arXiv subjects

Xu Tian

Publications and source records attributed to Xu Tian.

13 recordsLinked to original sources

arXiv2026

Percolating Multifractal Domains at a Polymorphic Phase Boundary

Giant piezoelectricity in ferroelectrics is commonly associated with phase-boundary instabilities, among which the polymorphic phase boundary (PPB) is a prominent example conventionally attributed to the coexistence of ferroelectric phases. Here, using large-scale molecular dynamics simulations of the lead-free (K,Na)NbO3-(Bi,Na)ZrO3 solid solutions, we show that the PPB hosts a percolating multifractal polar domain which governs the dielectric and piezoelectric responses. By quantifying the global fractal dimension and multifractal spectrum width of this polar network, we identify fractal connectivity and multiscale heterogeneity as microstructural order parameters for the PPB. The maximum reversible piezoelectric response occurs when the fractal-domain volume fraction approaches the three-dimensional percolation threshold, suggesting that near-critical polar connectivity enables giant reversible electromechanical coupling. In this mechanism, the fractal backbone preserves polar memory and provides the restoring force required for reversibility, while the surrounding nonfractal regions supply the polar compliance needed for large polarization rotation and strain. These results establish percolating multifractal polar domains as a microscopic mechanism for PPB-enhanced piezoelectricity and suggest fractal connectivity as a design parameter for high-performance piezoelectrics.

cond-mat.mtrl-sci↗

arXiv2026

Benchmark Evaluation of Federated Learning on Multi-organ Images

The privacy requirements of medical data and its substantial variations across organs and modalities hinder the clinical implementation of medical AI. Federated learning (FL) is a feasible approach to overcome these challenges. Due to the continuous emergence of FL algorithms and the highly heterogeneous nature of medical data, objectively evaluating their performance in real-world clinical settings remains difficult. Therefore, a comprehensive federated medical imaging benchmark, serving as a unified evaluation standard, is crucial for advancing the technology toward reliable clinical application. Existing federated medical imaging benchmarks have not yet adequately incorporated state-of-the-art algorithms, are limited to data from single organs or modalities, and overly emphasize model accuracy, making it difficult to comprehensively assess the overall efficacy of FL in real-world medical environments. To address these challenges, we developed the MobenFL benchmark. This benchmark integrates 20 cutting-edge FL algorithms and 22 medical imaging datasets, covering 12 critical organs across the human body, surpassing existing benchmark in breadth. In terms of evaluation dimensions, MobenFL not only assesses performance but also systematically incorporates key metrics such as algorithmic efficiency and privacy protection capabilities. Additionally, it conducts specialized evaluations for complex real-world clinical scenarios involving different diseases, devices, and imaging modalities, thereby providing a comprehensive and in-depth evaluation framework for the clinical application of FL in the medical field.

cs.CV↗

arXiv2026

Task-guided Spatiotemporal Network with Diffusion Augmentation for EEG-based Dementia Diagnosis and MMSE Prediction

Patients with dementia typically exhibit cognitive impairment, which is routinely assessed using the Mini-Mental State Examination (MMSE). Concurrently, their underlying neurophysiological abnormalities are reflected in Electroencephalography (EEG), providing a basis for joint modeling. However, traditional multi-task approaches suffer from feature entanglement, which leads to inter-task interference when handling heterogeneous objectives.To address this challenge, we propose a task-guided spatiotemporal network (TGSN) with diffusion augmentation for EEG-based dementia diagnosis and MMSE prediction. Specifically, TGSN integrates a multi-band feature fusion module to capture complementary spectral information from EEG. Meanwhile, a pre-trained data augmentation module utilizing a diffusion process is introduced toincrease sample diversity. To model the complex spatiotemporal patterns of EEG, we propose a gated spatiotemporal attention module that captures long-range spatial dependencies and temporal dynamics. Moreover, we design a task-guided query module to achieve task-specific feature extraction, thereby mitigating task interference. The effectiveness of TGSN is evaluated on the XY02 dataset. Experimental results demonstrate that the proposed network outperforms several state-of-the-art methods, achieving classification accuracies of 97.78\% for Alzheimer's Disease (AD)/Frontotemporal Dementia (FTD) and 83.93\% for AD/FTD/Vascular Cognitive Impairment (VCI), which exceed the best baselines by 16.39\% and 8.28\%, respectively. In parallel, it reduces the RMSE for MMSE prediction to 1.93 and 2.38, achieving significant error reductions of 1.44 and 1.43 compared to the best baselines. Additionally, validation on the DS004504 dataset demonstrates strong cross-dataset generalization...

