arXiv subjects

Yan Zhang

Publications and source records attributed to Yan Zhang.

At least 415 records · Page 23Linked to original sources

arXiv2023

On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative Filtering

Collaborative filtering (CF) is an important research direction in recommender systems that aims to make recommendations given the information on user-item interactions. Graph CF has attracted more and more attention in recent years due to its effectiveness in leveraging high-order information in the user-item bipartite graph for better recommendations. Specifically, recent studies show the success of graph neural networks (GNN) for CF is attributed to its low-pass filtering effects. However, current researches lack a study of how different signal components contributes to recommendations, and how to design strategies to properly use them well. To this end, from the view of spectral transformation, we analyze the important factors that a graph filter should consider to achieve better performance. Based on the discoveries, we design JGCF, an efficient and effective method for CF based on Jacobi polynomial bases and frequency decomposition strategies. Extensive experiments on four widely used public datasets show the effectiveness and efficiency of the proposed methods, which brings at most 27.06% performance gain on Alibaba-iFashion. Besides, the experimental results also show that JGCF is better at handling sparse datasets, which shows potential in making recommendations for cold-start users.

cs.IR↗

arXiv2023

Pansharpening via Frequency-Aware Fusion Network with Explicit Similarity Constraints

The process of fusing a high spatial resolution (HR) panchromatic (PAN) image and a low spatial resolution (LR) multispectral (MS) image to obtain an HRMS image is known as pansharpening. With the development of convolutional neural networks, the performance of pansharpening methods has been improved, however, the blurry effects and the spectral distortion still exist in their fusion results due to the insufficiency in details learning and the frequency mismatch between MSand PAN. Therefore, the improvement of spatial details at the premise of reducing spectral distortion is still a challenge. In this paper, we propose a frequency-aware fusion network (FAFNet) together with a novel high-frequency feature similarity loss to address above mentioned problems. FAFNet is mainly composed of two kinds of blocks, where the frequency aware blocks aim to extract features in the frequency domain with the help of discrete wavelet transform (DWT) layers, and the frequency fusion blocks reconstruct and transform the features from frequency domain to spatial domain with the assistance of inverse DWT (IDWT) layers. Finally, the fusion results are obtained through a convolutional block. In order to learn the correspondence, we also propose a high-frequency feature similarity loss to constrain the HF features derived from PAN and MS branches, so that HF features of PAN can reasonably be used to supplement that of MS. Experimental results on three datasets at both reduced- and full-resolution demonstrate the superiority of the proposed method compared with several state-of-the-art pansharpening models.

eess.IV↗

arXiv2023

Decay dynamics of a giant atom in a structured bath with broken time-reversal symmetry

We study in this paper the decay dynamics of a two-level giant atom, which is coupled to a quasi-one-dimensional sawtooth lattice exposed to uniform synthetic magnetic fluxes. In the case where the two sublattices have a large detuning, the giant atom is effectively coupled to a single-band structured bath with flux-controlled energy band and time-reversal symmetry. This feature significantly affects the decay dynamics of the giant atom as well as the propagation of the emitted photon. In particular, the giant atom can exhibit chiral spontaneous emission and allow for nonreciprocal delayed light, which are however unattainable by coupling a small atom to this lattice. Giant atoms with different frequencies can be designed to emit photons towards different directions and with different group velocities. Our results pave the way towards engineering quantum networks and manipulating giant-atom interference effects.

quant-ph↗

arXiv2023

Unlocking Slot Attention by Changing Optimal Transport Costs

Slot attention is a powerful method for object-centric modeling in images and videos. However, its set-equivariance limits its ability to handle videos with a dynamic number of objects because it cannot break ties. To overcome this limitation, we first establish a connection between slot attention and optimal transport. Based on this new perspective we propose MESH (Minimize Entropy of Sinkhorn): a cross-attention module that combines the tiebreaking properties of unregularized optimal transport with the speed of regularized optimal transport. We evaluate slot attention using MESH on multiple object-centric learning benchmarks and find significant improvements over slot attention in every setting.

cs.LG↗

arXiv2023

Balancing Explainability-Accuracy of Complex Models

Explainability of AI models is an important topic that can have a significant impact in all domains and applications from autonomous driving to healthcare. The existing approaches to explainable AI (XAI) are mainly limited to simple machine learning algorithms, and the research regarding the explainability-accuracy tradeoff is still in its infancy especially when we are concerned about complex machine learning techniques like neural networks and deep learning (DL). In this work, we introduce a new approach for complex models based on the co-relation impact which enhances the explainability considerably while also ensuring the accuracy at a high level. We propose approaches for both scenarios of independent features and dependent features. In addition, we study the uncertainty associated with features and output. Furthermore, we provide an upper bound of the computation complexity of our proposed approach for the dependent features. The complexity bound depends on the order of logarithmic of the number of observations which provides a reliable result considering the higher dimension of dependent feature space with a smaller number of observations.

