arXiv subjects

Shuai Tang

Publications and source records attributed to Shuai Tang.

At least 19 recordsLinked to original sources

arXiv2026

Evidential-Based Higher-Order Set Argumentation Framework

Evidential argumentation extends Dung's abstract argumentation by requiring arguments and interactions to be backed by chains of evidence rooted in prima-facie elements. However, existing formalisms lack a unified treatment of evidential support, higher-order relations (attacks and supports targeting arbitrary elements), and collective interactions (sources as sets). In this paper, we introduce the Evidential-Based Higher-Order Set Argumentation Framework (EHSAF), which conservatively generalises several existing frameworks within a single expressive setting. We develop two complete semantics for EHSAFs: an \emph{adjacent complete labelling semantics} that admits multiple truth values (true, false, undecided) for arguments in support cycles, reflecting an open epistemic attitude toward future evidence; and an \emph{extension-based complete semantics} that follows a strict evidentialist stance, accepting only arguments with well-founded support chains. We show that these two semantics diverge in the presence of support cycles, and prove their equivalence under support-acyclicity. To enable computational reasoning, we provide a normal propositional encoding of EHSAFs and prove that, in three-valued {\L}ukasiewicz logic, its models correspond precisely to the adjacent complete labellings. We further extend this encoding to continuous fuzzy logics (G{\"o}del, Product, and {\L}ukasiewicz), defining a continuous fuzzy normal encoded semantics. We establish that this fuzzy semantics satisfies key properties---continuity, monotonicity, boundary conditions, and solution existence---and that its ternarisation recovers the adjacent complete labellings under natural t-norm conditions. Our framework thus unifies expressive argumentation with principled three-valued and fuzzy semantics, bridging the gap between qualitative and quantitative reasoning about evidence.

cs.AI↗

arXiv2026

$d$-wave altermagnetism revealed by resonant inelastic X-ray scattering

Altermagnetism defines a third fundamental class of collinear magnetic order, featuring compensated magnetic moments with antiparallel spin alignment, yet lifted Kramers degeneracy without the need for relativistic spin-orbit coupling. Its ability to host spin-polarized electronic bands and unconventional chiral magnons makes it a promising platform for functional materials. However, experimental verification has proven challenging; while circular dichroism in resonant inelastic X-ray scattering (RIXS) has been suggested as a signature of chiral magnons, it remains controversial whether this effect is an intrinsic property of altermagnetism or an artifact of experimental geometry. In this work, we resolve this debate and provide unambiguous experimental evidence of $d$-wave altermagnetism in the strongly correlated Lieb-lattice magnet La$_2$O$_3$Mn$_2$Se$_2$. The RIXS spectra exhibit a $d$-wave-symmetry circular dichroism in the magnetic excitations that vanishes in the paramagnetic phase. Through RIXS-operator symmetry analysis and exact-diagonalization calculations, we prove that the observed dichroism is a direct consequence of altermagnetic symmetry constraints, independent of magnon branch splitting. Our results provide definitive evidence for the experimental realization of $d$-wave altermagnetism in La$_2$O$_3$Mn$_2$Se$_2$ and establish circularly polarized RIXS as a highly symmetry-sensitive spectroscopic framework for detecting magnetic phases that evade conventional probes.

cond-mat.str-el↗

arXiv2026

Methods for characterization of atomic-scale field emission point-electron-source

Field emission (FE) electron sources are made close to atomic-scale to reach the highest spatial resolution as well as stable emission for electron microscopy, electron beam inspection and lithography. At present, no single agreed method exists of using FE current-voltage data to extract the apparent emission area, which is needed for predicting some beam properties. The 1956 theory of Murphy and Good (MG) is better physics than the 1920s theory of Fowler and Nordheim (FN) and colleagues, but many researchers use simplified FN theory to analyse experimental data. The present paper reports an experimental method of finding apparent emission area, based on using field ion and field electron microscopes (FIM-FEM). The discrepancy of emission area between the FIM-FEM method and MG-based analysis is a factor of 7.4, while that with simplified FN-based analysis is about 25, confirming MG theory is better for FE data analysis. The result allows deduction of key indicators, including source energy spread, reduced brightness and emission efficiency. A downloadable program is made available to help analysis. Our work provides a new experimental method of characterizing FE electron sources, especially the atomic-scale cold cathode, for which existing plot-based data-analysis methods are not suitable.