cs.LG↗

arXiv2025

Mixed-State Phase Transitions in Measurement-Dressed Imaginary-Time Evolution

Motivated by the ubiquity of decoherence in quantum hardware and the growing role of imaginary-time evolution (ITE) in quantum algorithms, we investigate how many-body correlations generated by imaginary-time filtering are modified by local decoherence. We introduce measurement-dressed imaginary-time evolution (MDITE), which alternates ITE with projective-measurement channels, producing a competition between low-energy filtering and local dephasing. By developing a new efficient quantum Monte Carlo method, we uncover MDITE mixed-state transitions with spontaneous-symmetry-breaking signatures in the driving of 1D transverse-field Ising and 2D columnar dimerized Heisenberg Hamiltonians in the resulting density matrices. In the continuous limit, the Choi-Jamiolkowski mapping yields a tractable equilibrium description with conformal criticality that qualitatively captures the phase transitions. At finite protocol parameters, however, the four-point correlator violates the conformal cross-ratio form and the critical exponents deviate from their continuous-limit values, signaling the loss of conformal symmetry and richer nonequilibrium criticality. Our results establish MDITE as a controlled setting for exploring mixed-state phases and critical phenomena driven by the interplay between imaginary-time filtering and decoherence.

quant-ph↗

arXiv2025

CEPerFed: Communication-Efficient Personalized Federated Learning for Multi-Pulse MRI Classification

Multi-pulse magnetic resonance imaging (MRI) is widely utilized for clinical practice such as Alzheimer's disease diagnosis. To train a robust model for multi-pulse MRI classification, it requires large and diverse data from various medical institutions while protecting privacy by preventing raw data sharing across institutions. Although federated learning (FL) is a feasible solution to address this issue, it poses challenges of model convergence due to the effect of data heterogeneity and substantial communication overhead due to large numbers of parameters transmitted within the model. To address these challenges, we propose CEPerFed, a communication-efficient personalized FL method. It mitigates the effect of data heterogeneity by incorporating client-side historical risk gradients and historical mean gradients to coordinate local and global optimization. The former is used to weight the contributions from other clients, enhancing the reliability of local updates, while the latter enforces consistency between local updates and the global optimization direction to ensure stable convergence across heterogeneous data distributions. To address the high communication overhead, we propose a hierarchical SVD (HSVD) strategy that transmits only the most critical information required for model updates. Experiments on five classification tasks demonstrate the effectiveness of the CEPerFed method. The code will be released upon acceptance at https://github.com/LD0416/CEPerFed.

cs.LG↗

arXiv2025

Spontaneous continuous-symmetry breaking and tower of states in a comb chain

Based on the study of a one-dimensional (1D) antiferromagnetic Heisenberg model on a comb lattice, this work identifies an example of spontaneous continuous symmetry breaking in a 1D system with short-range interactions. When a symmetry-preserving relevant perturbation is applied to the system, we find that this model can always be described by the Marshall-Lieb-Mattis (MLM) theorem. The Shen-Qiu-Tian theorem establishes a direct connection between the MLM theorem (in the case of bipartite lattices with unequal numbers of sites in the two sublattices) and the breaking of continuous symmetry. Moreover, although authors of previous studies have suggested that the presence of a tower of states (TOS) serves as an important numerical diagnostic of the tendency of a system toward spontaneous symmetry breaking, these investigations have primarily focused on two-dimensional systems. In 1D systems, however, the presence of long-range order does not automatically imply the emergence of a TOS. Here, we observe the existence of a TOS in a 1D realistic ferrimagnetic lattice system with short-range interactions.

cond-mat.str-el↗

arXiv2023

MRI-based Multi-task Decoupling Learning for Alzheimer's Disease Detection and MMSE Score Prediction: A Multi-site Validation

Accurately detecting Alzheimer's disease (AD) and predicting mini-mental state examination (MMSE) score are important tasks in elderly health by magnetic resonance imaging (MRI). Most of the previous methods on these two tasks are based on single-task learning and rarely consider the correlation between them. Since the MMSE score, which is an important basis for AD diagnosis, can also reflect the progress of cognitive impairment, some studies have begun to apply multi-task learning methods to these two tasks. However, how to exploit feature correlation remains a challenging problem for these methods. To comprehensively address this challenge, we propose a MRI-based multi-task decoupled learning method for AD detection and MMSE score prediction. First, a multi-task learning network is proposed to implement AD detection and MMSE score prediction, which exploits feature correlation by adding three multi-task interaction layers between the backbones of the two tasks. Each multi-task interaction layer contains two feature decoupling modules and one feature interaction module. Furthermore, to enhance the generalization between tasks of the features selected by the feature decoupling module, we propose the feature consistency loss constrained feature decoupling module. Finally, in order to exploit the specific distribution information of MMSE score in different groups, a distribution loss is proposed to further enhance the model performance. We evaluate our proposed method on multi-site datasets. Experimental results show that our proposed multi-task decoupled representation learning method achieves good performance, outperforming single-task learning and other existing state-of-the-art methods.

