arXiv subjects

Yang Wang

Publications and source records attributed to Yang Wang.

At least 469 records · Page 26Linked to original sources

arXiv2024

Spatio-Temporal Contrastive Learning Enhanced GNNs for Session-based Recommendation

Session-based recommendation (SBR) systems aim to utilize the user's short-term behavior sequence to predict the next item without the detailed user profile. Most recent works try to model the user preference by treating the sessions as between-item transition graphs and utilize various graph neural networks (GNNs) to encode the representations of pair-wise relations among items and their neighbors. Some of the existing GNN-based models mainly focus on aggregating information from the view of spatial graph structure, which ignores the temporal relations within neighbors of an item during message passing and the information loss results in a sub-optimal problem. Other works embrace this challenge by incorporating additional temporal information but lack sufficient interaction between the spatial and temporal patterns. To address this issue, inspired by the uniformity and alignment properties of contrastive learning techniques, we propose a novel framework called Session-based Recommendation with Spatio-Temporal Contrastive Learning Enhanced GNNs (RESTC). The idea is to supplement the GNN-based main supervised recommendation task with the temporal representation via an auxiliary cross-view contrastive learning mechanism. Furthermore, a novel global collaborative filtering graph (CFG) embedding is leveraged to enhance the spatial view in the main task. Extensive experiments demonstrate the significant performance of RESTC compared with the state-of-the-art baselines e.g., with an improvement as much as 27.08% gain on HR@20 and 20.10% gain on MRR@20.

cs.IR↗

arXiv2024

Modeling Spatio-temporal Dynamical Systems with Neural Discrete Learning and Levels-of-Experts

In this paper, we address the issue of modeling and estimating changes in the state of the spatio-temporal dynamical systems based on a sequence of observations like video frames. Traditional numerical simulation systems depend largely on the initial settings and correctness of the constructed partial differential equations (PDEs). Despite recent efforts yielding significant success in discovering data-driven PDEs with neural networks, the limitations posed by singular scenarios and the absence of local insights prevent them from performing effectively in a broader real-world context. To this end, this paper propose the universal expert module -- that is, optical flow estimation component, to capture the evolution laws of general physical processes in a data-driven fashion. To enhance local insight, we painstakingly design a finer-grained physical pipeline, since local characteristics may be influenced by various internal contextual information, which may contradict the macroscopic properties of the whole system. Further, we harness currently popular neural discrete learning to unveil the underlying important features in its latent space, this process better injects interpretability, which can help us obtain a powerful prior over these discrete random variables. We conduct extensive experiments and ablations to demonstrate that the proposed framework achieves large performance margins, compared with the existing SOTA baselines.

cs.LG↗

arXiv2024

Phoneme-Based Proactive Anti-Eavesdropping with Controlled Recording Privilege

The widespread smart devices raise people's concerns of being eavesdropped on. To enhance voice privacy, recent studies exploit the nonlinearity in microphone to jam audio recorders with inaudible ultrasound. However, existing solutions solely rely on energetic masking. Their simple-form noise leads to several problems, such as high energy requirements and being easily removed by speech enhancement techniques. Besides, most of these solutions do not support authorized recording, which restricts their usage scenarios. In this paper, we design an efficient yet robust system that can jam microphones while preserving authorized recording. Specifically, we propose a novel phoneme-based noise with the idea of informational masking, which can distract both machines and humans and is resistant to denoising techniques. Besides, we optimize the noise transmission strategy for broader coverage and implement a hardware prototype of our system. Experimental results show that our system can reduce the recognition accuracy of recordings to below 50\% under all tested speech recognition systems, which is much better than existing solutions.

cs.CR↗

arXiv2024

Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization

Test-time domain adaptation aims to adapt the model trained on source domains to unseen target domains using a few unlabeled images. Emerging research has shown that the label and domain information is separately embedded in the weight matrix and batch normalization (BN) layer. Previous works normally update the whole network naively without explicitly decoupling the knowledge between label and domain. As a result, it leads to knowledge interference and defective distribution adaptation. In this work, we propose to reduce such learning interference and elevate the domain knowledge learning by only manipulating the BN layer. However, the normalization step in BN is intrinsically unstable when the statistics are re-estimated from a few samples. We find that ambiguities can be greatly reduced when only updating the two affine parameters in BN while keeping the source domain statistics. To further enhance the domain knowledge extraction from unlabeled data, we construct an auxiliary branch with label-independent self-supervised learning (SSL) to provide supervision. Moreover, we propose a bi-level optimization based on meta-learning to enforce the alignment of two learning objectives of auxiliary and main branches. The goal is to use the auxiliary branch to adapt the domain and benefit main task for subsequent inference. Our method keeps the same computational cost at inference as the auxiliary branch can be thoroughly discarded after adaptation. Extensive experiments show that our method outperforms the prior works on five WILDS real-world domain shift datasets. Our method can also be integrated with methods with label-dependent optimization to further push the performance boundary. Our code is available at https://github.com/ynanwu/MABN.

