arXiv subjects

Xiaochen Yang

Publications and source records attributed to Xiaochen Yang.

At least 37 records · Page 2Linked to original sources

arXiv2025

Self-Supervised Cross-Encoder for Neurodegenerative Disease Diagnosis

Deep learning has shown significant potential in diagnosing neurodegenerative diseases from MRI data. However, most existing methods rely heavily on large volumes of labeled data and often yield representations that lack interpretability. To address both challenges, we propose a novel self-supervised cross-encoder framework that leverages the temporal continuity in longitudinal MRI scans for supervision. This framework disentangles learned representations into two components: a static representation, constrained by contrastive learning, which captures stable anatomical features; and a dynamic representation, guided by input-gradient regularization, which reflects temporal changes and can be effectively fine-tuned for downstream classification tasks. Experimental results on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that our method achieves superior classification accuracy and improved interpretability. Furthermore, the learned representations exhibit strong zero-shot generalization on the Open Access Series of Imaging Studies (OASIS) dataset and cross-task generalization on the Parkinson Progression Marker Initiative (PPMI) dataset. The code for the proposed method will be made publicly available.

cs.CV↗

arXiv2025

PathoSCOPE: Few-Shot Pathology Detection via Self-Supervised Contrastive Learning and Pathology-Informed Synthetic Embeddings

Unsupervised pathology detection trains models on non-pathological data to flag deviations as pathologies, offering strong generalizability for identifying novel diseases and avoiding costly annotations. However, building reliable normality models requires vast healthy datasets, as hospitals' data is inherently biased toward symptomatic populations, while privacy regulations hinder the assembly of representative healthy cohorts. To address this limitation, we propose PathoSCOPE, a few-shot unsupervised pathology detection framework that requires only a small set of non-pathological samples (minimum 2 shots), significantly improving data efficiency. We introduce Global-Local Contrastive Loss (GLCL), comprised of a Local Contrastive Loss to reduce the variability of non-pathological embeddings and a Global Contrastive Loss to enhance the discrimination of pathological regions. We also propose a Pathology-informed Embedding Generation (PiEG) module that synthesizes pathological embeddings guided by the global loss, better exploiting the limited non-pathological samples. Evaluated on the BraTS2020 and ChestXray8 datasets, PathoSCOPE achieves state-of-the-art performance among unsupervised methods while maintaining computational efficiency (2.48 GFLOPs, 166 FPS).

cs.CV↗

arXiv2025

VISTA: Unsupervised 2D Temporal Dependency Representations for Time Series Anomaly Detection

Time Series Anomaly Detection (TSAD) is essential for uncovering rare and potentially harmful events in unlabeled time series data. Existing methods are highly dependent on clean, high-quality inputs, making them susceptible to noise and real-world imperfections. Additionally, intricate temporal relationships in time series data are often inadequately captured in traditional 1D representations, leading to suboptimal modeling of dependencies. We introduce VISTA, a training-free, unsupervised TSAD algorithm designed to overcome these challenges. VISTA features three core modules: 1) Time Series Decomposition using Seasonal and Trend Decomposition via Loess (STL) to decompose noisy time series into trend, seasonal, and residual components; 2) Temporal Self-Attention, which transforms 1D time series into 2D temporal correlation matrices for richer dependency modeling and anomaly detection; and 3) Multivariate Temporal Aggregation, which uses a pretrained feature extractor to integrate cross-variable information into a unified, memory-efficient representation. VISTA's training-free approach enables rapid deployment and easy hyperparameter tuning, making it suitable for industrial applications. It achieves state-of-the-art performance on five multivariate TSAD benchmarks.

