arXiv subjects

Lei Liu

Publications and source records attributed to Lei Liu.

At least 181 records · Page 10Linked to original sources

arXiv2024

Time-Series Contrastive Learning against False Negatives and Class Imbalance

As an exemplary self-supervised approach for representation learning, time-series contrastive learning has exhibited remarkable advancements in contemporary research. While recent contrastive learning strategies have focused on how to construct appropriate positives and negatives, in this study, we conduct theoretical analysis and find they have overlooked the fundamental issues: false negatives and class imbalance inherent in the InfoNCE loss-based framework. Therefore, we introduce a straightforward modification grounded in the SimCLR framework, universally adaptable to models engaged in the instance discrimination task. By constructing instance graphs to facilitate interactive learning among instances, we emulate supervised contrastive learning via the multiple-instances discrimination task, mitigating the harmful impact of false negatives. Moreover, leveraging the graph structure and few-labeled data, we perform semi-supervised consistency classification and enhance the representative ability of minority classes. We compared our method with the most popular time-series contrastive learning methods on four real-world time-series datasets and demonstrated our significant advantages in overall performance.

cs.LG↗

arXiv2024

Large Language Models are Good Attackers: Efficient and Stealthy Textual Backdoor Attacks

With the burgeoning advancements in the field of natural language processing (NLP), the demand for training data has increased significantly. To save costs, it has become common for users and businesses to outsource the labor-intensive task of data collection to third-party entities. Unfortunately, recent research has unveiled the inherent risk associated with this practice, particularly in exposing NLP systems to potential backdoor attacks. Specifically, these attacks enable malicious control over the behavior of a trained model by poisoning a small portion of the training data. Unlike backdoor attacks in computer vision, textual backdoor attacks impose stringent requirements for attack stealthiness. However, existing attack methods meet significant trade-off between effectiveness and stealthiness, largely due to the high information entropy inherent in textual data. In this paper, we introduce the Efficient and Stealthy Textual backdoor attack method, EST-Bad, leveraging Large Language Models (LLMs). Our EST-Bad encompasses three core strategies: optimizing the inherent flaw of models as the trigger, stealthily injecting triggers with LLMs, and meticulously selecting the most impactful samples for backdoor injection. Through the integration of these techniques, EST-Bad demonstrates an efficient achievement of competitive attack performance while maintaining superior stealthiness compared to prior methods across various text classifier datasets.

cs.CL↗

arXiv2024

Service Placement and Trajectory Design for Heterogeneous Tasks in Multi-UAV Cooperative Computing Networks

In this paper, we consider deploying multiple Unmanned Aerial Vehicles (UAVs) to enhance the computation service of Mobile Edge Computing (MEC) through collaborative computation among UAVs. In particular, the tasks of different types and service requirements in MEC network are offloaded from one UAV to another. To pursue the goal of low-carbon edge computing, we study the problem of minimizing system energy consumption by jointly optimizing computation resource allocation, task scheduling, service placement, and UAV trajectories. Considering the inherent unpredictability associated with task generation and the dynamic nature of wireless fading channels, addressing this problem presents a significant challenge. To overcome this issue, we reformulate the complicated non-convex problem as a Markov decision process and propose a soft actor-critic-based trajectory optimization and resource allocation algorithm to implement a flexible learning strategy. Numerical results illustrate that within a multi-UAV-enabled MEC network, the proposed algorithm effectively reduces the system energy consumption in heterogeneous tasks and services scenarios compared to other baseline solutions.

cs.IT↗

arXiv2024

Learning-based Big Data Sharing Incentive in Mobile AIGC Networks

Rapid advancements in wireless communication have led to a dramatic upsurge in data volumes within mobile edge networks. These substantial data volumes offer opportunities for training Artificial Intelligence-Generated Content (AIGC) models to possess strong prediction and decision-making capabilities. AIGC represents an innovative approach that utilizes sophisticated generative AI algorithms to automatically generate diverse content based on user inputs. Leveraging mobile edge networks, mobile AIGC networks enable customized and real-time AIGC services for users by deploying AIGC models on edge devices. Nonetheless, several challenges hinder the provision of high-quality AIGC services, including issues related to the quality of sensing data for AIGC model training and the establishment of incentives for big data sharing from mobile devices to edge devices amidst information asymmetry. In this paper, we initially define a Quality of Data (QoD) metric based on the age of information to quantify the quality of sensing data. Subsequently, we propose a contract theoretic model aimed at motivating mobile devices for big data sharing. Furthermore, we employ a Proximal Policy Optimization (PPO) algorithm to determine the optimal contract. Numerical results demonstrate the efficacy and reliability of the proposed PPO-based contract model.

