arXiv subjects

Kai Yang

Publications and source records attributed to Kai Yang.

At least 127 records · Page 7Linked to original sources

arXiv2025

Initial Model Incorporation for Deep Learning FWI: Pretraining or Denormalization?

Subsurface property neural network reparameterized full waveform inversion (FWI) has emerged as an effective unsupervised learning framework, which can invert stably with an inaccurate starting model. It updates the trainable neural network parameters instead of fine-tuning on the subsurface model directly. There are primarily two ways to embed the prior knowledge of the initial model into neural networks, that is, pretraining and denormalization. Pretraining first regulates the neural networks' parameters by fitting the initial velocity model; Denormalization directly adds the outputs of the network into the initial models without pretraining. In this letter, we systematically investigate the influence of the two ways of initial model incorporation for the neural network reparameterized FWI. We demonstrate that pretraining requires inverting the model perturbation based on a constant velocity value (mean) with a two-stage implementation. It leads to a complex workflow and inconsistency of objective functions in the two-stage process, causing the network parameters to become inactive and lose plasticity. Experimental results demonstrate that denormalization can simplify workflows, accelerate convergence, and enhance inversion accuracy compared with pretraining.

cs.LG↗

arXiv2025

Electrically tunable quantum interference of atomic spins on surfaces

Controlling quantum interference near avoided energy-level crossings is crucial for fast and reliable coherent manipulation in quantum information processing. However, achieving tunable quantum interference in atomically-precise engineered structures remains challenging. Here, we demonstrate electrical control of quantum interference using atomic spins on an insulating film in a scanning tunneling microscope. Using bias voltages applied across the tunnel junction, we modulate the atomically-confined magnetic interaction between the probe tip and surface atoms with a strong electric field, and drive the spin state rapidly through the energy-level anticrossing. This all-electrical manipulation allows us to achieve Landau-Zener-Stückelberg-Majorana (LZSM) interferometry on both single spins and pairs of interacting spins. The LZSM pattern exhibits multiphoton resonances, and its asymmetry suggests that the spin dynamics is influenced by spin-transfer torque of tunneling electrons. Multi-level LZSM spectra measured on coupled spins with tunable interactions show distinct interference patterns depending on their many-body energy landscapes. These results open new avenues for all-electrical quantum manipulation in spin-based quantum processors in the strongly driven regime.

cond-mat.mes-hall↗

arXiv2025

Fog Intelligence for Network Anomaly Detection

Anomalies are common in network system monitoring. When manifested as network threats to be mitigated, service outages to be prevented, and security risks to be ameliorated, detecting such anomalous network behaviors becomes of great importance. However, the growing scale and complexity of the mobile communication networks, as well as the ever-increasing amount and dimensionality of the network surveillance data, make it extremely difficult to monitor a mobile network and discover abnormal network behaviors. Recent advances in machine learning allow for obtaining near-optimal solutions to complicated decision-making problems with many sources of uncertainty that cannot be accurately characterized by traditional mathematical models. However, most machine learning algorithms are centralized, which renders them inapplicable to a large-scale distributed wireless networks with tens of millions of mobile devices. In this article, we present fog intelligence, a distributed machine learning architecture that enables intelligent wireless network management. It preserves the advantage of both edge processing and centralized cloud computing. In addition, the proposed architecture is scalable, privacy-preserving, and well suited for intelligent management of a distributed wireless network.

cs.NI↗

arXiv2025

MetaSTNet: Multimodal Meta-learning for Cellular Traffic Conformal Prediction

Network traffic prediction techniques have attracted much attention since they are valuable for network congestion control and user experience improvement. While existing prediction techniques can achieve favorable performance when there is sufficient training data, it remains a great challenge to make accurate predictions when only a small amount of training data is available. To tackle this problem, we propose a deep learning model, entitled MetaSTNet, based on a multimodal meta-learning framework. It is an end-to-end network architecture that trains the model in a simulator and transfers the meta-knowledge to a real-world environment, which can quickly adapt and obtain accurate predictions on a new task with only a small amount of real-world training data. In addition, we further employ cross conformal prediction to assess the calibrated prediction intervals. Extensive experiments have been conducted on real-world datasets to illustrate the efficiency and effectiveness of MetaSTNet.