cs.LG↗

arXiv2025

Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation

Automatic adversarial prompt generation provides remarkable success in jailbreaking safely-aligned large language models (LLMs). Existing gradient-based attacks, while demonstrating outstanding performance in jailbreaking white-box LLMs, often generate garbled adversarial prompts with chaotic appearance. These adversarial prompts are difficult to transfer to other LLMs, hindering their performance in attacking unknown victim models. In this paper, for the first time, we delve into the semantic meaning embedded in garbled adversarial prompts and propose a novel method that "translates" them into coherent and human-readable natural language adversarial prompts. In this way, we can effectively uncover the semantic information that triggers vulnerabilities of the model and unambiguously transfer it to the victim model, without overlooking the adversarial information hidden in the garbled text, to enhance jailbreak attacks. It also offers a new approach to discovering effective designs for jailbreak prompts, advancing the understanding of jailbreak attacks. Experimental results demonstrate that our method significantly improves the success rate of jailbreak attacks against various safety-aligned LLMs and outperforms state-of-the-arts by large margins. With at most 10 queries, our method achieves an average attack success rate of 81.8% in attacking 7 commercial closed-source LLMs, including GPT and Claude-3 series, on HarmBench. Our method also achieves over 90% attack success rates against Llama-2-Chat models on AdvBench, despite their outstanding resistance to jailbreak attacks. Code at: https://github.com/qizhangli/Adversarial-Prompt-Translator.

cs.LG↗

arXiv2025

Synthetic accessibility and sodium ion conductivity of the Na$_{8-x}$A$^{x}$P$_2$O$_9$ (NAP) high-temperature sodium superionic conductor framework

Advancement of solid state electrolytes (SSEs) for all solid state batteries typically focuses on modification of a parent structural framework for improved conductivity, \textit{e.g.} cation substitution for an immobile ion or varying the concentration of the mobile ion. Therefore, novel frameworks can be disruptive by enabling fast ion conduction aided by different structure and diffusion mechanisms, and unlocking optimal conductors with different properties (\textit{e.g.} mechanical properties, sintering needs, electrochemical stability) than previously published. Herein, we perform a high throughput survey of an understudied structural framework for sodium ion conduction, Na$_{8-x}$A$^x$P$_2$O$_9$ (NAP), to understand the family's thermodynamic stability, synthesizability, and ionic conduction. We first show that the parent phase Na$_4$TiP$_2$O$_9$ (NTP) undergoes a structural distortion (with accompanying conductivity transition) due to unstable phonons from a pseduo-Jahn Teller mode in the 1D titanium chains. Then, screening of cation-substituted structural candidates with \textit{ab initio} and machine-learned potential calculations reveal a number of candidates that are thermodynamically stable, likely synthesizable, and have high predicted ionic conductivities. High throughput experimental trials and subsequent methodology optimization of one Na$_4$SnP$_2$O$_9$ (NSP) highlight collective challenges to the synthesis pathways for sodium phosphate materials via solid state synthesis. Our results demonstrate that NAP is a highly tunable conduction framework whose high temperature conductivity transition has heretofore eliminated it from significant research interest. By expanding the structural toolkit for SSE design, we increase the number of useful sodium ion electrolytes for integration into safe and accessible solid state batteries.

cond-mat.mtrl-sci↗

arXiv2024

COMO: Cross-Mamba Interaction and Offset-Guided Fusion for Multimodal Object Detection

Single-modal object detection tasks often experience performance degradation when encountering diverse scenarios. In contrast, multimodal object detection tasks can offer more comprehensive information about object features by integrating data from various modalities. Current multimodal object detection methods generally use various fusion techniques, including conventional neural networks and transformer-based models, to implement feature fusion strategies and achieve complementary information. However, since multimodal images are captured by different sensors, there are often misalignments between them, making direct matching challenging. This misalignment hinders the ability to establish strong correlations for the same object across different modalities. In this paper, we propose a novel approach called the CrOss-Mamba interaction and Offset-guided fusion (COMO) framework for multimodal object detection tasks. The COMO framework employs the cross-mamba technique to formulate feature interaction equations, enabling multimodal serialized state computation. This results in interactive fusion outputs while reducing computational overhead and improving efficiency. Additionally, COMO leverages high-level features, which are less affected by misalignment, to facilitate interaction and transfer complementary information between modalities, addressing the positional offset challenges caused by variations in camera angles and capture times. Furthermore, COMO incorporates a global and local scanning mechanism in the cross-mamba module to capture features with local correlation, particularly in remote sensing images. To preserve low-level features, the offset-guided fusion mechanism ensures effective multiscale feature utilization, allowing the construction of a multiscale fusion data cube that enhances detection performance.