cs.NI↗

arXiv2024

Harnessing the power of longitudinal medical imaging for eye disease prognosis using Transformer-based sequence modeling

Deep learning has enabled breakthroughs in automated diagnosis from medical imaging, with many successful applications in ophthalmology. However, standard medical image classification approaches only assess disease presence at the time of acquisition, neglecting the common clinical setting of longitudinal imaging. For slow, progressive eye diseases like age-related macular degeneration (AMD) and primary open-angle glaucoma (POAG), patients undergo repeated imaging over time to track disease progression and forecasting the future risk of developing disease is critical to properly plan treatment. Our proposed Longitudinal Transformer for Survival Analysis (LTSA) enables dynamic disease prognosis from longitudinal medical imaging, modeling the time to disease from sequences of fundus photography images captured over long, irregular time periods. Using longitudinal imaging data from the Age-Related Eye Disease Study (AREDS) and Ocular Hypertension Treatment Study (OHTS), LTSA significantly outperformed a single-image baseline in 19/20 head-to-head comparisons on late AMD prognosis and 18/20 comparisons on POAG prognosis. A temporal attention analysis also suggested that, while the most recent image is typically the most influential, prior imaging still provides additional prognostic value.

cs.CV↗

arXiv2024

Distributed Memory Approximate Message Passing

Approximate message passing (AMP) algorithms are iterative methods for signal recovery in noisy linear systems. In some scenarios, AMP algorithms need to operate within a distributed network. To address this challenge, the distributed extensions of AMP (D-AMP, FD-AMP) and orthogonal/vector AMP (D-OAMP/D-VAMP) were proposed, but they still inherit the limitations of centralized algorithms. In this letter, we propose distributed memory AMP (D-MAMP) to overcome the IID matrix limitation of D-AMP/FD-AMP, as well as the high complexity and heavy communication cost of D-OAMP/D-VAMP. We introduce a matrix-by-vector variant of MAMP tailored for distributed computing. Leveraging this variant, D-MAMP enables each node to execute computations utilizing locally available observation vectors and transform matrices. Meanwhile, global summations of locally updated results are conducted through message interaction among nodes. For acyclic graphs, D-MAMP converges to the same mean square error performance as the centralized MAMP.

eess.SP↗

arXiv2024

X-Recon: Learning-based Patient-specific High-Resolution CT Reconstruction from Orthogonal X-Ray Images

Rapid and accurate diagnosis of pneumothorax, utilizing chest X-ray and computed tomography (CT), is crucial for assisted diagnosis. Chest X-ray is commonly used for initial localization of pneumothorax, while CT ensures accurate quantification. However, CT scans involve high radiation doses and can be costly. To achieve precise quantitative diagnosis while minimizing radiation exposure, we proposed X-Recon, a CT ultra-sparse reconstruction network based on ortho-lateral chest X-ray images. X-Recon integrates generative adversarial networks (GANs), including a generator with a multi-scale fusion rendering module and a discriminator enhanced by 3D coordinate convolutional layers, designed to facilitate CT reconstruction. To improve precision, a projective spatial transformer is utilized to incorporate multi-angle projection loss. Additionally, we proposed PTX-Seg, a zero-shot pneumothorax segmentation algorithm, combining image processing techniques with deep-learning models for the segmentation of air-accumulated regions and lung structures. Experiments on a large-scale dataset demonstrate its superiority over existing approaches. X-Recon achieved a significantly higher reconstruction resolution with a higher average spatial resolution and a lower average slice thickness. The reconstruction metrics achieved state-of-the-art performance in terms of several metrics including peak signal-to-noise ratio. The zero-shot segmentation algorithm, PTX-Seg, also demonstrated high segmentation precision for the air-accumulated region, the left lung, and the right lung. Moreover, the consistency analysis for the pneumothorax chest occupancy ratio between reconstructed CT and original CT obtained a high correlation coefficient. Code will be available at: https://github.com/wangyunpengbio/X-Recon

cs.CV↗

arXiv2024

First-principles study of structural and electronic properties of multiferroic oxide Mn3TeO6 under high pressure

