arXiv subjects

Lin Wang

Publications and source records attributed to Lin Wang.

At least 289 records · Page 16Linked to original sources

arXiv2023

FedRec+: Enhancing Privacy and Addressing Heterogeneity in Federated Recommendation Systems

Preserving privacy and reducing communication costs for edge users pose significant challenges in recommendation systems. Although federated learning has proven effective in protecting privacy by avoiding data exchange between clients and servers, it has been shown that the server can infer user ratings based on updated non-zero gradients obtained from two consecutive rounds of user-uploaded gradients. Moreover, federated recommendation systems (FRS) face the challenge of heterogeneity, leading to decreased recommendation performance. In this paper, we propose FedRec+, an ensemble framework for FRS that enhances privacy while addressing the heterogeneity challenge. FedRec+ employs optimal subset selection based on feature similarity to generate near-optimal virtual ratings for pseudo items, utilizing only the user's local information. This approach reduces noise without incurring additional communication costs. Furthermore, we utilize the Wasserstein distance to estimate the heterogeneity and contribution of each client, and derive optimal aggregation weights by solving a defined optimization problem. Experimental results demonstrate the state-of-the-art performance of FedRec+ across various reference datasets.

cs.LG↗

arXiv2023

DELTA: Diverse Client Sampling for Fasting Federated Learning

Partial client participation has been widely adopted in Federated Learning (FL) to reduce the communication burden efficiently. However, an inadequate client sampling scheme can lead to the selection of unrepresentative subsets, resulting in significant variance in model updates and slowed convergence. Existing sampling methods are either biased or can be further optimized for faster convergence.In this paper, we present DELTA, an unbiased sampling scheme designed to alleviate these issues. DELTA characterizes the effects of client diversity and local variance, and samples representative clients with valuable information for global model updates. In addition, DELTA is a proven optimal unbiased sampling scheme that minimizes variance caused by partial client participation and outperforms other unbiased sampling schemes in terms of convergence. Furthermore, to address full-client gradient dependence,we provide a practical version of DELTA depending on the available clients' information, and also analyze its convergence. Our results are validated through experiments on both synthetic and real-world datasets.

cs.LG↗

arXiv2023

NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding

The application of deep learning to nursing procedure activity understanding has the potential to greatly enhance the quality and safety of nurse-patient interactions. By utilizing the technique, we can facilitate training and education, improve quality control, and enable operational compliance monitoring. However, the development of automatic recognition systems in this field is currently hindered by the scarcity of appropriately labeled datasets. The existing video datasets pose several limitations: 1) these datasets are small-scale in size to support comprehensive investigations of nursing activity; 2) they primarily focus on single procedures, lacking expert-level annotations for various nursing procedures and action steps; and 3) they lack temporally localized annotations, which prevents the effective localization of targeted actions within longer video sequences. To mitigate these limitations, we propose NurViD, a large video dataset with expert-level annotation for nursing procedure activity understanding. NurViD consists of over 1.5k videos totaling 144 hours, making it approximately four times longer than the existing largest nursing activity datasets. Notably, it encompasses 51 distinct nursing procedures and 177 action steps, providing a much more comprehensive coverage compared to existing datasets that primarily focus on limited procedures. To evaluate the efficacy of current deep learning methods on nursing activity understanding, we establish three benchmarks on NurViD: procedure recognition on untrimmed videos, procedure and action recognition on trimmed videos, and action detection. Our benchmark and code will be available at \url{https://github.com/minghu0830/NurViD-benchmark}.

cs.CV↗

arXiv2023

DPCIPI: A pre-trained deep learning model for predicting cross-immunity between drifted strains of Influenza A/H3N2