cs.LG↗

arXiv2023

Simulation Software of the JUNO Experiment

The Jiangmen Underground Neutrino Observatory (JUNO) is a multi-purpose experiment, under construction in southeast China, that is designed to determine the neutrino mass ordering and precisely measure neutrino oscillation parameters. Monte Carlo simulation plays an important role for JUNO detector design, detector commissioning, offline data processing, and physics processing. The JUNO experiment has the world's largest liquid scintillator detector instrumented with many thousands of PMTs. The broad energy range of interest, long lifetime, and the large scale present data processing challenges across all areas. This paper describes the JUNO simulation software, highlighting the challenges of JUNO simulation and solutions to meet these challenges, including such issues as support for time-correlated analysis, event mixing, event correlation and handling the simulation of many millions of optical photons.

hep-ex↗

arXiv2023

Prokaryotic genome editing based on the subtype I-B-Svi CRISPR-Cas system

Type I CRISPR-Cas systems are the most common among six types of CRISPR-Cas systems, however, non-self-targeting genome editing based on a single Cas3 of type I CRISPR-Cas systems has not been reported. Here, we present the subtype I-B-Svi CRISPR-Cas system (with three confirmed CRISPRs and a cas gene cluster) and genome editing based on this system found in Streptomyces virginiae IBL14. Importantly, like the animal-derived bacterial protein SpCas9 (1368 amino-acids), the single, compact, non-animal-derived bacterial protein SviCas3 (771 amino-acids) can also direct template-based microbial genome editing through the target cell's own homology-directed repair system, which breaks the view that the genome editing based on type I CRISPR-Cas systems requires a full Cascade. Notably, no off-target changes or indel-formation were detected in the analysis of potential off-target sites. This discovery broadens our understanding of the diversity of type I CRISPR-Cas systems and will facilitate new developments in genome editing tools.

q-bio.GN↗

arXiv2023

Giant-Atom Effects on Population and Entanglement Dynamics of Rydberg Atoms

Giant atoms are attracting interest as an emerging paradigm in the quantum optics of engineered waveguides. Here we propose to realize a synthetic giant atom working in the optical regime starting from a pair of interacting Rydberg atoms driven by a coherent field and coupled to a photonic crystal waveguide. Giant-atom effects can be observed as a phase-dependent decay of the double Rydberg excitation during the initial evolution of this atomic pair while (internal) atomic entanglement is exhibited at later times. Such an intriguing entanglement onset occurs in the presence of intrinsic atomic decay toward non-guided vacuum modes and is accompanied by an anti-bunching correlation of the emitted photons. Our findings may be relevant to quantum information processing, besides broadening the giant-atom waveguide physics with optically driven natural atoms.

quant-ph↗

arXiv2023

CrossSplit: Mitigating Label Noise Memorization through Data Splitting

We approach the problem of improving robustness of deep learning algorithms in the presence of label noise. Building upon existing label correction and co-teaching methods, we propose a novel training procedure to mitigate the memorization of noisy labels, called CrossSplit, which uses a pair of neural networks trained on two disjoint parts of the labelled dataset. CrossSplit combines two main ingredients: (i) Cross-split label correction. The idea is that, since the model trained on one part of the data cannot memorize example-label pairs from the other part, the training labels presented to each network can be smoothly adjusted by using the predictions of its peer network; (ii) Cross-split semi-supervised training. A network trained on one part of the data also uses the unlabeled inputs of the other part. Extensive experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet and mini-WebVision datasets demonstrate that our method can outperform the current state-of-the-art in a wide range of noise ratios.

cs.CV↗

arXiv2023

Finite Axiomatizability of Transitive Logics of Finite Depth and of Finite Weak Width

This paper presents a study of the finite axiomatizability of transitive logics of finite depth and finite weak width. We prove the finite axiomatizability of each transitive logic of finite depth and of weak width $1$ that is characterized by rooted transitive frames in which all antichains contain at most $n$ irreflexive points. As a negative result, we show that there are non-finitely-axiomatizable transitive logics of depth $n$ and of weak width $k$ for each $n\geqslant3$ and $k\geqslant2$.

math.LO↗

arXiv2023

Multimodal Feature Extraction and Fusion for Emotional Reaction Intensity Estimation and Expression Classification in Videos with Transformers