quant-ph↗

arXiv2025

Encoding higher-order argumentation frameworks with supports to propositional logic systems

Argumentation frameworks ($AF$s) have been extensively developed, but existing higher-order bipolar $AF$s suffer from critical limitations: attackers and supporters are restricted to arguments, multi-valued and fuzzy semantics lack unified generalization, and encodings often rely on complex logics with poor interoperability. To address these gaps, this paper proposes a higher-order argumentation framework with supports ($HAFS$), which explicitly allows attacks and supports to act as both targets and sources of interactions. We define a suite of semantics for $HAFS$s, including extension-based semantics, adjacent complete labelling semantics (a 3-valued semantics), and numerical equational semantics ([0,1]-valued semantics). Furthermore, we develop a normal encoding methodology to translate $HAFS$s into propositional logic systems ($\mathcal{PLS}$s): $HAFS$s under complete labelling semantics are encoded into {\L}ukasiewicz's three-valued propositional logic ($\mathcal{PL}_3^L$), and those under equational semantics are encoded into fuzzy $\mathcal{PLS}$s ($\mathcal{PL}_{[0,1]}$) such as G\"odel and Product fuzzy logics. We prove model equivalence between $HAFS$s and their encoded logical formulas, establishing the logical foundation of $HAFS$ semantics. Additionally, we investigate the relationships between 3-valued complete semantics and fuzzy equational semantics, showing that models of fuzzy encoded semantics can be transformed into complete semantics models via ternarization, and vice versa for specific t-norms. This work advances the formalization and logical encoding of higher-order bipolar argumentation, enabling seamless integration with lightweight computational solvers and uniform handling of uncertainty.

math.LO↗

arXiv2025

LAA3D: A Benchmark of Detecting and Tracking Low-Altitude Aircraft in 3D Space

Perception of Low-Altitude Aircraft (LAA) in 3D space enables precise 3D object localization and behavior understanding. However, datasets tailored for 3D LAA perception remain scarce. To address this gap, we present LAA3D, a large-scale dataset designed to advance 3D detection and tracking of low-altitude aerial vehicles. LAA3D contains 15,000 real images and 600,000 synthetic frames, captured across diverse scenarios, including urban and suburban environments. It covers multiple aerial object categories, including electric Vertical Take-Off and Landing (eVTOL) aircraft, Micro Aerial Vehicles (MAVs), and Helicopters. Each instance is annotated with 3D bounding box, class label, and instance identity, supporting tasks such as 3D object detection, 3D multi-object tracking (MOT), and 6-DoF pose estimation. Besides, we establish the LAA3D Benchmark, integrating multiple tasks and methods with unified evaluation protocols for comparison. Furthermore, we propose MonoLAA, a monocular 3D detection baseline, achieving robust 3D localization from zoom cameras with varying focal lengths. Models pretrained on synthetic images transfer effectively to real-world data with fine-tuning, demonstrating strong sim-to-real generalization. Our LAA3D provides a comprehensive foundation for future research in low-altitude 3D object perception.

cs.CV↗

arXiv2025

Encoding argumentation frameworks with set attackers to propositional logic systems

Argumentation frameworks ($AF$s) have been a useful tool for approximate reasoning. The encoding method is an important approach to formally model $AF$s under related semantics. The aim of this paper is to develop the encoding method from classical Dung's $AF$s ($DAF$s) to $AF$s with set attackers ($AFSA$s) including higher-level argumentation frames ($HLAF$s), Barringer's higher-order $AF$s ($BHAF$s), frameworks with sets of attacking arguments ($SETAF$s) and higher-order set $AF$s ($HSAF$s). Regarding syntactic structures, we propose the $HSAF$s where the target of an attack is either an argument or an attack and the sources are sets of arguments and attacks. Regarding semantics, we translate $HLAF$s and $SETAF$s under respective complete semantics to {\L}ukasiewicz's 3-valued propositional logic system ($PL_3^L$). Furthermore, we propose complete semantics of $BHAF$s and $HSAF$s by respectively generalizing from $HLAF$s and $SETAF$s, and then translate to the $PL_3^L$. Moreover, for numerical semantics of $AFSA$s, we propose the equational semantics and translate to fuzzy propositional logic systems ($PL_{[0,1]}$s). This paper establishes relationships of model equivalence between an $AFSA$ under a given semantics and the encoded formula in a related propositional logic system ($PLS$). By connections of $AFSA$s and $PLS$s, this paper provides the logical foundations for $AFSA$s associated with complete semantics and equational semantics. The results advance the argumentation theory by unifying $HOAF$s and $SETAF$s under logical formalisms, paving the way for automated reasoning tools in AI, decision support, and multi-agent systems.