Predicting cross-immunity between viral strains is vital for public health surveillance and vaccine development. Traditional neural network methods, such as BiLSTM, could be ineffective due to the lack of lab data for model training and the overshadowing of crucial features within sequence concatenation. The current work proposes a less data-consuming model incorporating a pre-trained gene sequence model and a mutual information inference operator. Our methodology utilizes gene alignment and deduplication algorithms to preprocess gene sequences, enhancing the model's capacity to discern and focus on distinctions among input gene pairs. The model, i.e., DNA Pretrained Cross-Immunity Protection Inference model (DPCIPI), outperforms state-of-the-art (SOTA) models in predicting hemagglutination inhibition titer from influenza viral gene sequences only. Improvement in binary cross-immunity prediction is 1.58% in F1, 2.34% in precision, 1.57% in recall, and 1.57% in Accuracy. For multilevel cross-immunity improvements, the improvement is 2.12% in F1, 3.50% in precision, 2.19% in recall, and 2.19% in Accuracy. Our study highlights the potential of pre-trained gene models in revolutionizing gene sequence-related prediction tasks. With more gene sequence data being harnessed and larger models trained, we foresee a significant impact of pre-trained models on clinical and public health applications.

cs.CE↗

arXiv2023

Group-Orthogonal Subsampling for Hierarchical Data Based on Linear Mixed Models

Hierarchical data analysis is crucial in various fields for making discoveries. The linear mixed model is often used for training hierarchical data, but its parameter estimation is computationally expensive, especially with big data. Subsampling techniques have been developed to address this challenge. However, most existing subsampling methods assume homogeneous data and do not consider the possible heterogeneity in hierarchical data. To address this limitation, we develop a new approach called group-orthogonal subsampling (GOSS) for selecting informative subsets of hierarchical data that may exhibit heterogeneity. GOSS selects subdata with balanced data size among groups and combinatorial orthogonality within each group, resulting in subdata that are $D$- and $A$-optimal for building linear mixed models. Estimators of parameters trained on GOSS subdata are consistent and asymptotically normal. GOSS is shown to be numerically appealing via simulations and a real data application. Theoretical proofs, R codes, and supplementary numerical results are accessible online as Supplementary Materials.

stat.ME↗

arXiv2023

Berry Curvature and Bulk-Boundary Correspondence from Transport Measurement for Photonic Chern Bands

Berry curvature is a fundamental element to characterize topological quantum physics, while a full measurement of Berry curvature in momentum space was not reported for topological states. Here we achieve two-dimensional Berry curvature reconstruction in a photonic quantum anomalous Hall system via Hall transport measurement of a momentum-resolved wave packet. Integrating measured Berry curvature over the two-dimensional Brillouin zone, we obtain Chern numbers corresponding to -1 and 0. Further, we identify bulk-boundary correspondence by measuring topology-linked chiral edge states at the boundary. The full topological characterization of photonic Chern bands from Berry curvature, Chern number, and edge transport measurements enables our photonic system to serve as a versatile platform for further in-depth study of novel topological physics.

quant-ph↗

arXiv2023

Distilling Efficient Vision Transformers from CNNs for Semantic Segmentation

In this paper, we tackle a new problem: how to transfer knowledge from the pre-trained cumbersome yet well-performed CNN-based model to learn a compact Vision Transformer (ViT)-based model while maintaining its learning capacity? Due to the completely different characteristics of ViT and CNN and the long-existing capacity gap between teacher and student models in Knowledge Distillation (KD), directly transferring the cross-model knowledge is non-trivial. To this end, we subtly leverage the visual and linguistic-compatible feature character of ViT (i.e., student), and its capacity gap with the CNN (i.e., teacher) and propose a novel CNN-to-ViT KD framework, dubbed C2VKD. Importantly, as the teacher's features are heterogeneous to those of the student, we first propose a novel visual-linguistic feature distillation (VLFD) module that explores efficient KD among the aligned visual and linguistic-compatible representations. Moreover, due to the large capacity gap between the teacher and student and the inevitable prediction errors of the teacher, we then propose a pixel-wise decoupled distillation (PDD) module to supervise the student under the combination of labels and teacher's predictions from the decoupled target and non-target classes. Experiments on three semantic segmentation benchmark datasets consistently show that the increment of mIoU of our method is over 200% of the SoTA KD methods

cs.CV↗

arXiv2023

Integrated Sensing and Communication enabled Doppler Frequency Shift Estimation and Compensation