cs.CV↗

arXiv2024

Experimental quantum e-commerce

E-commerce, a type of trading that occurs at a high frequency on the Internet, requires guaranteeing the integrity, authentication and non-repudiation of messages through long distance. As current e-commerce schemes are vulnerable to computational attacks, quantum cryptography, ensuring information-theoretic security against adversary's repudiation and forgery, provides a solution to this problem. However, quantum solutions generally have much lower performance compared to classical ones. Besides, when considering imperfect devices, the performance of quantum schemes exhibits a significant decline. Here, for the first time, we demonstrate the whole e-commerce process of involving the signing of a contract and payment among three parties by proposing a quantum e-commerce scheme, which shows resistance of attacks from imperfect devices. Results show that with a maximum attenuation of 25 dB among participants, our scheme can achieve a signature rate of 0.82 times per second for an agreement size of approximately 0.428 megabit. This proposed scheme presents a promising solution for providing information-theoretic security for e-commerce.

quant-ph↗

arXiv2024

Distance-aware Attention Reshaping: Enhance Generalization of Neural Solver for Large-scale Vehicle Routing Problems

Neural solvers based on attention mechanism have demonstrated remarkable effectiveness in solving vehicle routing problems. However, in the generalization process from small scale to large scale, we find a phenomenon of the dispersion of attention scores in existing neural solvers, which leads to poor performance. To address this issue, this paper proposes a distance-aware attention reshaping method, assisting neural solvers in solving large-scale vehicle routing problems. Specifically, without the need for additional training, we utilize the Euclidean distance information between current nodes to adjust attention scores. This enables a neural solver trained on small-scale instances to make rational choices when solving a large-scale problem. Experimental results show that the proposed method significantly outperforms existing state-of-the-art neural solvers on the large-scale CVRPLib dataset.

cs.AI↗

arXiv2024

Open Set Dandelion Network for IoT Intrusion Detection

As IoT devices become widely, it is crucial to protect them from malicious intrusions. However, the data scarcity of IoT limits the applicability of traditional intrusion detection methods, which are highly data-dependent. To address this, in this paper we propose the Open-Set Dandelion Network (OSDN) based on unsupervised heterogeneous domain adaptation in an open-set manner. The OSDN model performs intrusion knowledge transfer from the knowledge-rich source network intrusion domain to facilitate more accurate intrusion detection for the data-scarce target IoT intrusion domain. Under the open-set setting, it can also detect newly-emerged target domain intrusions that are not observed in the source domain. To achieve this, the OSDN model forms the source domain into a dandelion-like feature space in which each intrusion category is compactly grouped and different intrusion categories are separated, i.e., simultaneously emphasising inter-category separability and intra-category compactness. The dandelion-based target membership mechanism then forms the target dandelion. Then, the dandelion angular separation mechanism achieves better inter-category separability, and the dandelion embedding alignment mechanism further aligns both dandelions in a finer manner. To promote intra-category compactness, the discriminating sampled dandelion mechanism is used. Assisted by the intrusion classifier trained using both known and generated unknown intrusion knowledge, a semantic dandelion correction mechanism emphasises easily-confused categories and guides better inter-category separability. Holistically, these mechanisms form the OSDN model that effectively performs intrusion knowledge transfer to benefit IoT intrusion detection. Comprehensive experiments on several intrusion datasets verify the effectiveness of the OSDN model, outperforming three state-of-the-art baseline methods by 16.9%.