Mn3TeO6 (MTO) has been experimentally found to adopt a P21/n structure under high pressure, which exhibits a significantly smaller band gap compared to the atmospheric R-3 phase. In this study, we systematically investigate the magnetism, structural phase transition and electronic properties of MTO under high pressure through first-principles calculations. Both R-3 and P21/n phases of MTO are antiferromagnetic at zero temperature. The R-3 phase transforms to the P21/n phase at 7.58 GPa, accompanied by a considerable volume collapse of about 6.47%. Employing the accurate method that combines DFT+U and G0W0, the calculated band gap of R-3 phase at zero pressure is very close to the experimental values, while that of the P21/n phase is significantly overestimated. The main reason for this difference is that the experimental study incorrectly used the Kubelka-Munk plot for the indirect band gap to obtain the band gap of the P21/n phase instead of the Kubelka-Munk plot for the direct band gap. Furthermore, our study reveals that the transition from the R-3 phase to the P21/n phase is accompanied by a slight reduction in the band gap.

cond-mat.mtrl-sci↗

arXiv2024

Interleaved Block-Sparse Transform

Low-complexity Bayes-optimal memory approximate message passing (MAMP) is an efficient signal estimation algorithm in compressed sensing and multicarrier modulation. However, achieving replica Bayes optimality with MAMP necessitates a large-scale right-unitarily invariant transformation, which is prohibitive in practical systems due to its high computational complexity and hardware costs. To solve this difficulty, this letter proposes a low-complexity interleaved block-sparse (IBS) transform, which consists of interleaved multiple low-dimensional transform matrices, aimed at reducing the hardware implementation scale while mitigating performance loss. Furthermore, an IBS cross-domain memory approximate message passing (IBS-CD-MAMP) estimator is developed, comprising a memory linear estimator in the IBS transform domain and a non-linear estimator in the source domain. Numerical results show that the IBS-CD-MAMP offers a reduced implementation scale and lower complexity with excellent performance in IBS-based compressed sensing and interleave frequency division multiplexing systems.

cs.IT↗

arXiv2024

Overflow-Avoiding Memory AMP

Approximate Message Passing (AMP) type algorithms are widely used for signal recovery in high-dimensional noisy linear systems. Recently, a principle called Memory AMP (MAMP) was proposed. Leveraging this principle, the gradient descent MAMP (GD-MAMP) algorithm was designed, inheriting the strengths of AMP and OAMP/VAMP. In this paper, we first provide an overflow-avoiding GD-MAMP (OA-GD-MAMP) to address the overflow problem that arises from some intermediate variables exceeding the range of floating point numbers. Second, we develop a complexity-reduced GD-MAMP (CR-GD-MAMP) to reduce the number of matrix-vector products per iteration by 1/3 (from 3 to 2) with little to no impact on the convergence speed.

cs.IT↗

arXiv2024

Report on Methods and Applications for Crafting 3D Humans

This paper presents an in-depth exploration of 3D human model and avatar generation technology, propelled by the rapid advancements in large-scale models and artificial intelligence. The paper reviews the comprehensive process of 3D human model generation, from scanning to rendering, and highlights the pivotal role these models play in entertainment, VR, AR, healthcare, and education. We underscore the significance of diffusion models in generating high-fidelity images and videos. It emphasizes the indispensable nature of 3D human models in enhancing user experiences and functionalities across various fields. Furthermore, this paper anticipates the potential of integrating large-scale models with deep learning to revolutionize 3D content generation, offering insights into the future prospects of the technology. It concludes by emphasizing the importance of continuous innovation in the field, suggesting that ongoing advancements will significantly expand the capabilities and applications of 3D human models and avatars.

cs.GR↗

arXiv2024

Towards Point Cloud Compression for Machine Perception: A Simple and Strong Baseline by Learning the Octree Depth Level Predictor