Despite the millimeter wave technology fulfills the low-latency and high data transmission, it will cause severe Doppler Frequency Shift (DFS) for high-speed vehicular network, which tremendously damages the communication performance. In this paper, we propose an Integrated Sensing and Communication (ISAC) enabled DFS estimation and compensation algorithm. Firstly, the DFS is coarsely estimated and compensated using radar detection. Then, the designed preamble sequence is used to accurately estimate and compensate DFS. In addition, an adaptive DFS estimator is designed to reduce the computational complexity. Compared with the traditional DFS estimation algorithm, the improvement of the proposed algorithm is verified in bit error rate and mean square error performance by simulation results.

eess.SP↗

arXiv2023

Waveform Design for MIMO-OFDM Integrated Sensing and Communication System: An Information Theoretical Approach

Integrated sensing and communication (ISAC) is regarded as the enabling technology in the future 5th-Generation-Advanced (5G-A) and 6th-Generation (6G) mobile communication system. ISAC waveform design is critical in ISAC system. However, the difference of the performance metrics between sensing and communication brings challenges for the ISAC waveform design. This paper applies the unified performance metrics in information theory, namely mutual information (MI), to measure the communication and sensing performance in multicarrier ISAC system. In multi-input multi-output orthogonal frequency division multiplexing (MIMO-OFDM) ISAC system, we first derive the sensing and communication MI with subcarrier correlation and spatial correlation. Then, we propose optimal waveform designs for maximizing the sensing MI, communication MI and the weighted sum of sensing and communication MI, respectively. The optimization results are validated by Monte Carlo simulations. Our work provides effective closed-form expressions for waveform design, enabling the realization of MIMO-OFDM ISAC system with balanced performance in communication and sensing.

cs.IT↗

arXiv2023

Variantional autoencoder with decremental information bottleneck for disentanglement

One major challenge of disentanglement learning with variational autoencoders is the trade-off between disentanglement and reconstruction fidelity. Previous studies, which increase the information bottleneck during training, tend to lose the constraint of disentanglement, leading to the information diffusion problem. In this paper, we present a novel framework for disentangled representation learning, DeVAE, which utilizes hierarchical latent spaces with decreasing information bottlenecks across these spaces. The key innovation of our approach lies in connecting the hierarchical latent spaces through disentanglement-invariant transformations, allowing the sharing of disentanglement properties among spaces while maintaining an acceptable level of reconstruction performance. We demonstrate the effectiveness of DeVAE in achieving a balance between disentanglement and reconstruction through a series of experiments and ablation studies on dSprites and Shapes3D datasets. Code is available at https://github.com/erow/disentanglement_lib/tree/pytorch#devae.

cs.LG↗

arXiv2023

Towards Novel Class Discovery: A Study in Novel Skin Lesions Clustering

Existing deep learning models have achieved promising performance in recognizing skin diseases from dermoscopic images. However, these models can only recognize samples from predefined categories, when they are deployed in the clinic, data from new unknown categories are constantly emerging. Therefore, it is crucial to automatically discover and identify new semantic categories from new data. In this paper, we propose a new novel class discovery framework for automatically discovering new semantic classes from dermoscopy image datasets based on the knowledge of known classes. Specifically, we first use contrastive learning to learn a robust and unbiased feature representation based on all data from known and unknown categories. We then propose an uncertainty-aware multi-view cross pseudo-supervision strategy, which is trained jointly on all categories of data using pseudo labels generated by a self-labeling strategy. Finally, we further refine the pseudo label by aggregating neighborhood information through local sample similarity to improve the clustering performance of the model for unknown categories. We conducted extensive experiments on the dermatology dataset ISIC 2019, and the experimental results show that our approach can effectively leverage knowledge from known categories to discover new semantic categories. We also further validated the effectiveness of the different modules through extensive ablation experiments. Our code will be released soon.

cs.CV↗

arXiv2023

N-functionalized Ti2C MXene as high-performance adsorbent for strontium ions: a first-principles study