cs.LG↗

arXiv2024

Lightweight Adaptive Feature De-drifting for Compressed Image Classification

JPEG is a widely used compression scheme to efficiently reduce the volume of transmitted images. The artifacts appear among blocks due to the information loss, which not only affects the quality of images but also harms the subsequent high-level tasks in terms of feature drifting. High-level vision models trained on high-quality images will suffer performance degradation when dealing with compressed images, especially on mobile devices. Numerous learning-based JPEG artifact removal methods have been proposed to handle visual artifacts. However, it is not an ideal choice to use these JPEG artifact removal methods as a pre-processing for compressed image classification for the following reasons: 1. These methods are designed for human vision rather than high-level vision models; 2. These methods are not efficient enough to serve as pre-processing on resource-constrained devices. To address these issues, this paper proposes a novel lightweight AFD module to boost the performance of pre-trained image classification models when facing compressed images. First, a FDE-Net is devised to generate the spatial-wise FDM in the DCT domain. Next, the estimated FDM is transmitted to the FE-Net to generate the mapping relationship between degraded features and corresponding high-quality features. A simple but effective RepConv block equipped with structural re-parameterization is utilized in FE-Net, which enriches feature representation in the training phase while maintaining efficiency in the deployment phase. After training on limited compressed images, the AFD-Module can serve as a "plug-and-play" model for pre-trained classification models to improve their performance on compressed images. Experiments demonstrate that our proposed AFD module can comprehensively improve the accuracy of the pre-trained classification models and significantly outperform the existing methods.

cs.CV↗

arXiv2023

Toward a stellar population catalog in the Kilo Degree Survey: the impact of stellar recipes on stellar masses and star formation rates

The Kilo Degree Survey (KiDS) is currently the only sky survey providing optical ($ugri$) plus near-infrared (NIR, $ZYHJK_S$) seeing matched photometry over an area larger than 1000 $\rm deg^2$. This is obtained by incorporating the NIR data from the VISTA Kilo Degree Infrared Galaxy (VIKING) survey, covering the same KiDS footprint. As such, the KiDS multi-wavelength photometry represents a unique dataset to test the ability of stellar population models to return robust photometric stellar mass ($M_*$) and star-formation rate (SFR) estimates. Here we use a spectroscopic sample of galaxies for which we possess $u g r i Z Y J H K_s$ ``gaussianized'' magnitudes from KiDS data release 4. We fit the spectral energy distribution from the 9-band photometry using: 1) three different popular libraries of stellar {population} templates, 2) single burst, simple and delayed exponential star-formation history models, and 3) a wide range of priors on age and metallicity. As template fitting codes we use two popular softwares: LePhare and CIGALE. We investigate the variance of the stellar masses and the star-formation rates from the different combinations of templates, star formation recipes and codes to assess the stability of these estimates and define some ``robust'' median quantities to be included in the upcoming KiDS data releases. As a science validation test, we derive the mass function, the star formation rate function, and the SFR-$M_*$ relation for a low-redshift ($z<0.5$) sample of galaxies, that result in excellent agreement with previous literature data. The final catalog, containing $\sim290\,000$ galaxies with redshift $0.01<z<0.9$, is made publicly available.

astro-ph.GA↗

arXiv2023

Parameter space investigation for spin-dependent electron diffraction in the Kapitza-Dirac effect

We demonstrate that spin-dependent electron diffraction is possible for a smooth range of transverse electron momenta in a two-photon Bragg scattering scenario of the Kapitza-Dirac effect. Our analysis is rendered possible by introducing a generalized specification for quantifying spin-dependent diffraction, yielding an optimization problem which is solved by making use of a Newton gradient iteration scheme. With this procedure, we investigate the spin-dependent effect for different transverse electron momenta and different laser polarizations of the standing light wave Kapitza-Dirac scattering. The possibility for using arbitrarily low transverse electron momenta, when setting up a spin-dependent Kapitza-Dirac experiment allows longer interaction times of the electron with the laser and therefore enables less constraining parameters for an implementation of the effect.

quant-ph↗

arXiv2023

Mechanism of charge transfer and electrostatic field fluctuations in high entropy metallic alloys

High entropy alloys present a new class of disordered metals which hold promising prospects for the next generation of materials and technology. However, much of the basic physics underlying these robust, multifunctional materials -- and those of other, more generic forms of disordered matter -- still remain the subject of ongoing inquiry. We thus present a minimal-working model that describes the disorder-driven fluctuations in the electronic charge distributions and electrostatic "Madelung" fields in disordered metals. Our theory follows a standard perturbative scheme and captures the leading contributions from dominant electronic processes, including electrostatic screening and impurity scattering events. We show here that a modest first-order treatment incorporating these effects is sufficient to reproduce the linear charge transfer trends featured in both high-entropy and other conventional alloys, our model also shedding light on the microscopic origins of these statistical features. We further elaborate on the nature of these electronic charge and Madelung field fluctuations by determining how these emerge from the statistics of the underlying disorder, and how these can be described using the linear response formulation that we develop here. In doing so, our work answers various questions which have long-perplexed the disordered materials community. It also opens up possible avenues for providing systematic corrections to modern first-principles approaches to disorder-modeling (e.g. the conventional CPA method) which currently lack these statistical features.