In this paper, we present our advanced solutions to the two sub-challenges of Affective Behavior Analysis in the wild (ABAW) 2023: the Emotional Reaction Intensity (ERI) Estimation Challenge and Expression (Expr) Classification Challenge. ABAW 2023 aims to tackle the challenge of affective behavior analysis in natural contexts, with the ultimate goal of creating intelligent machines and robots that possess the ability to comprehend human emotions, feelings, and behaviors. For the Expression Classification Challenge, we propose a streamlined approach that handles the challenges of classification effectively. However, our main contribution lies in our use of diverse models and tools to extract multimodal features such as audio and video cues from the Hume-Reaction dataset. By studying, analyzing, and combining these features, we significantly enhance the model's accuracy for sentiment prediction in a multimodal context. Furthermore, our method achieves outstanding results on the Emotional Reaction Intensity (ERI) Estimation Challenge, surpassing the baseline method by an impressive 84\% increase, as measured by the Pearson Coefficient, on the validation dataset.

cs.CV↗

arXiv2023

CoMP Transmission in Downlink NOMA-Based Cellular-Connected UAV Networks

In this paper, we study the integration between the coordinated multipoint (CoMP) transmission and the non-orthogonal multiple access (NOMA) in the downlink cellular-connected UAV networks with the coexistence of aerial users (AUs) and terrestrial users (TUs). Based on the comparison of the desired signal strength to the dominant interference strength, the AUs are classified into CoMP-AUs and Non-CoMP AUs, where the former receives transmissions from two cooperative BSs, and constructs two exclusive NOMA clusters with two TUs, respectively. A Non-CoMP AU constructs a NOMA cluster with a TU served by the same BS. By leveraging the tools from stochastic geometry, we propose a novel analytical framework to evaluate the performance of the CoMP-NOMA based cellular-connected UAV network in terms of coverage probability, and average ergodic rate. We reveal the superiority of the proposed CoMP-NOMA scheme by comparing with three benchmark schemes, and further quantify the impacts of key system parameters on the network performance. By harvesting the benefits of both CoMP and NOMA, we prove that the proposed framework can provide reliable connection for AUs by using CoMP and enhance the average ergodic rate through NOMA technique as well.

cs.NI↗

arXiv2023

Data-Efficient Image Quality Assessment with Attention-Panel Decoder

Blind Image Quality Assessment (BIQA) is a fundamental task in computer vision, which however remains unresolved due to the complex distortion conditions and diversified image contents. To confront this challenge, we in this paper propose a novel BIQA pipeline based on the Transformer architecture, which achieves an efficient quality-aware feature representation with much fewer data. More specifically, we consider the traditional fine-tuning in BIQA as an interpretation of the pre-trained model. In this way, we further introduce a Transformer decoder to refine the perceptual information of the CLS token from different perspectives. This enables our model to establish the quality-aware feature manifold efficiently while attaining a strong generalization capability. Meanwhile, inspired by the subjective evaluation behaviors of human, we introduce a novel attention panel mechanism, which improves the model performance and reduces the prediction uncertainty simultaneously. The proposed BIQA method maintains a lightweight design with only one layer of the decoder, yet extensive experiments on eight standard BIQA datasets (both synthetic and authentic) demonstrate its superior performance to the state-of-the-art BIQA methods, i.e., achieving the SRCC values of 0.875 (vs. 0.859 in LIVEC) and 0.980 (vs. 0.969 in LIVE).

cs.CV↗

arXiv2023

Local-to-Global Panorama Inpainting for Locale-Aware Indoor Lighting Prediction

Predicting panoramic indoor lighting from a single perspective image is a fundamental but highly ill-posed problem in computer vision and graphics. To achieve locale-aware and robust prediction, this problem can be decomposed into three sub-tasks: depth-based image warping, panorama inpainting and high-dynamic-range (HDR) reconstruction, among which the success of panorama inpainting plays a key role. Recent methods mostly rely on convolutional neural networks (CNNs) to fill the missing contents in the warped panorama. However, they usually achieve suboptimal performance since the missing contents occupy a very large portion in the panoramic space while CNNs are plagued by limited receptive fields. The spatially-varying distortion in the spherical signals further increases the difficulty for conventional CNNs. To address these issues, we propose a local-to-global strategy for large-scale panorama inpainting. In our method, a depth-guided local inpainting is first applied on the warped panorama to fill small but dense holes. Then, a transformer-based network, dubbed PanoTransformer, is designed to hallucinate reasonable global structures in the large holes. To avoid distortion, we further employ cubemap projection in our design of PanoTransformer. The high-quality panorama recovered at any locale helps us to capture spatially-varying indoor illumination with physically-plausible global structures and fine details.

cs.CV↗

arXiv2023

Efficient Gridless DoA Estimation Method of Non-uniform Linear Arrays with Applications in Automotive Radars