math.LO↗

arXiv2025

Encoding Argumentation Frameworks to Propositional Logic Systems

This paper generalizes the encoding of argumentation frameworks beyond the classical 2-valued propositional logic system ($PL_2$) to 3-valued propositional logic systems ($PL_3$s) and fuzzy propositional logic systems ($PL_{[0,1]}s$), employing two key encodings: normal encoding ($ec_1$) and regular encoding ($ec_2$). Specifically, via $ec_1$ and $ec_2$, we establish model relationships between Dung's classical semantics (stable and complete semantics) and the encoded semantics associated with Kleene's $PL_3$ and {\L}ukasiewicz's $PL_3$. Through $ec_1$, we also explore connections between Gabbay's real equational semantics and the encoded semantics of $PL_{[0,1]}s$, including showing that Gabbay's $Eq_{\text{max}}^R$ and $Eq_{\text{inverse}}^R$ correspond to the fuzzy encoded semantics of $PL_{[0,1]}^G$ and $PL_{[0,1]}^P$ respectively. Additionally, we propose a new fuzzy encoded semantics ($Eq^L$) associated with {\L}ukasiewicz's $PL_{[0,1]}$ and investigate interactions between complete semantics and fuzzy encoded semantics. This work strengthens the links between argumentation frameworks and propositional logic systems, providing a framework for constructing new argumentation semantics.

cs.AI↗

arXiv2024

Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable

Machine unlearning is motivated by desire for data autonomy: a person can request to have their data's influence removed from deployed models, and those models should be updated as if they were retrained without the person's data. We show that, counter-intuitively, these updates expose individuals to high-accuracy reconstruction attacks which allow the attacker to recover their data in its entirety, even when the original models are so simple that privacy risk might not otherwise have been a concern. We show how to mount a near-perfect attack on the deleted data point from linear regression models. We then generalize our attack to other loss functions and architectures, and empirically demonstrate the effectiveness of our attacks across a wide range of datasets (capturing both tabular and image data). Our work highlights that privacy risk is significant even for extremely simple model classes when individuals can request deletion of their data from the model.

cs.LG↗

arXiv2023

Membership Inference Attacks on Diffusion Models via Quantile Regression

Recently, diffusion models have become popular tools for image synthesis because of their high-quality outputs. However, like other large-scale models, they may leak private information about their training data. Here, we demonstrate a privacy vulnerability of diffusion models through a \emph{membership inference (MI) attack}, which aims to identify whether a target example belongs to the training set when given the trained diffusion model. Our proposed MI attack learns quantile regression models that predict (a quantile of) the distribution of reconstruction loss on examples not used in training. This allows us to define a granular hypothesis test for determining the membership of a point in the training set, based on thresholding the reconstruction loss of that point using a custom threshold tailored to the example. We also provide a simple bootstrap technique that takes a majority membership prediction over ``a bag of weak attackers'' which improves the accuracy over individual quantile regression models. We show that our attack outperforms the prior state-of-the-art attack while being substantially less computationally expensive -- prior attacks required training multiple ``shadow models'' with the same architecture as the model under attack, whereas our attack requires training only much smaller models.

cs.LG↗

arXiv2023

Scalable Membership Inference Attacks via Quantile Regression

Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference can be formalized as a hypothesis testing problem. The most effective existing attacks estimate the distribution of some test statistic (usually the model's confidence on the true label) on points that were (and were not) used in training by training many \emph{shadow models} -- i.e. models of the same architecture as the model being attacked, trained on a random subsample of data. While effective, these attacks are extremely computationally expensive, especially when the model under attack is large. We introduce a new class of attacks based on performing quantile regression on the distribution of confidence scores induced by the model under attack on points that are not used in training. We show that our method is competitive with state-of-the-art shadow model attacks, while requiring substantially less compute because our attack requires training only a single model. Moreover, unlike shadow model attacks, our proposed attack does not require any knowledge of the architecture of the model under attack and is therefore truly ``black-box". We show the efficacy of this approach in an extensive series of experiments on various datasets and model architectures.