cond-mat.dis-nn↗

arXiv2023

First principles residual resistivity using locally self-consistent multiple scattering method

The locally self-consistent multiple scattering (LSMS) method can perform efficient first-principles calculations of systems with large number of atoms. In this work, we combine the Kubo-Greenwood equation with LSMS, enabling us to calculate first-principles residual resistivity of large systems. This has been implemented in the open-source code lsms. We apply this method to selected pure elements and binary random alloys. The results compare well with experiment, and with values obtained from a first-principles effective medium technique (KKR-CPA). We discuss future applications of this method to complex systems where other methods are not applicable.

cond-mat.mtrl-sci↗

arXiv2023

Cosmology with Galaxy Cluster Properties using Machine Learning

[Abridged] Galaxy clusters are the most massive gravitationally-bound systems in the universe and are widely considered to be an effective cosmological probe. We propose the first Machine Learning method using galaxy cluster properties to derive unbiased constraints on a set of cosmological parameters, including Omega_m, sigma_8, Omega_b, and h_0. We train the machine learning model with mock catalogs including "measured" quantities from Magneticum multi-cosmology hydrodynamical simulations, like gas mass, gas bolometric luminosity, gas temperature, stellar mass, cluster radius, total mass, velocity dispersion, and redshift, and correctly predict all parameters with uncertainties of the order of ~14% for Omega_m, ~8% for sigma_8, ~6% for Omega_b, and ~3% for h_0. This first test is exceptionally promising, as it shows that machine learning can efficiently map the correlations in the multi-dimensional space of the observed quantities to the cosmological parameter space and narrow down the probability that a given sample belongs to a given cosmological parameter combination. In the future, these ML tools can be applied to cluster samples with multi-wavelength observations from surveys like LSST, CSST, Euclid, Roman in optical and near-infrared bands, and eROSITA in X-rays, to constrain both the cosmology and the effect of the baryonic feedback.

astro-ph.CO↗

arXiv2023

Semi-supervised Estimation of Event Rate with Doubly-censored Survival Data

Electronic Health Record (EHR) has emerged as a valuable source of data for translational research. To leverage EHR data for risk prediction and subsequently clinical decision support, clinical endpoints are often time to onset of a clinical condition of interest. Precise information on clinical event times is often not directly available and requires labor-intensive manual chart review to ascertain. In addition, events may occur outside of the hospital system, resulting in both left and right censoring often termed double censoring. On the other hand, proxies such as time to the first diagnostic code are readily available yet with varying degrees of accuracy. Using error-prone event times derived from these proxies can lead to biased risk estimates while only relying on manually annotated event times, which are typically only available for a small subset of patients, can lead to high variability. This signifies the need for semi-supervised estimation methods that can efficiently combine information from both the small subset of labeled observations and a large size of surrogate proxies. While semi-supervised estimation methods have been recently developed for binary and right-censored data, no methods currently exist in the presence of double censoring. This paper fills the gap by developing a robust and efficient Semi-supervised Estimation of Event rate with Doubly-censored Survival data (SEEDS) by leveraging a small set of gold standard labels and a large set of surrogate features. Under regularity conditions, we demonstrate that the proposed SEEDS estimator is consistent and asymptotically normal. Simulation results illustrate that SEEDS performs well in finite samples and can be substantially more efficient compared to the supervised counterpart. We apply the SEEDS to estimate the age-specific survival rate of type 2 diabetes using EHR data from Mass General Brigham.

stat.ME↗

arXiv2023

Hidden Real Topology and Unusual Magnetoelectric Responses in Monolayer Antiferromagnetic Cr$_2$Se$_2$O

Recently, the real topology has been attracting widespread interest in two dimensions (2D). Here, based on first-principles calculations and theoretical analysis, we reveal the monolayer Cr$_2$Se$_2$O (ML-CrSeO) as the first material example of a 2D antiferromagnetic (AFM) real Chern insulator (RCI) with topologically protected corner states. Unlike previous RCIs, we find that the real topology of the ML-CrSeO is rooted in one certain mirror subsystem of the two spin channels, and can not be directly obtained from all the valence bands in each spin channel as commonly believed. In particular, due to antiferromagnetism, the corner modes in ML-CrSeO exhibit strong corner-contrasted spin polarization, leading to spin-corner coupling (SCC). This SCC enables a direct connection between spin space and real space. Consequently, large and switchable net magnetization can be induced in the ML-CrSeO nanodisk by electrostatic means, such as potential step and in-plane electric field, and the corresponding magnetoelectric responses behave like a sign function, distinguished from that of the conventional multiferroic materials. Our work considerably broadens the candidate range of RCI materials, and opens up a new direction for topo-spintronics and 2D AFM materials research.