cs.NI↗

arXiv2025

Cellular Traffic Prediction via Deep State Space Models with Attention Mechanism

Cellular traffic prediction is of great importance for operators to manage network resources and make decisions. Traffic is highly dynamic and influenced by many exogenous factors, which would lead to the degradation of traffic prediction accuracy. This paper proposes an end-to-end framework with two variants to explicitly characterize the spatiotemporal patterns of cellular traffic among neighboring cells. It uses convolutional neural networks with an attention mechanism to capture the spatial dynamics and Kalman filter for temporal modelling. Besides, we can fully exploit the auxiliary information such as social activities to improve prediction performance. We conduct extensive experiments on three real-world datasets. The results show that our proposed models outperform the state-of-the-art machine learning techniques in terms of prediction accuracy.

cs.LG↗

arXiv2025

Cellular Traffic Prediction via Byzantine-robust Asynchronous Federated Learning

Network traffic prediction plays a crucial role in intelligent network operation. Traditional prediction methods often rely on centralized training, necessitating the transfer of vast amounts of traffic data to a central server. This approach can lead to latency and privacy concerns. To address these issues, federated learning integrated with differential privacy has emerged as a solution to improve data privacy and model robustness in distributed settings. Nonetheless, existing federated learning protocols are vulnerable to Byzantine attacks, which may significantly compromise model robustness. Developing a robust and privacy-preserving prediction model in the presence of Byzantine clients remains a significant challenge. To this end, we propose an asynchronous differential federated learning framework based on distributionally robust optimization. The proposed framework utilizes multiple clients to train the prediction model collaboratively with local differential privacy. In addition, regularization techniques have been employed to further improve the Byzantine robustness of the models. We have conducted extensive experiments on three real-world datasets, and the results elucidate that our proposed distributed algorithm can achieve superior performance over existing methods.

cs.LG↗

arXiv2025

Exploration by Random Distribution Distillation

Exploration remains a critical challenge in online reinforcement learning, as an agent must effectively explore unknown environments to achieve high returns. Currently, the main exploration algorithms are primarily count-based methods and curiosity-based methods, with prediction-error methods being a prominent example. In this paper, we propose a novel method called \textbf{R}andom \textbf{D}istribution \textbf{D}istillation (RDD), which samples the output of a target network from a normal distribution. RDD facilitates a more extensive exploration by explicitly treating the difference between the prediction network and the target network as an intrinsic reward. Furthermore, by introducing randomness into the output of the target network for a given state and modeling it as a sample from a normal distribution, intrinsic rewards are bounded by two key components: a pseudo-count term ensuring proper exploration decay and a discrepancy term accounting for predictor convergence. We demonstrate that RDD effectively unifies both count-based and prediction-error approaches. It retains the advantages of prediction-error methods in high-dimensional spaces, while also implementing an intrinsic reward decay mode akin to the pseudo-count method. In the experimental section, RDD is compared with more advanced methods in a series of environments. Both theoretical analysis and experimental results confirm the effectiveness of our approach in improving online exploration for reinforcement learning tasks.

cs.LG↗

arXiv2025

Argus: Federated Non-convex Bilevel Learning over 6G Space-Air-Ground Integrated Network

The space-air-ground integrated network (SAGIN) has recently emerged as a core element in the 6G networks. However, traditional centralized and synchronous optimization algorithms are unsuitable for SAGIN due to infrastructureless and time-varying environments. This paper aims to develop a novel Asynchronous algorithm a.k.a. Argus for tackling non-convex and non-smooth decentralized federated bilevel learning over SAGIN. The proposed algorithm allows networked agents (e.g. autonomous aerial vehicles) to tackle bilevel learning problems in time-varying networks asynchronously, thereby averting stragglers from impeding the overall training speed. We provide a theoretical analysis of the iteration complexity, communication complexity, and computational complexity of Argus. Its effectiveness is further demonstrated through numerical experiments.