cs.LG↗

arXiv2023

Improved Differentially Private Regression via Gradient Boosting

We revisit the problem of differentially private squared error linear regression. We observe that existing state-of-the-art methods are sensitive to the choice of hyperparameters -- including the ``clipping threshold'' that cannot be set optimally in a data-independent way. We give a new algorithm for private linear regression based on gradient boosting. We show that our method consistently improves over the previous state of the art when the clipping threshold is taken to be fixed without knowledge of the data, rather than optimized in a non-private way -- and that even when we optimize the hyperparameters of competitor algorithms non-privately, our algorithm is no worse and often better. In addition to a comprehensive set of experiments, we give theoretical insights to explain this behavior.

cs.LG↗

arXiv2022

Private Synthetic Data for Multitask Learning and Marginal Queries

We provide a differentially private algorithm for producing synthetic data simultaneously useful for multiple tasks: marginal queries and multitask machine learning (ML). A key innovation in our algorithm is the ability to directly handle numerical features, in contrast to a number of related prior approaches which require numerical features to be first converted into {high cardinality} categorical features via {a binning strategy}. Higher binning granularity is required for better accuracy, but this negatively impacts scalability. Eliminating the need for binning allows us to produce synthetic data preserving large numbers of statistical queries such as marginals on numerical features, and class conditional linear threshold queries. Preserving the latter means that the fraction of points of each class label above a particular half-space is roughly the same in both the real and synthetic data. This is the property that is needed to train a linear classifier in a multitask setting. Our algorithm also allows us to produce high quality synthetic data for mixed marginal queries, that combine both categorical and numerical features. Our method consistently runs 2-5x faster than the best comparable techniques, and provides significant accuracy improvements in both marginal queries and linear prediction tasks for mixed-type datasets.

cs.LG↗

arXiv2022

Functional acoustic metamaterial using shortcut to adiabatic passage in acoustic waveguide couplers

Shortcut to adiabatic passage (STAP), initially proposed to accelerate adiabatic quantum state transfer, has been widely explored and applied in quantum optics and integrated optics. Here we bring STAP into the field of acoustics to design compact couplers and functional metamaterial. The space-varying coupling strengths of acoustic waveguides (WGs) are tailored by means of dressed states in a three-level system, accounting for the desirable acoustic energy transfer among three WGs with short length. We show that the acoustic coupler has one-way feature when loss is introduced into the intermediate WG. More uniquely, when the propagation of acoustic wave is designed to mimic a Hadamard transformation, an acoustic metamaterial can be constructed by arraying several couplers, possessing the beam-splitting function and unidirectional, broadband performances. Our work bridges STAP and the acoustic coupler as well as metamaterial, which may have profound impacts on exploring quantum technologies for promoting advanced acoustic devices.

physics.optics↗

arXiv2022

MAMDR: A Model Agnostic Learning Method for Multi-Domain Recommendation

Large-scale e-commercial platforms in the real-world usually contain various recommendation scenarios (domains) to meet demands of diverse customer groups. Multi-Domain Recommendation (MDR), which aims to jointly improve recommendations on all domains and easily scales to thousands of domains, has attracted increasing attention from practitioners and researchers. Existing MDR methods usually employ a shared structure and several specific components to respectively leverage reusable features and domain-specific information. However, data distribution differs across domains, making it challenging to develop a general model that can be applied to all circumstances. Additionally, during training, shared parameters often suffer from the domain conflict while specific parameters are inclined to overfitting on data sparsity domains. we first present a scalable MDR platform served in Taobao that enables to provide services for thousands of domains without specialists involved. To address the problems of MDR methods, we propose a novel model agnostic learning framework, namely MAMDR, for the multi-domain recommendation. Specifically, we first propose a Domain Negotiation (DN) strategy to alleviate the conflict between domains. Then, we develop a Domain Regularization (DR) to improve the generalizability of specific parameters by learning from other domains. We integrate these components into a unified framework and present MAMDR, which can be applied to any model structure to perform multi-domain recommendation. Finally, we present a large-scale implementation of MAMDR in the Taobao application and construct various public MDR benchmark datasets which can be used for following studies. Extensive experiments on both benchmark datasets and industry datasets demonstrate the effectiveness and generalizability of MAMDR.