cs.CV↗

arXiv2024

Denoising Reuse: Exploiting Inter-frame Motion Consistency for Efficient Video Latent Generation

Video generation using diffusion-based models is constrained by high computational costs due to the frame-wise iterative diffusion process. This work presents a Diffusion Reuse MOtion (Dr. Mo) network to accelerate latent video generation. Our key discovery is that coarse-grained noises in earlier denoising steps have demonstrated high motion consistency across consecutive video frames. Following this observation, Dr. Mo propagates those coarse-grained noises onto the next frame by incorporating carefully designed, lightweight inter-frame motions, eliminating massive computational redundancy in frame-wise diffusion models. The more sensitive and fine-grained noises are still acquired via later denoising steps, which can be essential to retain visual qualities. As such, deciding which intermediate steps should switch from motion-based propagations to denoising can be a crucial problem and a key tradeoff between efficiency and quality. Dr. Mo employs a meta-network named Denoising Step Selector (DSS) to dynamically determine desirable intermediate steps across video frames. Extensive evaluations on video generation and editing tasks have shown that Dr. Mo can substantially accelerate diffusion models in video tasks with improved visual qualities.

cs.CV↗

arXiv2024

Warped multifidelity Gaussian processes for data fusion of skewed environmental data

Understanding the dynamics of climate variables is paramount for numerous sectors, like energy and environmental monitoring. This study focuses on the critical need for a precise mapping of environmental variables for national or regional monitoring networks, a task notably challenging when dealing with skewed data. To address this issue, we propose a novel data fusion approach, the \textit{warped multifidelity Gaussian process} (WMFGP). The method performs prediction using multiple time-series, accommodating varying reliability and resolutions and effectively handling skewness. In an extended simulation experiment the benefits and the limitations of the methods are explored, while as a case study, we focused on the wind speed monitored by the network of ARPA Lombardia, one of the regional environmental agencies operting in Italy. ARPA grapples with data gaps, and due to the connection between wind speed and air quality, it struggles with an effective air quality management. We illustrate the efficacy of our approach in filling the wind speed data gaps through two extensive simulation experiments. The case study provides more informative wind speed predictions crucial for predicting air pollutant concentrations, enhancing network maintenance, and advancing understanding of relevant meteorological and climatic phenomena.

stat.AP↗

arXiv2024

Facial Identity Anonymization via Intrinsic and Extrinsic Attention Distraction

The unprecedented capture and application of face images raise increasing concerns on anonymization to fight against privacy disclosure. Most existing methods may suffer from the problem of excessive change of the identity-independent information or insufficient identity protection. In this paper, we present a new face anonymization approach by distracting the intrinsic and extrinsic identity attentions. On the one hand, we anonymize the identity information in the feature space by distracting the intrinsic identity attention. On the other, we anonymize the visual clues (i.e. appearance and geometry structure) by distracting the extrinsic identity attention. Our approach allows for flexible and intuitive manipulation of face appearance and geometry structure to produce diverse results, and it can also be used to instruct users to perform personalized anonymization. We conduct extensive experiments on multiple datasets and demonstrate that our approach outperforms state-of-the-art methods.

cs.CV↗

arXiv2024

PUAL: A Classifier on Trifurcate Positive-Unlabeled Data

Positive-unlabeled (PU) learning aims to train a classifier using the data containing only labeled-positive instances and unlabeled instances. However, existing PU learning methods are generally hard to achieve satisfactory performance on trifurcate data, where the positive instances distribute on both sides of the negative instances. To address this issue, firstly we propose a PU classifier with asymmetric loss (PUAL), by introducing a structure of asymmetric loss on positive instances into the objective function of the global and local learning classifier. Then we develop a kernel-based algorithm to enable PUAL to obtain non-linear decision boundary. We show that, through experiments on both simulated and real-world datasets, PUAL can achieve satisfactory classification on trifurcate data.