This paper focuses on the gridless direction-of-arrival (DoA) estimation for data acquired by non-uniform linear arrays (NLAs) in automotive applications. Atomic norm minimization (ANM) is a promising gridless sparse recovery algorithm under the Toeplitz model and solved by convex relaxation, thus it is only applicable to uniform linear arrays (ULAs) with array manifolds having a Vandermonde structure. In automotive applications, it is essential to apply the gridless DoA estimation to NLAs with arbitrary geometry with efficiency. In this paper, a fast ANM-based gridless DoA estimation algorithm for NLAs is proposed, which employs the array manifold separation technique and the accelerated proximal gradient (APG) technique, making it applicable to NLAs without losing of efficiency. Simulation and measurement experiments on automotive multiple-input multiple-output (MIMO) radars demonstrate the superiority of the proposed method.

eess.SP↗

arXiv2023

Robust Trajectory and Offloading for Energy-Efficient UAV Edge Computing in Industrial Internet of Things

Efficient data processing and computation are essential for the industrial Internet of things (IIoT) to empower various applications, which yet can be significantly bottlenecked by the limited energy capacity and computation capability of the IIoT nodes. In this paper, we employ an unmanned aerial vehicle (UAV) as an edge server to assist IIoT data processing, while considering the practical issue of UAV jittering. Specifically, we propose a joint design on trajectory and offloading strategies to minimize energy consumption due to local and edge computation, as well as data transmission. We particularly address the UAV jittering that induces Gaussian-distributed uncertainties associated with flying waypoints, resulting in probabilistic-form flying speed and data offloading constraints. We exploit the Bernstein-type inequality to reformulate the constraints in deterministic forms and decompose the energy minimization to solve for trajectory and offloading separately within an alternating optimization framework. The subproblems are then tackled with the successive convex approximation technique. Simulation results show that our proposal strictly guarantees robustness under uncertainties and effectively reduces energy consumption as compared with the baselines.

eess.SP↗

arXiv2023

Cooperative Data Collection with Multiple UAVs for Information Freshness in the Internet of Things

Maintaining the freshness of information in the Internet of Things (IoT) is a critical yet challenging problem. In this paper, we study cooperative data collection using multiple Unmanned Aerial Vehicles (UAVs) with the objective of minimizing the total average Age of Information (AoI). We consider various constraints of the UAVs, including kinematic, energy, trajectory, and collision avoidance, in order to optimize the data collection process. Specifically, each UAV, which has limited on-board energy, takes off from its initial location and flies over sensor nodes to collect update packets in cooperation with the other UAVs. The UAVs must land at their final destinations with non-negative residual energy after the specified time duration to ensure they have enough energy to complete their missions. It is crucial to design the trajectories of the UAVs and the transmission scheduling of the sensor nodes to enhance information freshness. We model the multi-UAV data collection problem as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP), as each UAV is unaware of the dynamics of the environment and can only observe a part of the sensors. To address the challenges of this problem, we propose a multi-agent Deep Reinforcement Learning (DRL)-based algorithm with centralized learning and decentralized execution. In addition to the reward shaping, we use action masks to filter out invalid actions and ensure that the constraints are met. Simulation results demonstrate that the proposed algorithms can significantly reduce the total average AoI compared to the baseline algorithms, and the use of the action mask method can improve the convergence speed of the proposed algorithm.

cs.IT↗

arXiv2023

Annotating Covert Hazardous Driving Scenarios Online: Utilizing Drivers' Electroencephalography (EEG) Signals

As autonomous driving systems prevail, it is becoming increasingly critical that the systems learn from databases containing fine-grained driving scenarios. Most databases currently available are human-annotated; they are expensive, time-consuming, and subject to behavioral biases. In this paper, we provide initial evidence supporting a novel technique utilizing drivers' electroencephalography (EEG) signals to implicitly label hazardous driving scenarios while passively viewing recordings of real-road driving, thus sparing the need for manual annotation and avoiding human annotators' behavioral biases during explicit report. We conducted an EEG experiment using real-life and animated recordings of driving scenarios and asked participants to report danger explicitly whenever necessary. Behavioral results showed the participants tended to report danger only when overt hazards (e.g., a vehicle or a pedestrian appearing unexpectedly from behind an occlusion) were in view. By contrast, their EEG signals were enhanced at the sight of both an overt hazard and a covert hazard (e.g., an occlusion signalling possible appearance of a vehicle or a pedestrian from behind). Thus, EEG signals were more sensitive to driving hazards than explicit reports. Further, the Time-Series AI (TSAI) successfully classified EEG signals corresponding to overt and covert hazards. We discuss future steps necessary to materialize the technique in real life.

cs.HC↗