arXiv subjects

Yan Zhang

Publications and source records attributed to Yan Zhang.

At least 451 records · Page 25Linked to original sources

arXiv2022

PC-GANs: Progressive Compensation Generative Adversarial Networks for Pan-sharpening

The fusion of multispectral and panchromatic images is always dubbed pansharpening. Most of the available deep learning-based pan-sharpening methods sharpen the multispectral images through a one-step scheme, which strongly depends on the reconstruction ability of the network. However, remote sensing images always have large variations, as a result, these one-step methods are vulnerable to the error accumulation and thus incapable of preserving spatial details as well as the spectral information. In this paper, we propose a novel two-step model for pan-sharpening that sharpens the MS image through the progressive compensation of the spatial and spectral information. Firstly, a deep multiscale guided generative adversarial network is used to preliminarily enhance the spatial resolution of the MS image. Starting from the pre-sharpened MS image in the coarse domain, our approach then progressively refines the spatial and spectral residuals over a couple of generative adversarial networks (GANs) that have reverse architectures. The whole model is composed of triple GANs, and based on the specific architecture, a joint compensation loss function is designed to enable the triple GANs to be trained simultaneously. Moreover, the spatial-spectral residual compensation structure proposed in this paper can be extended to other pan-sharpening methods to further enhance their fusion results. Extensive experiments are performed on different datasets and the results demonstrate the effectiveness and efficiency of our proposed method.

eess.IV↗

arXiv2022

Pay More Attention to History: A Context Modelling Strategy for Conversational Text-to-SQL

Conversational text-to-SQL aims at converting multi-turn natural language queries into their corresponding SQL (Structured Query Language) representations. One of the most intractable problems of conversational text-to-SQL is modelling the semantics of multi-turn queries and gathering the proper information required for the current query. This paper shows that explicitly modelling the semantic changes by adding each turn and the summarization of the whole context can bring better performance on converting conversational queries into SQLs. In particular, we propose two conversational modelling tasks in both turn grain and conversation grain. These two tasks simply work as auxiliary training tasks to help with multi-turn conversational semantic parsing. We conducted empirical studies and achieved new state-of-the-art results on the large-scale open-domain conversational text-to-SQL dataset. The results demonstrate that the proposed mechanism significantly improves the performance of multi-turn semantic parsing.

cs.CL↗

arXiv2022

Compositional Human-Scene Interaction Synthesis with Semantic Control

Synthesizing natural interactions between virtual humans and their 3D environments is critical for numerous applications, such as computer games and AR/VR experiences. Our goal is to synthesize humans interacting with a given 3D scene controlled by high-level semantic specifications as pairs of action categories and object instances, e.g., "sit on the chair". The key challenge of incorporating interaction semantics into the generation framework is to learn a joint representation that effectively captures heterogeneous information, including human body articulation, 3D object geometry, and the intent of the interaction. To address this challenge, we design a novel transformer-based generative model, in which the articulated 3D human body surface points and 3D objects are jointly encoded in a unified latent space, and the semantics of the interaction between the human and objects are embedded via positional encoding. Furthermore, inspired by the compositional nature of interactions that humans can simultaneously interact with multiple objects, we define interaction semantics as the composition of varying numbers of atomic action-object pairs. Our proposed generative model can naturally incorporate varying numbers of atomic interactions, which enables synthesizing compositional human-scene interactions without requiring composite interaction data. We extend the PROX dataset with interaction semantic labels and scene instance segmentation to evaluate our method and demonstrate that our method can generate realistic human-scene interactions with semantic control. Our perceptual study shows that our synthesized virtual humans can naturally interact with 3D scenes, considerably outperforming existing methods. We name our method COINS, for COmpositional INteraction Synthesis with Semantic Control. Code and data are available at https://github.com/zkf1997/COINS.

cs.CV↗

arXiv2022

IAM: A Comprehensive and Large-Scale Dataset for Integrated Argument Mining Tasks

Traditionally, a debate usually requires a manual preparation process, including reading plenty of articles, selecting the claims, identifying the stances of the claims, seeking the evidence for the claims, etc. As the AI debate attracts more attention these years, it is worth exploring the methods to automate the tedious process involved in the debating system. In this work, we introduce a comprehensive and large dataset named IAM, which can be applied to a series of argument mining tasks, including claim extraction, stance classification, evidence extraction, etc. Our dataset is collected from over 1k articles related to 123 topics. Near 70k sentences in the dataset are fully annotated based on their argument properties (e.g., claims, stances, evidence, etc.). We further propose two new integrated argument mining tasks associated with the debate preparation process: (1) claim extraction with stance classification (CESC) and (2) claim-evidence pair extraction (CEPE). We adopt a pipeline approach and an end-to-end method for each integrated task separately. Promising experimental results are reported to show the values and challenges of our proposed tasks, and motivate future research on argument mining.