cs.IR↗

arXiv2022

Spectrally Adaptive Common Spatial Patterns

The method of Common Spatial Patterns (CSP) is widely used for feature extraction of electroencephalography (EEG) data, such as in motor imagery brain-computer interface (BCI) systems. It is a data-driven method estimating a set of spatial filters so that the power of the filtered EEG signal is maximized for one motor imagery class and minimized for the other. This method, however, is prone to overfitting and is known to suffer from poor generalization especially with limited calibration data. Additionally, due to the high heterogeneity in brain data and the non-stationarity of brain activity, CSP is usually trained for each user separately resulting in long calibration sessions or frequent re-calibrations that are tiring for the user. In this work, we propose a novel algorithm called Spectrally Adaptive Common Spatial Patterns (SACSP) that improves CSP by learning a temporal/spectral filter for each spatial filter so that the spatial filters are concentrated on the most relevant temporal frequencies for each user. We show the efficacy of SACSP in providing better generalizability and higher classification accuracy from calibration to online control compared to existing methods. Furthermore, we show that SACSP provides neurophysiologically relevant information about the temporal frequencies of the filtered signals. Our results highlight the differences in the motor imagery signal among BCI users as well as spectral differences in the signals generated for each class, and show the importance of learning robust user-specific features in a data-driven manner.

eess.SP↗

arXiv2021

Unidirectional acoustic metamaterials based on nonadiabatic holonomic quantum transformations

Nonadiabatic holonomic quantum transformations (NHQTs) have attracted wide attention and have been applied in many aspects of quantum computation, whereas related research is usually limited to the field of quantum physics. Here we bring NHQTs into constructing a unidirectional acoustic metamaterial (UDAM) for shaping classical beams. The UDAM is made up of an array of three-waveguide couplers, where the propagation of acoustic waves mimics the evolution of NHQTs. The excellent agreement among analytical predictions, numerical simulations, and experimental measurements confirms the great applicability of NHQTs in acoustic metamaterial engineering. The present work extends research on NHQTs from quantum physics to the field of classical waves for designing metamaterials with simple structures and may pave a new way to design UDAMs that would be of potential applications in acoustic isolation, communication, and stealth.

physics.class-ph↗

arXiv2021

Fast Adaptation with Linearized Neural Networks

The inductive biases of trained neural networks are difficult to understand and, consequently, to adapt to new settings. We study the inductive biases of linearizations of neural networks, which we show to be surprisingly good summaries of the full network functions. Inspired by this finding, we propose a technique for embedding these inductive biases into Gaussian processes through a kernel designed from the Jacobian of the network. In this setting, domain adaptation takes the form of interpretable posterior inference, with accompanying uncertainty estimation. This inference is analytic and free of local optima issues found in standard techniques such as fine-tuning neural network weights to a new task. We develop significant computational speed-ups based on matrix multiplies, including a novel implementation for scalable Fisher vector products. Our experiments on both image classification and regression demonstrate the promise and convenience of this framework for transfer learning, compared to neural network fine-tuning. Code is available at https://github.com/amzn/xfer/tree/master/finite_ntk.

stat.ML↗

arXiv2020

Deep Transfer Learning with Ridge Regression

The large amount of online data and vast array of computing resources enable current researchers in both industry and academia to employ the power of deep learning with neural networks. While deep models trained with massive amounts of data demonstrate promising generalisation ability on unseen data from relevant domains, the computational cost of finetuning gradually becomes a bottleneck in transfering the learning to new domains. We address this issue by leveraging the low-rank property of learnt feature vectors produced from deep neural networks (DNNs) with the closed-form solution provided in kernel ridge regression (KRR). This frees transfer learning from finetuning and replaces it with an ensemble of linear systems with many fewer hyperparameters. Our method is successful on supervised and semi-supervised transfer learning tasks.

cs.LG↗