Radionuclides sequestration through adsorption technology has attracted much attention due to its unique characters such as high removal efficiency, low cost, and ease of operation. In this work, the interaction mechanism of N-functionalized Ti2C MXene (Ti2CN2) as a potential adsorbent for the removal of strontium ions is investigated by using first principles method. Our results show that surface N atoms are connected to Sr ions by a robust chemical N-Sr bond, which provides a stronger interaction and greater capacity (1.291g g-1) of Sr ion adsorption on Ti2CN2 than Ti2C with other surficial groups O, F and OH. Furthermore, the thermal stability of the adsorption structure of Sr on Ti2CN2 with full layer coverage at room temperature is verified by using ab initio molecular dynamics simulations. Our results are expected to provide a new perspective for the design of MXene materials as adsorbent for radionuclide.

cond-mat.mtrl-sci↗

arXiv2023

OmniZoomer: Learning to Move and Zoom in on Sphere at High-Resolution

Omnidirectional images (ODIs) have become increasingly popular, as their large field-of-view (FoV) can offer viewers the chance to freely choose the view directions in immersive environments such as virtual reality. The Möbius transformation is typically employed to further provide the opportunity for movement and zoom on ODIs, but applying it to the image level often results in blurry effect and aliasing problem. In this paper, we propose a novel deep learning-based approach, called \textbf{OmniZoomer}, to incorporate the Möbius transformation into the network for movement and zoom on ODIs. By learning various transformed feature maps under different conditions, the network is enhanced to handle the increasing edge curvatures, which alleviates the blurry effect. Moreover, to address the aliasing problem, we propose two key components. Firstly, to compensate for the lack of pixels for describing curves, we enhance the feature maps in the high-resolution (HR) space and calculate the transformed index map with a spatial index generation module. Secondly, considering that ODIs are inherently represented in the spherical space, we propose a spherical resampling module that combines the index map and HR feature maps to transform the feature maps for better spherical correlation. The transformed feature maps are decoded to output a zoomed ODI. Experiments show that our method can produce HR and high-quality ODIs with the flexibility to move and zoom in to the object of interest. Project page is available at http://vlislab22.github.io/OmniZoomer/.

cs.CV↗

arXiv2023

Complex unit lattice cell for low-emittance storage ring light source

To achieve the true diffraction-limited emittance of a storage ring light source, such as ~10 pm.rad for medium-energy electron beams, within a limited circumference, it is generally necessary to increase the number of bending magnets in a multi-bend achromat (MBA) lattice, as in the future upgrade plan of MAX IV with a 19BA replacing the current 7BA. However, this comes with extremely strong quadrupole and sextupole magnets and very limited space. The former can result in very small vacuum chambers, increasing the coupling impedance and thus enhancing the beam instabilities, and the latter can pose significant challenges in accommodating the necessary diagnostics and vacuum components. Inspired by the hybrid MBA lattice concept, in this paper we propose a new unit lattice concept called the complex unit lattice cell, which can reduce the magnet strengths and also save space. The complex unit cell is numerically studied using a simplified model. Then as an example, a 17BA lattice based on the complex unit cell concept is designed for a 3 GeV storage ring light source with a circumference of 537.6 m, which has a natural emittance of 19.3 pm.rad. This 17BA lattice is also compared with the 17BA lattice designed with conventional unit cells to showcase the benefits of the complex unit cell concept. This 17BA lattice also suggests a new type of MBA lattice, which we call the MBA lattice with semi-distributed chromatic correction.