cs.CL↗

arXiv2022

Med-DANet: Dynamic Architecture Network for Efficient Medical Volumetric Segmentation

For 3D medical image (e.g. CT and MRI) segmentation, the difficulty of segmenting each slice in a clinical case varies greatly. Previous research on volumetric medical image segmentation in a slice-by-slice manner conventionally use the identical 2D deep neural network to segment all the slices of the same case, ignoring the data heterogeneity among image slices. In this paper, we focus on multi-modal 3D MRI brain tumor segmentation and propose a dynamic architecture network named Med-DANet based on adaptive model selection to achieve effective accuracy and efficiency trade-off. For each slice of the input 3D MRI volume, our proposed method learns a slice-specific decision by the Decision Network to dynamically select a suitable model from the predefined Model Bank for the subsequent 2D segmentation task. Extensive experimental results on both BraTS 2019 and 2020 datasets show that our proposed method achieves comparable or better results than previous state-of-the-art methods for 3D MRI brain tumor segmentation with much less model complexity. Compared with the state-of-the-art 3D method TransBTS, the proposed framework improves the model efficiency by up to 3.5x without sacrificing the accuracy. Our code will be publicly available soon.

eess.IV↗

arXiv2022

Digital Twin Assisted Task Offloading for Aerial Edge Computing and Networks

Considering the user mobility and unpredictable mobile edge computing (MEC) environments, this paper studies the intelligent task offloading problem in unmanned aerial vehicle (UAV)-enabled MEC with the assistance of digital twin (DT). We aim at minimizing the energy consumption of the entire MEC system by jointly optimizing mobile terminal users (MTUs) association, UAV trajectory, transmission power distribution and computation capacity allocation while respecting the constraints of mission maximum processing delays. Specifically, double deep Q-network (DDQN) algorithm stemming from deep reinforcement learning is first proposed to effectively solve the problem of MTUs association and UAV trajectory. Then, the closed-form expression is employed to handle the problem of transmission power distribution and the computation capacity allocation problem is further addressed via an iterative algorithm. Numerical results show that our proposed scheme is able to converge and significantly reduce the total energy consumption of the MEC system compared to the benchmark schemes.

cs.IT↗

arXiv2022

Incentivizing Proof-of-Stake Blockchain for Secured Data Collection in UAV-Assisted IoT: A Multi-Agent Reinforcement Learning Approach

The Internet of Things (IoT) can be conveniently deployed while empowering various applications, where the IoT nodes can form clusters to finish certain missions collectively. In this paper, we propose to employ unmanned aerial vehicles (UAVs) to assist the clustered IoT data collection with blockchain-based security provisioning. In particular, the UAVs generate candidate blocks based on the collected data, which are then audited through a lightweight proof-of-stake consensus mechanism within the UAV-based blockchain network. To motivate efficient blockchain while reducing the operational cost, a stake pool is constructed at the active UAV while encouraging stake investment from other UAVs with profit sharing. The problem is formulated to maximize the overall profit through the blockchain system in unit time by jointly investigating the IoT transmission, incentives through investment and profit sharing, and UAV deployment strategies. Then, the problem is solved in a distributed manner while being decoupled into two layers. The inner layer incorporates IoT transmission and incentive design, which are tackled with large-system approximation and one-leader-multi-follower Stackelberg game analysis, respectively. The outer layer for UAV deployment is undertaken with a multi-agent deep deterministic policy gradient approach. Results show the convergence of the proposed learning process and the UAV deployment, and also demonstrated is the performance superiority of our proposal as compared with the baselines.

cs.NI↗

arXiv2022

A Formal Specification of Operating System based on ARINC 653

In this paper, by using the formal language \emph{Circus}, we give a formal specification of an operating system based on ARINC 653 standard. Our specification includes interrupt handling, time and memory management, partition and process scheduling, system call response and related APEX services. Especially, the concurrent behaviours of partitions and processes are also specified.

cs.LO↗

arXiv2022

A Universal Framework for Reconstructing Complex Networks and Node Dynamics from Discrete or Continuous Dynamics Data