eess.IV↗

arXiv2021

Incentive Compatible Pareto Alignment for Multi-Source Large Graphs

In this paper, we focus on learning effective entity matching models over multi-source large-scale data. For real applications, we relax typical assumptions that data distributions/spaces, or entity identities are shared between sources, and propose a Relaxed Multi-source Large-scale Entity-matching (RMLE) problem. Challenges of the problem include 1) how to align large-scale entities between sources to share information and 2) how to mitigate negative transfer from joint learning multi-source data. What's worse, one practical issue is the entanglement between both challenges. Specifically, incorrect alignments may increase negative transfer; while mitigating negative transfer for one source may result in poorly learned representations for other sources and then decrease alignment accuracy. To handle the entangled challenges, we point out that the key is to optimize information sharing first based on Pareto front optimization, by showing that information sharing significantly influences the Pareto front which depicts lower bounds of negative transfer. Consequently, we proposed an Incentive Compatible Pareto Alignment (ICPA) method to first optimize cross-source alignments based on Pareto front optimization, then mitigate negative transfer constrained on the optimized alignments. This mechanism renders each source can learn based on its true preference without worrying about deteriorating representations of other sources. Specifically, the Pareto front optimization encourages minimizing lower bounds of negative transfer, which optimizes whether and which to align. Comprehensive empirical evaluation results on four large-scale datasets are provided to demonstrate the effectiveness and superiority of ICPA. Online A/B test results at a search advertising platform also demonstrate the effectiveness of ICPA in production environments.

stat.ML↗

arXiv2017

Speculate-Correct Error Bounds for k-Nearest Neighbor Classifiers

We introduce the speculate-correct method to derive error bounds for local classifiers. Using it, we show that k nearest neighbor classifiers, in spite of their famously fractured decision boundaries, have exponential error bounds with O(sqrt((k + ln n) / n)) error bound range for n in-sample examples.

cs.LG↗

arXiv2017

Frame Stacking and Retaining for Recurrent Neural Network Acoustic Model

Frame stacking is broadly applied in end-to-end neural network training like connectionist temporal classification (CTC), and it leads to more accurate models and faster decoding. However, it is not well-suited to conventional neural network based on context-dependent state acoustic model, if the decoder is unchanged. In this paper, we propose a novel frame retaining method which is applied in decoding. The system which combined frame retaining with frame stacking could reduces the time consumption of both training and decoding. Long short-term memory (LSTM) recurrent neural networks (RNNs) using it achieve almost linear training speedup and reduces relative 41\% real time factor (RTF). At the same time, recognition performance is no degradation or improves sightly on Shenma voice search dataset in Mandarin.

cs.CL↗

arXiv2017

Deep LSTM for Large Vocabulary Continuous Speech Recognition

Recurrent neural networks (RNNs), especially long short-term memory (LSTM) RNNs, are effective network for sequential task like speech recognition. Deeper LSTM models perform well on large vocabulary continuous speech recognition, because of their impressive learning ability. However, it is more difficult to train a deeper network. We introduce a training framework with layer-wise training and exponential moving average methods for deeper LSTM models. It is a competitive framework that LSTM models of more than 7 layers are successfully trained on Shenma voice search data in Mandarin and they outperform the deep LSTM models trained by conventional approach. Moreover, in order for online streaming speech recognition applications, the shallow model with low real time factor is distilled from the very deep model. The recognition accuracy have little loss in the distillation process. Therefore, the model trained with the proposed training framework reduces relative 14\% character error rate, compared to original model which has the similar real-time capability. Furthermore, the novel transfer learning strategy with segmental Minimum Bayes-Risk is also introduced in the framework. The strategy makes it possible that training with only a small part of dataset could outperform full dataset training from the beginning.

cs.CL↗

arXiv2017

Exponential Moving Average Model in Parallel Speech Recognition Training

As training data rapid growth, large-scale parallel training with multi-GPUs cluster is widely applied in the neural network model learning currently.We present a new approach that applies exponential moving average method in large-scale parallel training of neural network model. It is a non-interference strategy that the exponential moving average model is not broadcasted to distributed workers to update their local models after model synchronization in the training process, and it is implemented as the final model of the training system. Fully-connected feed-forward neural networks (DNNs) and deep unidirectional Long short-term memory (LSTM) recurrent neural networks (RNNs) are successfully trained with proposed method for large vocabulary continuous speech recognition on Shenma voice search data in Mandarin. The character error rate (CER) of Mandarin speech recognition further degrades than state-of-the-art approaches of parallel training.

cs.CL↗

arXiv2014

On semi-classical limits of ground states of a nonlinear Maxwell-Dirac system

We study the semi-classical ground states of the nonlinear Maxwell-Dirac system: \[ \left\{ \begin{aligned} &\al\cdot\big(i\hbar\nabla+ q(x)\fa(x)\big) w-a\bt w -ωw - q(x)ϕ(x) w = P(x)g(\jdz{w}) w\\ &-Δϕ=q(x)\jdz{w}^2\\ &-Δ{A_k}=q(x)(α_k w)\cdot \bar w\ \ \ \ k=1,2,3 \end{aligned}\right. \] for $x\in\R^3$, where $\fa$ is the magnetic field, $ϕ$ is the electron field and $q$ describes the changing pointwise charge distribution. We develop a variational method to establish the existence of least energy solutions for $\hbar$ small. We also describe the concentration behavior of the solutions as $\hbar\to 0$.

math.AP↗