Point cloud compression has garnered significant interest in computer vision. However, existing algorithms primarily cater to human vision, while most point cloud data is utilized for machine vision tasks. To address this, we propose a point cloud compression framework that simultaneously handles both human and machine vision tasks. Our framework learns a scalable bit-stream, using only subsets for different machine vision tasks to save bit-rate, while employing the entire bit-stream for human vision tasks. Building on mainstream octree-based frameworks like VoxelContext-Net, OctAttention, and G-PCC, we introduce a new octree depth-level predictor. This predictor adaptively determines the optimal depth level for each octree constructed from a point cloud, controlling the bit-rate for machine vision tasks. For simpler tasks (\textit{e.g.}, classification) or objects/scenarios, we use fewer depth levels with fewer bits, saving bit-rate. Conversely, for more complex tasks (\textit{e.g}., segmentation) or objects/scenarios, we use deeper depth levels with more bits to enhance performance. Experimental results on various datasets (\textit{e.g}., ModelNet10, ModelNet40, ShapeNet, ScanNet, and KITTI) show that our point cloud compression approach improves performance for machine vision tasks without compromising human vision quality.

cs.CV↗

arXiv2024

Exploring Channel Estimation and Signal Detection for ODDM-based ISAC Systems

Inspired by providing reliable communications for high-mobility scenarios, in this letter, we investigate the channel estimation and signal detection in integrated sensing and communication~(ISAC) systems based on the orthogonal delay-Doppler multiplexing~(ODDM) modulation, which consists of a pulse-train that can achieve the orthogonality with respect to the resolution of the delay-Doppler~(DD) plane. To enhance the communication performance in the ODDM-based ISAC systems, we first propose a low-complexity approximation algorithm for channel estimation, which addresses the challenge of the high complexity from high resolution in the ODDM modulation, and achieves performance close to that of the maximum likelihood estimator scheme. Then, we employ the orthogonal approximate message-passing scheme to detect the symbols in the communication process based on the estimated channel information. Finally, simulation results show that the detection performance of ODDM is better than other multi-carrier modulation schemes. Specifically, the ODDM outperforms the orthogonal time frequency space scheme by 2.3 dB when the bit error ratio is $10^{-6}$.

eess.SP↗

arXiv2024

Adaptive and Parallel Split Federated Learning in Vehicular Edge Computing

Vehicular edge intelligence (VEI) is a promising paradigm for enabling future intelligent transportation systems by accommodating artificial intelligence (AI) at the vehicular edge computing (VEC) system. Federated learning (FL) stands as one of the fundamental technologies facilitating collaborative model training locally and aggregation, while safeguarding the privacy of vehicle data in VEI. However, traditional FL faces challenges in adapting to vehicle heterogeneity, training large models on resource-constrained vehicles, and remaining susceptible to model weight privacy leakage. Meanwhile, split learning (SL) is proposed as a promising collaborative learning framework which can mitigate the risk of model wights leakage, and release the training workload on vehicles. SL sequentially trains a model between a vehicle and an edge cloud (EC) by dividing the entire model into a vehicle-side model and an EC-side model at a given cut layer. In this work, we combine the advantages of SL and FL to develop an Adaptive Split Federated Learning scheme for Vehicular Edge Computing (ASFV). The ASFV scheme adaptively splits the model and parallelizes the training process, taking into account mobile vehicle selection and resource allocation. Our extensive simulations, conducted on non-independent and identically distributed data, demonstrate that the proposed ASFV solution significantly reduces training latency compared to existing benchmarks, while adapting to network dynamics and vehicles' mobility.

cs.LG↗

arXiv2024

How Can Large Language Models Understand Spatial-Temporal Data?