cond-mat.mtrl-sci↗

arXiv2023

Mock Observations: Formation and Evolution of diffuse light in Galaxy Groups and Clusters in the IllustrisTNG Simulations

In this paper, by analyzing mock images from the IllustrisTNG100-1 simulation, we examine the properties of the diffuse light and compare them to those of central and satellite galaxies. Our findings suggest that the majority of the diffuse light originates from satellites. This claim is supported by the similarity between the age and metallicity distributions of the diffuse light and those of the satellites. Notably, the color distribution of the diffuse light gradually evolves to resemble that of the centrals at lower redshifts, suggesting a coevolution or passive process. The radial profiles of the diffuse light reveal distinct trends, with the inner regions displaying a relatively flat distribution and the outer regions showing a descending pattern. This finding suggests that the formation of the diffuse light is influenced by both major mergers and stellar tidal stripping. Moreover, strong correlations are found between the stellar mass of the diffuse light and the overall stellar mass of the satellites, as well as between the stellar mass of the diffuse light and the number of satellites within groups or clusters. These relationships can be described by power-law and logarithmic functions. Overall, the diffuse light components predominantly originate from satellites with intermediate ages and metallicities. These satellites typically fall within the stellar mass range of $\rm 8<\log_{10}M_{star}/M_{\odot}< 10$ and the color range of $\rm -1<[g-r]^{0.1}< 0$. As the redshift decreases, the growth of the diffuse light is primarily influenced by the redder satellites, while the most massive and reddest satellites have minimal roles in its growth.

astro-ph.GA↗

arXiv2023

MetaGCD: Learning to Continually Learn in Generalized Category Discovery

In this paper, we consider a real-world scenario where a model that is trained on pre-defined classes continually encounters unlabeled data that contains both known and novel classes. The goal is to continually discover novel classes while maintaining the performance in known classes. We name the setting Continual Generalized Category Discovery (C-GCD). Existing methods for novel class discovery cannot directly handle the C-GCD setting due to some unrealistic assumptions, such as the unlabeled data only containing novel classes. Furthermore, they fail to discover novel classes in a continual fashion. In this work, we lift all these assumptions and propose an approach, called MetaGCD, to learn how to incrementally discover with less forgetting. Our proposed method uses a meta-learning framework and leverages the offline labeled data to simulate the testing incremental learning process. A meta-objective is defined to revolve around two conflicting learning objectives to achieve novel class discovery without forgetting. Furthermore, a soft neighborhood-based contrastive network is proposed to discriminate uncorrelated images while attracting correlated images. We build strong baselines and conduct extensive experiments on three widely used benchmarks to demonstrate the superiority of our method.

cs.CV↗

arXiv2023

A Geometrical Approach to Evaluate the Adversarial Robustness of Deep Neural Networks

Deep Neural Networks (DNNs) are widely used for computer vision tasks. However, it has been shown that deep models are vulnerable to adversarial attacks, i.e., their performances drop when imperceptible perturbations are made to the original inputs, which may further degrade the following visual tasks or introduce new problems such as data and privacy security. Hence, metrics for evaluating the robustness of deep models against adversarial attacks are desired. However, previous metrics are mainly proposed for evaluating the adversarial robustness of shallow networks on the small-scale datasets. Although the Cross Lipschitz Extreme Value for nEtwork Robustness (CLEVER) metric has been proposed for large-scale datasets (e.g., the ImageNet dataset), it is computationally expensive and its performance relies on a tractable number of samples. In this paper, we propose the Adversarial Converging Time Score (ACTS), an attack-dependent metric that quantifies the adversarial robustness of a DNN on a specific input. Our key observation is that local neighborhoods on a DNN's output surface would have different shapes given different inputs. Hence, given different inputs, it requires different time for converging to an adversarial sample. Based on this geometry meaning, ACTS measures the converging time as an adversarial robustness metric. We validate the effectiveness and generalization of the proposed ACTS metric against different adversarial attacks on the large-scale ImageNet dataset using state-of-the-art deep networks. Extensive experiments show that our ACTS metric is an efficient and effective adversarial metric over the previous CLEVER metric.

cs.CV↗