cs.LG↗

arXiv2025

Contextures: Representations from Contexts

Despite the empirical success of foundation models, we do not have a systematic characterization of the representations that these models learn. In this paper, we establish the contexture theory. It shows that a large class of representation learning methods can be characterized as learning from the association between the input and a context variable. Specifically, we show that many popular methods aim to approximate the top-d singular functions of the expectation operator induced by the context, in which case we say that the representation learns the contexture. We demonstrate the generality of the contexture theory by proving that representation learning within various learning paradigms -- supervised, self-supervised, and manifold learning -- can all be studied from such a perspective. We also prove that the representations that learn the contexture are optimal on those tasks that are compatible with the context. One important implication of the contexture theory is that once the model is large enough to approximate the top singular functions, further scaling up the model size yields diminishing returns. Therefore, scaling is not all we need, and further improvement requires better contexts. To this end, we study how to evaluate the usefulness of a context without knowing the downstream tasks. We propose a metric and show by experiments that it correlates well with the actual performance of the encoder on many real datasets.

cs.LG↗

arXiv2025

A New Multiple Correlation Coefficient without Specifying the Dependent Variable

Multiple correlation is a fundamental concept with broad applications. The classical multiple correlation coefficient is developed to assess how strongly a dependent variable is associated with a linear combination of independent variables. To compute this coefficient, the dependent variable must be chosen in advance. In many applications, however, it is difficult and even infeasible to specify the dependent variable, especially when some variables of interest are equally important. To overcome this difficulty, we propose a new coefficient of multiple correlation which (a) does not require the specification of the dependent variable, (b) has a simple formula and shares connections with the classical correlation coefficients, (c) consistently measures the linear correlation between continuous variables, which is 0 if and only if variables are uncorrelated and 1 if and only if one variable is a linear function of others, and (d) has an asymptotic distribution which can be used for hypothesis testing. We study the asymptotic behavior of the sample coefficient under mild regularity conditions. Given that the asymptotic bias of the sample coefficient is not negligible when the data dimension and the sample size are comparable, we propose a bias-corrected estimator that consistently performs well in such cases. Moreover, we develop an efficient strategy for making inferences on multiple correlation based on either the limiting distribution or the resampling methods and the stochastic approximation Monte Carlo algorithm, depending on whether the regularity assumptions are valid or not. Theoretical and numerical studies demonstrate that our coefficient provides a useful tool for evaluating multiple correlation in practice.

stat.ME↗

arXiv2025

RGB-Phase Speckle: Cross-Scene Stereo 3D Reconstruction via Wrapped Pre-Normalization

3D reconstruction garners increasing attention alongside the advancement of high-level image applications, where dense stereo matching (DSM) serves as a pivotal technique. Previous studies often rely on publicly available datasets for training, focusing on modifying network architectures or incorporating specialized modules to extract domain-invariant features and thus improve model robustness. In contrast, inspired by single-frame structured-light phase-shifting encoding, this study introduces RGB-Speckle, a cross-scene 3D reconstruction framework based on an active stereo camera system, designed to enhance robustness. Specifically, we propose a novel phase pre-normalization encoding-decoding method: first, we randomly perturb phase-shift maps and embed them into the three RGB channels to generate color speckle patterns; subsequently, the camera captures phase-encoded images modulated by objects as input to a stereo matching network. This technique effectively mitigates external interference and ensures consistent input data for RGB-Speckle, thereby bolstering cross-domain 3D reconstruction stability. To validate the proposed method, we conduct complex experiments: (1) construct a color speckle dataset for complex scenarios based on the proposed encoding scheme; (2) evaluate the impact of the phase pre-normalization encoding-decoding technique on 3D reconstruction accuracy; and (3) further investigate its robustness across diverse conditions. Experimental results demonstrate that the proposed RGB-Speckle model offers significant advantages in cross-domain and cross-scene 3D reconstruction tasks, enhancing model generalization and reinforcing robustness in challenging environments, thus providing a novel solution for robust 3D reconstruction research.

eess.IV↗

arXiv2025

High-Order and Energy-Stable Implicit-Explicit Relaxation Runge-Kutta Schemes for Gradient Flows