While Large Language Models (LLMs) dominate tasks like natural language processing and computer vision, harnessing their power for spatial-temporal forecasting remains challenging. The disparity between sequential text and complex spatial-temporal data hinders this application. To address this issue, this paper introduces STG-LLM, an innovative approach empowering LLMs for spatial-temporal forecasting. We tackle the data mismatch by proposing: 1) STG-Tokenizer: This spatial-temporal graph tokenizer transforms intricate graph data into concise tokens capturing both spatial and temporal relationships; 2) STG-Adapter: This minimalistic adapter, consisting of linear encoding and decoding layers, bridges the gap between tokenized data and LLM comprehension. By fine-tuning only a small set of parameters, it can effectively grasp the semantics of tokens generated by STG-Tokenizer, while preserving the original natural language understanding capabilities of LLMs. Extensive experiments on diverse spatial-temporal benchmark datasets show that STG-LLM successfully unlocks LLM potential for spatial-temporal forecasting. Remarkably, our approach achieves competitive performance on par with dedicated SOTA methods.

cs.LG↗

arXiv2024

Interleave Frequency Division Multiplexing

In this letter, we study interleave frequency division multiplexing (IFDM) for multicarrier modulation in static multipath and mobile time-varying channels, which outperforms orthogonal frequency division multiplexing (OFDM), orthogonal time frequency space (OTFS), and affine frequency division multiplexing (AFDM) by considering practical advanced detectors. The fundamental principle underlying existing modulation techniques is to establish sparse equivalent channel matrices in order to facilitate the design of low-complexity detection algorithms for signal recovery, making a trade-off between performance and implementation complexity. In contrast, the proposed IFDM establishes an equivalent fully dense and right-unitarily invariant channel matrix with the goal of achieving channel capacity, ensuring that the signals undergo sufficient statistical channel fading. Meanwhile, a low-complexity and replica maximum a posteriori (MAP)-optimal cross-domain memory approximate message passing (CD-MAMP) detector is proposed for IFDM by exploiting the sparsity of the time-domain channel and the unitary invariance in interleave-frequency-domain channel. Numerical results show that IFDM with extremely low-complexity CD-MAMP outperforms OFDM, OTFS, and AFDM with state-of-the-art orthogonal approximate message passing detectors, particularly at low velocities.

cs.IT↗

arXiv2024

Unveiling the effects of Cu doping on the H2 activation by CeO2 surface frustrated Lewis pairs

Recently, the solid-state frustrated Lewis pairs (FLPs) on the surface of CeO2 have been demonstrated to effectively catalyze the selective hydrogenation of unsaturated substrates, hence, the relationship between their intrinsic properties and H2 activation at the atomic scale has attracted great attention. In this work, the effects of Cu doping on the intrinsic FLPs properties for different facets of CeO2 is investigated by using density functional theory calculations, including the geometric parameters between Lewis acid-base centers, and the reactivity of Lewis acid-base towards H2 activation. The study demonstrates that introducing O vacancies on different crystal facets of CeO2 creates FLPs with the ability to efficiently cleavage hydrogen molecules. After the substitution of Ce with Cu, the inadequate electron availability of Cu to bond with O contributes to a reduction in the formation energy of O vacancies. Importantly, Cu exert an influence not only on the intrinsic properties of FLPs but also on the formation of new Ce-O and Cu-O FLPs. Considering the H2 activation, the doping of Cu results in an enhancement for the thermodynamics by decreasing the reaction energies, while a hinderance for the kinetics by increasing the energy barriers. Overall, with these theoretical investigations, we propose certain hints for the future experimental studies concerning the synthesis of Cu doped CeO2 catalysts for the H2 activation and hydrogenation reactions.

physics.chem-ph↗

arXiv2024

On the Sundman-Sperling estimates for the restricted one-center-two-body problem

In the past two decades, since the discovery of the figure-8 orbit by Chenciner and Montgomery, the variational method has became one of the most popular tools for constructing new solutions of the $N$-body problem and its extended problems. However, finding solutions to the restricted three-body problem, in particular, the two primaries form a collision Kepler system, remains a great difficulty. One of the major reasons is the essential differences between two-body collisions and three-body collisions. In this paper, we consider a similar three-body system with less difficulty, i.e. the restricted one-center-two-body system, that is involving a massless particle and a collision Kepler system with one body fixed. It is an intermediate system between the restricted three-body problem and the two-center problem. By an in-depth analysis of the asymptotic behavior of the minimizer, and an argument of critical and infliction points, we prove the Sundman-Sperling estimates near the three-body collision for the minimizers. With these estimates, we provide a class of collision-free solutions with prescribed boundary angles. Finally, under the extended collision Kepler system from Gordon, we constructed a family of periodic and quasi-periodic solutions.

math.DS↗