://iopscience.iop.org/article/10.3847/2041-8213/ad5da4

Rolling bearing fault detection has developed rapidly in the field of fault diagnosis technology, and it occupies a very important position in this field. Deep learning-based bearing fault diagnosis models have achieved significant success. At the same time, with the continuous improvement of new signal processing technologies such as Fourier transform, wavelet transform and empirical mode decomposition, the fault diagnosis technology of rolling bearings has also been greatly developed, and it can be said that it has entered a new research stage. However, most of the existing methods are limited to varying degrees in the industrial field. The main ones are fast feature extraction and computational complexity. The key to this paper is to propose a lightweight bearing fault diagnosis model DKDL-Net to solve these challenges. The model is trained on the CWRU data set by decoupling knowledge distillation and low rank adaptive fine tuning. Specifically, we built and trained a teacher model based on a 6-layer neural network with 69,626 trainable parameters, and on this basis, using decoupling knowledge distillation (DKD) and Low-Rank adaptive (LoRA) fine-tuning, we trained the student sag model DKDL-Net, which has only 6838 parameters. Experiments show that DKDL-Net achieves 99.48% accuracy in computational complexity on the test set while maintaining model performance, which is 0.58% higher than the state-of-the-art (SOTA) model, and our model has lower parameters. Our code is available at Github link: https://github.com/SPBU-LiPengyi/DKDL-Net.git.

The spectrum share and open nature of wireless channels enable integrated sensing and communication (ISAC) susceptible to hostile jamming attacks. Due to the intrinsic orthogonality and rich azimuth angle information of orbital angular momentum (OAM), vortex electromagnetic waves with helical phase fronts have shown great potential to achieve high-resolution imaging and strong anti-jamming capability of wireless communication. Focusing on significantly enhancing the anti-jamming results of ISAC systems with limited bandwidth under hostile jamming, in this paper we propose a novel ISAC for anti-jamming with OAM scheme, where the OAM legitimate transmitter can simultaneously sense the position of jammers with dynamic behavior and send data to multiple OAM legitimate users. Specifically, the OAM modes for sensing and communications are respectively hopped according to pre-set index modulation information to suppress jamming. To acquire the position of the jammer, we develop the enhanced multiple-signal-classification-based three-dimension position estimation scheme with continuous sensing in both frequency and angular domains, where the OAM transmitter is designed with the concentric uniform-circular-array mono-static method, to significantly increase the azimuthal resolution. Then, based on the acquired jamming channel state information, we develop the joint transmit-receive beamforming and power allocation scheme, where the transmit and receive beamforming matrices are dynamically adjusted to mitigate the mixed interference containing inter-mode interference, inter-user interference, and jamming, thus maximizing the achievable sum rates (ASRs) of all users. Numerical results demonstrate that our proposed scheme can significantly increase the ASR under broadband jamming attacks and achieve high detection accuracy of targets .

To satisfy the various demands of growing devices and services, emerging high-frequency-based technologies promote near-field wireless communications. Therefore, near-field physical layer security has attracted much attention to facilitate the wireless information security against illegitimate eavesdropping. However, highly correlated channels between legitimate transceivers and eavesdroppers of existing multiple-input multiple-output (MIMO) based near-field secure technologies along with the low degrees of freedom significantly limit the enhancement of security results in wireless communications. To significantly increase the secrecy rates of near-field wireless communications, in this paper we propose the double-reconfigurable-intelligent-surface (RIS) assisted orbital angular momentum (OAM) secure scheme, where RISs with few reflecting elements are easily deployed to reconstruct the direct links blocked by obstacles between the legitimate transceivers, mitigate the inter-mode interference caused by the misalignment of legitimate transceivers, and adjust the OAM beams direction to interfere with eavesdroppers. Meanwhile, due to the unique orthogonality among OAM modes, the OAM-based joint index modulation and artificial noise scheme is proposed to weaken the information acquisition by eavesdroppers while increasing the achievable rate with the low cost of legitimate communications. To maximize the secrecy rate of our proposed scheme, we develop the Riemannian manifold conjugate gradient (RMCG)-based alternative optimization (AO) algorithm to jointly optimize the transmit power allocation of OAM modes and phase shifts of double RISs. Numerical results show that our proposed double-RIS-assisted OAM near-field secure scheme outperforms the existing works in terms of the secrecy rate and the eavesdropper's bit error rate.