In this paper, we propose a class of high-order and energy-stable implicit-explicit relaxation Runge-Kutta (IMEX RRK) schemes for solving the phase-field gradient flow models. By incorporating the scalar auxiliary variable (SAV) method, the original equations are reformulated into equivalent forms, and the modified energy is introduced. Then, based on the reformulated equations, we propose a kind of IMEX RRK methods, which are rigorously proved to preserve the energy dissipation law and achieve high-order accuracy for both Allen-Cahn and Cahn-Hilliard equations. Numerical experiments are conducted to validate the theoretical results, including the accuracy of the approximate solution and the efficiency of the proposed scheme. Furthermore, the schemes are extended to multi-component gradient flows, with the vector-valued Allen-Cahn equations serving as a representative example.

math.NA↗

arXiv2025

LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL

Enhancing reasoning in Large Multimodal Models (LMMs) faces unique challenges from the complex interplay between visual perception and logical reasoning, particularly in compact 3B-parameter architectures where architectural constraints limit reasoning capacity and modality alignment. While rule-based reinforcement learning (RL) excels in text-only domains, its multimodal extension confronts two critical barriers: (1) data limitations due to ambiguous answers and scarce complex reasoning examples, and (2) degraded foundational reasoning induced by multimodal pretraining. To address these challenges, we propose \textbf{LMM-R1}, a two-stage framework adapting rule-based RL for multimodal reasoning through \textbf{Foundational Reasoning Enhancement (FRE)} followed by \textbf{Multimodal Generalization Training (MGT)}. The FRE stage first strengthens reasoning abilities using text-only data with rule-based RL, then the MGT stage generalizes these reasoning capabilities to multimodal domains. Experiments on Qwen2.5-VL-Instruct-3B demonstrate that LMM-R1 achieves 4.83\% and 4.5\% average improvements over baselines in multimodal and text-only benchmarks, respectively, with a 3.63\% gain in complex Football Game tasks. These results validate that text-based reasoning enhancement enables effective multimodal generalization, offering a data-efficient paradigm that bypasses costly high-quality multimodal training data.

cs.CL↗

arXiv2025

Multi-Source Static CT with Adaptive Fluence Modulation to Minimize Hallucinations in Generative Reconstructions

Multi-source static Computed Tomography (CT) systems have introduced novel opportunities for adaptive imaging techniques. This work presents an innovative method of fluence field modulation using spotlight collimators. These instruments block positive or negative fan angles of even and odd indexed sources, respectively. Spotlight collimators enable volume of interest imaging by increasing relative exposure for the overlapping views. To achieve high quality reconstructions from sparse-view low-dose data, we introduce a generative reconstruction algorithm called Langevin Posterior Sampling (LPS), which uses a score based diffusion prior and physics based likelihood model to sample a posterior random walk. We conduct simulation-based experiments of head CT imaging for stroke detection and we demonstrate that spotlight collimators can effectively reduce the standard deviation and worst-case scenario hallucinations in reconstructed images. Compared to uniform fluence, our approach shows a significant reduction in posterior standard deviation. This highlights the potential for spotlight collimators and generative reconstructions to improve image quality and diagnostic accuracy of multi-source static CT.

physics.med-ph↗

arXiv2025

An Algorithm Board in Neural Decoding

Understanding the mechanisms of neural encoding and decoding has always been a highly interesting research topic in fields such as neuroscience and cognitive intelligence. In prior studies, some researchers identified a symmetry in neural data decoded by unsupervised methods in motor scenarios and constructed a cognitive learning system based on this pattern (i.e., symmetry). Nevertheless, the distribution state of the data flow that significantly influences neural decoding positions still remains a mystery within the system, which further restricts the enhancement of the system's interpretability. Based on this, this paper mainly explores changes in the distribution state within the system from the machine learning and mathematical statistics perspectives. In the experiment, we assessed the correctness of this symmetry using various tools and indicators commonly utilized in mathematics and statistics. According to the experimental results, the normal distribution (or Gaussian distribution) plays a crucial role in the decoding of prediction positions within the system. Eventually, an algorithm board similar to the Galton board was built to serve as the mathematical foundation of the discovered symmetry.