physics.acc-ph↗

arXiv2023

Routing for Intermittently-Powered Sensing Systems

Recently, intermittent computing (IC) has received tremendous attention due to its high potential in perpetual sensing for Internet-of-Things (IoT). By harvesting ambient energy, battery-free devices can perform sensing intermittently without maintenance, thus significantly improving IoT sustainability. To build a practical intermittently-powered sensing system, efficient routing across battery-free devices for data delivery is essential. However, the intermittency of these devices brings new challenges, rendering existing routing protocols inapplicable. In this paper, we propose RICS, the first-of-its-kind routing scheme tailored for intermittently-powered sensing systems. RICS features two major designs, with the goal of achieving low-latency data delivery on a network built with battery-free devices. First, RICS incorporates a fast topology construction protocol for each IC node to establish a path towards the sink node with the least hop count. Second, RICS employs a low-latency message forwarding protocol, which incorporates an efficient synchronization mechanism and a novel technique called pendulum-sync to avoid the time-consuming repeated node synchronization. Our evaluation based on an implementation in OMNeT++ and comprehensive experiments with varying system settings show that RICS can achieve orders of magnitude latency reduction in data delivery compared with the baselines.

cs.NI↗

arXiv2023

STS-GAN: Can We Synthesize Solid Texture with High Fidelity from Arbitrary 2D Exemplar?

Solid texture synthesis (STS), an effective way to extend a 2D exemplar to a 3D solid volume, exhibits advantages in computational photography. However, existing methods generally fail to accurately learn arbitrary textures, which may result in the failure to synthesize solid textures with high fidelity. In this paper, we propose a novel generative adversarial nets-based framework (STS-GAN) to extend the given 2D exemplar to arbitrary 3D solid textures. In STS-GAN, multi-scale 2D texture discriminators evaluate the similarity between the given 2D exemplar and slices from the generated 3D texture, promoting the 3D texture generator synthesizing realistic solid textures. Finally, experiments demonstrate that the proposed method can generate high-fidelity solid textures with similar visual characteristics to the 2D exemplar.

cs.CV↗

arXiv2023

Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples

Deep Neural Networks (DNNs) for 3D point cloud recognition are vulnerable to adversarial examples, threatening their practical deployment. Despite the many research endeavors have been made to tackle this issue in recent years, the diversity of adversarial examples on 3D point clouds makes them more challenging to defend against than those on 2D images. For examples, attackers can generate adversarial examples by adding, shifting, or removing points. Consequently, existing defense strategies are hard to counter unseen point cloud adversarial examples. In this paper, we first establish a comprehensive, and rigorous point cloud adversarial robustness benchmark to evaluate adversarial robustness, which can provide a detailed understanding of the effects of the defense and attack methods. We then collect existing defense tricks in point cloud adversarial defenses and then perform extensive and systematic experiments to identify an effective combination of these tricks. Furthermore, we propose a hybrid training augmentation methods that consider various types of point cloud adversarial examples to adversarial training, significantly improving the adversarial robustness. By combining these tricks, we construct a more robust defense framework achieving an average accuracy of 83.45\% against various attacks, demonstrating its capability to enabling robust learners. Our codebase are open-sourced on: \url{https://github.com/qiufan319/benchmark_pc_attack.git}.

cs.CV↗

arXiv2023

Look at the Neighbor: Distortion-aware Unsupervised Domain Adaptation for Panoramic Semantic Segmentation

Endeavors have been recently made to transfer knowledge from the labeled pinhole image domain to the unlabeled panoramic image domain via Unsupervised Domain Adaptation (UDA). The aim is to tackle the domain gaps caused by the style disparities and distortion problem from the non-uniformly distributed pixels of equirectangular projection (ERP). Previous works typically focus on transferring knowledge based on geometric priors with specially designed multi-branch network architectures. As a result, considerable computational costs are induced, and meanwhile, their generalization abilities are profoundly hindered by the variation of distortion among pixels. In this paper, we find that the pixels' neighborhood regions of the ERP indeed introduce less distortion. Intuitively, we propose a novel UDA framework that can effectively address the distortion problems for panoramic semantic segmentation. In comparison, our method is simpler, easier to implement, and more computationally efficient. Specifically, we propose distortion-aware attention (DA) capturing the neighboring pixel distribution without using any geometric constraints. Moreover, we propose a class-wise feature aggregation (CFA) module to iteratively update the feature representations with a memory bank. As such, the feature similarity between two domains can be consistently optimized. Extensive experiments show that our method achieves new state-of-the-art performance while remarkably reducing 80% parameters.

cs.CV↗