Many dynamical processes of complex systems can be understood as the dynamics of a group of nodes interacting on a given network structure. However, finding such interaction structure and node dynamics from time series of node behaviours is tough. Conventional methods focus on either network structure inference task or dynamics reconstruction problem, very few of them can work well on both. This paper proposes a universal framework for reconstructing network structure and node dynamics at the same time from observed time-series data of nodes. We use a differentiable Bernoulli sampling process to generate a candidate network structure, and use neural networks to simulate the node dynamics based on the candidate network. We then adjust all the parameters with a stochastic gradient descent algorithm to maximize the likelihood function defined on the data. The experiments show that our model can recover various network structures and node dynamics at the same time with high accuracy. It can also work well on binary, discrete and continuous time-series data, and the reconstruction results are robust against noise and missing information.

physics.soc-ph↗

arXiv2022

Giant atoms with time-dependent couplings

We study the decay dynamics of a two-level giant atom that is coupled to a waveguide with time-dependent coupling strengths. In the non-Markovian regime where the retardation effect cannot be ignored, we show that the dynamics of the atom depends on the atom-waveguide coupling strengths at an earlier time. This allows one to tailor the decay dynamics of the giant atom and even realize a stationary population revival with appropriate coupling modulations. Moreover, we demonstrate the possibility of simulating the quantum Zeno and quantum anti-Zeno effects in the giant-atom model with periodic coupling quenches. These results have potential applications in quantum information processing and quantum network engineering.

quant-ph↗

arXiv2022

Multi-wavelength Variation Phenomena of PKS 0735+178 on Diverse Timescale

BL Lac object PKS 0735+178 showed some complex multi-wavelength variation phenomena in the previous studies, especially for its color behavior. Bluer-when-brighter, redder-when-brighter and achromatic behavior were all found to be possible long-term trends of PKS 0735+178. In this work, we collected the long-term multi-wavelength data of PKS 0735+178, and also performed a multi-color optical monitoring on intraday timescale. The intraday variability was detected on one night. On the long timescale, a possible 22-day time lag was found between the $R$ and $γ$-ray bands. The results of the cross-correlation analysis exhibited strong correlations between various optical bands on both intraday and long timescale. However, only a mild correlation was found between the long-term $γ$-ray and $R$-band light curves, which could be interpreted by the different emission mechanisms of the $γ$-ray and optical emissions. PKS 0735+178 showed a significant harder-when-brighter in the $γ$-ray band, which is consistent with the observed optical bluer-when-brighter trend on both long-term and intraday timescales. We found that the HWB and BWB trends will be enhanced during the active states, especially for the historical low state. Such phenomenon indicates a special activity-dependent color behavior of PKS 0735+178, and it could be well interpreted by the jet emission model.

astro-ph.GA↗

arXiv2022

Giant Atoms in a Synthetic Frequency Dimension

Giant atoms that interact with real-space waveguides at multiple spatial points have attracted extensive attention due to their unique interference effects. Here we propose a feasible scheme for constructing giant atoms in a synthetic frequency dimension with, e.g., a dynamically modulated superconducting resonator and a tailored three-level artificial atom. Both analytical and numerical calculations show good agreement between our scheme and real-space two-level giant atoms. In particular, the symmetry of the model in momentum space can be broken by tuning the phase of the external field applied on the atom, enabling chiral interactions between the atom and the frequency lattice. We further demonstrate the possibility of simulating cascaded interaction and directional excitation transfer in the frequency dimension by directly extending our model to involve more such effective giant atoms.

quant-ph↗

arXiv2022

Light transfer transitions beyond higher-order exceptional points in parity-time and anti-parity-time symmetric waveguide arrays

We propose two non-Hermitian arrays consisting of $N=2l+1$ waveguides and exhibiting parity-time ($\mathcal{PT}$) or anti-$\mathcal{PT}$ symmetry for investigating light transfer dynamics based on $N$th-order exceptional points (EPs). The $\mathcal{PT}$-symmetric array supports two $N$th-order EPs separating an unbroken and a broken phase with real and imaginary eignvalues, respectively. Light transfer dynamics in this array exhibits radically different behaviors, i.e. a unidirectional oscillation behavior in the unbroken phase, an edge-towards localization behavior in the broken phase, and a center-towards localization behavior just at $N$th-order EPs. The anti-$\mathcal{PT}$-symmetric array supports also two $N$th-order EPs separating an unbroken and a broken phase, which refer however to imaginary and real eigenvalues, respectively. Accordingly, light transfer dynamics in this array exhibits a center-towards localization behavior in the unbroken phase and an origin-centered oscillation behavior in the broken phase. These nontrivial light transfer behaviors and their controlled transitions are not viable for otherwise split lower-order EPs and depend on the underlying $SU(2)$ symmetry of spin-$l$ matrices.

physics.optics↗

arXiv2022

Spatial Kramers-Kronig relation and unidirectional light reflection induced by Rydberg dipole-dipole interactions