cs.NE↗

arXiv2025

Affine Frequency Division Multiplexing: Extending OFDM for Scenario-Flexibility and Resilience

Next-generation wireless networks are conceived to provide reliable and high-data-rate communication services for diverse scenarios, such as vehicle-to-vehicle, unmanned aerial vehicles, and satellite networks. The severe Doppler spreads in the underlying time-varying channels induce destructive inter-carrier interference (ICI) in the extensively adopted orthogonal frequency division multiplexing (OFDM) waveform, leading to severe performance degradation. This calls for a new air interface design that can accommodate the severe delay-Doppler spreads in highly dynamic channels while possessing sufficient flexibility to cater to various applications. This article provides a comprehensive overview of a promising chirp-based waveform named affine frequency division multiplexing (AFDM). It is featured with two tunable parameters and achieves optimal diversity order in doubly dispersive channels (DDC). We study the fundamental principle of AFDM, illustrating its intrinsic suitability for DDC. Based on that, several potential applications of AFDM are explored. Furthermore, the major challenges and the corresponding solutions of AFDM are presented, followed by several future research directions. Finally, we draw some instructive conclusions about AFDM, hoping to provide useful inspiration for its development.

eess.SP↗

arXiv2025

ALMA observations of massive clouds in the central molecular zone: slim filaments tracing parsec-scale shocks

The central molecular zone (CMZ) of our Galaxy exhibits widespread emission from SiO and various complex organic molecules (COMs), yet the exact origin of such emission is uncertain. Here we report the discovery of a unique class of long ($>$0.5 pc) and narrow ($<$0.03 pc) filaments in the emission of SiO 5$-$4 and eight additional molecular lines, including several COMs, in our ALMA 1.3 mm spectral line observations toward two massive molecular clouds in the CMZ, which we name as slim filaments. However, these filaments are not detected in the 1.3 mm continuum at the 5$σ$ level. Their line-of-sight velocities are coherent and inconsistent with being outflows. The column densities and relative abundances of the detected molecules are statistically similar to those in protostellar outflows but different from those in dense cores within the same clouds. Turbulent pressure in these filaments dominates over self gravity and leads to hydrostatic inequilibrium, indicating that they are a different class of objects than the dense gas filaments in dynamical equilibrium ubiquitously found in nearby molecular clouds. We argue that these newly detected slim filaments are associated with parsec-scale shocks, likely arising from dynamic interactions between shock waves and molecular clouds. The dissipation of the slim filaments may replenish SiO and COMs in the interstellar medium and lead to their widespread emission in the CMZ.

astro-ph.GA↗

arXiv2025

Learning to Synthesize Compatible Fashion Items Using Semantic Alignment and Collocation Classification: An Outfit Generation Framework

The field of fashion compatibility learning has attracted great attention from both the academic and industrial communities in recent years. Many studies have been carried out for fashion compatibility prediction, collocated outfit recommendation, artificial intelligence (AI)-enabled compatible fashion design, and related topics. In particular, AI-enabled compatible fashion design can be used to synthesize compatible fashion items or outfits in order to improve the design experience for designers or the efficacy of recommendations for customers. However, previous generative models for collocated fashion synthesis have generally focused on the image-to-image translation between fashion items of upper and lower clothing. In this paper, we propose a novel outfit generation framework, i.e., OutfitGAN, with the aim of synthesizing a set of complementary items to compose an entire outfit, given one extant fashion item and reference masks of target synthesized items. OutfitGAN includes a semantic alignment module, which is responsible for characterizing the mapping correspondence between the existing fashion items and the synthesized ones, to improve the quality of the synthesized images, and a collocation classification module, which is used to improve the compatibility of a synthesized outfit. In order to evaluate the performance of our proposed models, we built a large-scale dataset consisting of 20,000 fashion outfits. Extensive experimental results on this dataset show that our OutfitGAN can synthesize photo-realistic outfits and outperform state-of-the-art methods in terms of similarity, authenticity and compatibility measurements.

cs.LG↗