stat.ML↗

arXiv2024

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

Despite their prevalence in deep-learning communities, over-parameterized models convey high demands of computational costs for proper training. This work studies the fine-grained, modular-level learning dynamics of over-parameterized models to attain a more efficient and fruitful training strategy. Empirical evidence reveals that when scaling down into network modules, such as heads in self-attention models, we can observe varying learning patterns implicitly associated with each module's trainability. To describe such modular-level learning capabilities, we introduce a novel concept dubbed modular neural tangent kernel (mNTK), and we demonstrate that the quality of a module's learning is tightly associated with its mNTK's principal eigenvalue $λ_{\max}$. A large $λ_{\max}$ indicates that the module learns features with better convergence, while those miniature ones may impact generalization negatively. Inspired by the discovery, we propose a novel training strategy termed Modular Adaptive Training (MAT) to update those modules with their $λ_{\max}$ exceeding a dynamic threshold selectively, concentrating the model on learning common features and ignoring those inconsistent ones. Unlike most existing training schemes with a complete BP cycle across all network modules, MAT can significantly save computations by its partially-updating strategy and can further improve performance. Experiments show that MAT nearly halves the computational cost of model training and outperforms the accuracy of baselines.

cs.LG↗

arXiv2024

Two-stage Information Spreading Evolution on The Control Role of Announcements

Modern social media networks have become an important platform for information competition among countries, regions, companies and other parties. This paper utilizes the research method of spread dynamics to investigate the influence of the control role of announcements in social networks on the spreading process. This paper distinguishes two spreading phases using the authentication intervention as a boundary: the unconfirmed spreading phase and the confirmed spreading phase. Based on the actual rules of spreading in online social networks, two kinds of verification results are defined: true information and false information. The Two-stage information spreading dynamics model is developed to analyze the changes in spreading effects due to different validation results. The impact of the intervention time on the overall spread process is analyzed by combining important control factors such as response cost and time-sensitivity. The validity of the model is verified by comparing the model simulation results with real cases and the adaptive capacity experiments. This work is analyzed and visualized from multiple perspectives, providing more quantitative results. The research content will provide a scientific basis for the intervention behavior of information management control by relevant departments or authorities.

cs.SI↗

arXiv2024

Long time numerical stability of implicit schemes for stochastic heat equations

This paper studies the long time stability of both stochastic heat equations on a bounded domain driven by a correlated noise and their approximations. It is popular for researchers to prove the intermittency of the solution which means that the moments of solution to stochastic heat equation usually grow exponentially to infinite and this hints that the solution to stochastic heat equation is generally not stable in long time. However, quite surprisingly in this paper we show that when the domain is bounded and when the noise is not singular in spatial variables, the system can be long time stable and we also prove that we can approximate the solution by its finite dimensional spectral approximation which is also long time stable. The idea is to use eigenfunction expansion of the Laplacian on bounded domain. We also present numerical experiments which are consistent with our theoretical results.

math.NA↗

arXiv2024

The Exact Risks of Reference Panel-based Regularized Estimators

Reference panel-based estimators have become widely used in genetic prediction of complex traits due to their ability to address data privacy concerns and reduce computational and communication costs. These estimators estimate the covariance matrix of predictors using an external reference panel, instead of relying solely on the original training data. In this paper, we investigate the performance of reference panel-based $L_1$ and $L_2$ regularized estimators within a unified framework based on approximate message passing (AMP). We uncover several key factors that influence the accuracy of reference panel-based estimators, including the sample sizes of the training data and reference panels, the signal-to-noise ratio, the underlying sparsity of the signal, and the covariance matrix among predictors. Our findings reveal that, even when the sample size of the reference panel matches that of the training data, reference panel-based estimators tend to exhibit lower accuracy compared to traditional regularized estimators. Furthermore, we observe that this performance gap widens as the amount of training data increases, highlighting the importance of constructing large-scale reference panels to mitigate this issue. To support our theoretical analysis, we develop a novel non-separable matrix AMP framework capable of handling the complexities introduced by a general covariance matrix and the additional randomness associated with a reference panel. We validate our theoretical results through extensive simulation studies and real data analyses using the UK Biobank database.