Any-to-any singing voice conversion (SVC) is an interesting audio editing technique, aiming to convert the singing voice of one singer into that of another, given only a few seconds of singing data. However, during the conversion process, the issue of timbre leakage is inevitable: the converted singing voice still sounds like the original singer's voice. To tackle this, we propose a latent diffusion model for SVC (LDM-SVC) in this work, which attempts to perform SVC in the latent space using an LDM. We pretrain a variational autoencoder structure using the noted open-source So-VITS-SVC project based on the VITS framework, which is then used for the LDM training. Besides, we propose a singer guidance training method based on classifier-free guidance to further suppress the timbre of the original singer. Experimental results show the superiority of the proposed method over previous works in both subjective and objective evaluations of timbre similarity., Comment: Accepted by Interspeech 2024

Accurate photometric redshift (photo-$z$) estimation requires support from multi-band observational data. However, in the actual process of astronomical observations and data processing, some sources may have missing observational data in certain bands for various reasons. This could greatly affect the accuracy and reliability of photo-$z$ estimation for these sources, and even render some estimation methods unusable. The same situation may exist for the upcoming Chinese Space Station Telescope (CSST). In this study, we employ a deep learning method called Generative Adversarial Imputation Networks (GAIN) to impute the missing photometric data in CSST, aiming to reduce the impact of data missing on photo-$z$ estimation and improve estimation accuracy. Our results demonstrate that using the GAIN technique can effectively fill in the missing photometric data in CSST. Particularly, when the data missing rate is below 30\%, the imputation of photometric data exhibits high accuracy, with higher accuracy in the $g$, $r$, $i$, $z$, and $y$ bands compared to the $NUV$ and $u$ bands. After filling in the missing values, the quality of photo-$z$ estimation obtained by the widely used Easy and Accurate Zphot from Yale (EAZY) software is notably enhanced. Evaluation metrics for assessing the quality of photo-$z$ estimation, including the catastrophic outlier fraction ($f_{out}$), the normalized median absolute deviation ($\rm {\sigma_{NMAD}}$), and the bias of photometric redshift ($bias$), all show some degree of improvement. Our research will help maximize the utilization of observational data and provide a new method for handling sample missing values for applications that require complete photometry data to produce results.

Model heterogeneous federated learning (MHeteroFL) enables FL clients to collaboratively train models with heterogeneous structures in a distributed fashion. However, existing MHeteroFL methods rely on training loss to transfer knowledge between the client model and the server model, resulting in limited knowledge exchange. To address this limitation, we propose the Federated model heterogeneous Matryoshka Representation Learning (FedMRL) approach for supervised learning tasks. It adds an auxiliary small homogeneous model shared by clients with heterogeneous local models. (1) The generalized and personalized representations extracted by the two models' feature extractors are fused by a personalized lightweight representation projector. This step enables representation fusion to adapt to local data distribution. (2) The fused representation is then used to construct Matryoshka representations with multi-dimensional and multi-granular embedded representations learned by the global homogeneous model header and the local heterogeneous model header. This step facilitates multi-perspective representation learning and improves model learning capability. Theoretical analysis shows that FedMRL achieves a $O(1/T)$ non-convex convergence rate. Extensive experiments on benchmark datasets demonstrate its superior model accuracy with low communication and computational costs compared to seven state-of-the-art baselines. It achieves up to 8.48% and 24.94% accuracy improvement compared with the state-of-the-art and the best same-category baseline, respectively.