stat.ME↗

arXiv2023

What dictates soft clay-like Lithium superionic conductor formation from rigid-salts mixture

Soft clay-like Li-superionic conductors have been recently synthesized by mixing rigid-salts. Through computational and experimental analysis, we clarify how a soft clay-like material can be created from a mixture of rigid-salts. Using molecular dynamics simulations with a deep learning-based interatomic potential energy model, we uncover the microscopic features responsible for soft clay-formation from ionic solid mixtures. We find that salt mixtures capable of forming molecular solid units on anion exchange, along with the slow kinetics of such reactions, are key to soft-clay formation. Molecular solid units serve as sites for shear transformation zones, and their inherent softness enables plasticity at low stress. Extended X-ray absorption fine structure spectroscopy confirms the formation of molecular solid units. A general strategy for creating soft clay-like materials from ionic solid mixtures is formulated.

cond-mat.mtrl-sci↗

arXiv2022

Towards Certified Robustness of Distance Metric Learning

Metric learning aims to learn a distance metric such that semantically similar instances are pulled together while dissimilar instances are pushed away. Many existing methods consider maximizing or at least constraining a distance margin in the feature space that separates similar and dissimilar pairs of instances to guarantee their generalization ability. In this paper, we advocate imposing an adversarial margin in the input space so as to improve the generalization and robustness of metric learning algorithms. We first show that, the adversarial margin, defined as the distance between training instances and their closest adversarial examples in the input space, takes account of both the distance margin in the feature space and the correlation between the metric and triplet constraints. Next, to enhance robustness to instance perturbation, we propose to enlarge the adversarial margin through minimizing a derived novel loss function termed the perturbation loss. The proposed loss can be viewed as a data-dependent regularizer and easily plugged into any existing metric learning methods. Finally, we show that the enlarged margin is beneficial to the generalization ability by using the theoretical technique of algorithmic robustness. Experimental results on 16 datasets demonstrate the superiority of the proposed method over existing state-of-the-art methods in both discrimination accuracy and robustness against possible noise.

stat.ML↗

arXiv2022

Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments

Few-shot image classification is a challenging problem that aims to achieve the human level of recognition based only on a small number of training images. One main solution to few-shot image classification is deep metric learning. These methods, by classifying unseen samples according to their distances to few seen samples in an embedding space learned by powerful deep neural networks, can avoid overfitting to few training images in few-shot image classification and have achieved the state-of-the-art performance. In this paper, we provide an up-to-date review of deep metric learning methods for few-shot image classification from 2018 to 2022 and categorize them into three groups according to three stages of metric learning, namely learning feature embeddings, learning class representations, and learning distance measures. With this taxonomy, we identify the novelties of different methods and problems they face. We conclude this review with a discussion on current challenges and future trends in few-shot image classification.

cs.CV↗

arXiv2022

Estimating trans-ancestry genetic correlation with unbalanced data resources

The aim of this paper is to propose a novel estimation method of using genetic-predicted observations to estimate trans-ancestry genetic correlations, which describes how genetic architecture of complex traits varies among populations, in genome-wide association studies (GWAS). Our new estimator corrects for prediction errors caused by high-dimensional weak GWAS signals, while addressing the heterogeneity of GWAS data across ethnicities, such as linkage disequilibrium (LD) differences, which can lead to biased findings in homogeneity-agnostic analyses. Moreover, our estimator only requires one population to have a large GWAS sample size, and the second population can only have a much smaller number of participants (for example, hundreds). It is designed to specifically address the unbalanced data resources such that the GWAS sample size for European populations is usually larger than that of non-European ancestry groups. Extensive simulations and real data analyses of 30 complex traits in the UK Biobank study show that our method is capable of providing reliable estimates of a wide range of complex traits. Our results provide deep insights into the transferability of population-specific genetic findings.

stat.ME↗