Kramers-Kronig (KK) relation between the dispersion and absorption responses of a signal field can be mapped from the frequency domain into the space domain via the dipole-dipole interactions between a homogeneous sample of target atoms and a control atom. This is achieved by establishing an effective two-level configuration for the three-level target atoms in the single-photon far-detuned driving regime while maintaining a high Rydberg excitation for the three-level control atom in the single-photon resonant driving regime. We find in particular that it is viable to realize a dynamically tunable spatial KK relation supporting asymmetric and even unidirectional reflection for appropriate signal frequencies in a controlled range. Taking a periodic lattice of target atoms instead, multiple Bragg scattering can be further incorporated into spatial KK relation to largely enhance the nonzero reflectivity yet without breaking the asymmetric or unidirectional reflection.

physics.atom-ph↗

arXiv2022

The Wanderings of Odysseus in 3D Scenes

Our goal is to populate digital environments, in which digital humans have diverse body shapes, move perpetually, and have plausible body-scene contact. The core challenge is to generate realistic, controllable, and infinitely long motions for diverse 3D bodies. To this end, we propose generative motion primitives via body surface markers, or GAMMA in short. In our solution, we decompose the long-term motion into a time sequence of motion primitives. We exploit body surface markers and conditional variational autoencoder to model each motion primitive, and generate long-term motion by implementing the generative model recursively. To control the motion to reach a goal, we apply a policy network to explore the generative model's latent space and use a tree-based search to preserve the motion quality during testing. Experiments show that our method can produce more realistic and controllable motion than state-of-the-art data-driven methods. With conventional path-finding algorithms, the generated human bodies can realistically move long distances for a long period of time in the scene. Code is released for research purposes at: \url{https://yz-cnsdqz.github.io/eigenmotion/GAMMA/}

cs.CV↗

arXiv2022

ERGO: Event Relational Graph Transformer for Document-level Event Causality Identification

Document-level Event Causality Identification (DECI) aims to identify causal relations between event pairs in a document. It poses a great challenge of across-sentence reasoning without clear causal indicators. In this paper, we propose a novel Event Relational Graph TransfOrmer (ERGO) framework for DECI, which improves existing state-of-the-art (SOTA) methods upon two aspects. First, we formulate DECI as a node classification problem by constructing an event relational graph, without the needs of prior knowledge or tools. Second, ERGO seamlessly integrates event-pair relation classification and global inference, which leverages a Relational Graph Transformer (RGT) to capture the potential causal chain. Besides, we introduce edge-building strategies and adaptive focal loss to deal with the massive false positives caused by common spurious correlation. Extensive experiments on two benchmark datasets show that ERGO significantly outperforms previous SOTA methods (13.1% F1 gains on average). We have conducted extensive quantitative analysis and case studies to provide insights for future research directions (Section 4.8).

cs.CL↗

arXiv2022

Diverse Preference Augmentation with Multiple Domains for Cold-start Recommendations

Cold-start issues have been more and more challenging for providing accurate recommendations with the fast increase of users and items. Most existing approaches attempt to solve the intractable problems via content-aware recommendations based on auxiliary information and/or cross-domain recommendations with transfer learning. Their performances are often constrained by the extremely sparse user-item interactions, unavailable side information, or very limited domain-shared users. Recently, meta-learners with meta-augmentation by adding noises to labels have been proven to be effective to avoid overfitting and shown good performance on new tasks. Motivated by the idea of meta-augmentation, in this paper, by treating a user's preference over items as a task, we propose a so-called Diverse Preference Augmentation framework with multiple source domains based on meta-learning (referred to as MetaDPA) to i) generate diverse ratings in a new domain of interest (known as target domain) to handle overfitting on the case of sparse interactions, and to ii) learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues. Specifically, we first conduct multi-source domain adaptation by dual conditional variational autoencoders and impose a Multi-domain InfoMax (MDI) constraint on the latent representations to learn domain-shared and domain-specific preference properties. To avoid overfitting, we add a Mutually-Exclusive (ME) constraint on the output of decoders to generate diverse ratings given content data. Finally, these generated diverse ratings and the original ratings are introduced into the meta-training procedure to learn a preference meta-learner, which produces good generalization ability on cold-start recommendation tasks. Experiments on real-world datasets show our proposed MetaDPA clearly outperforms the current state-of-the-art baselines.

cs.IR↗

arXiv2022

AMCAD: Adaptive Mixed-Curvature Representation based Advertisement Retrieval System

Graph embedding based retrieval has become one of the most popular techniques in the information retrieval community and search engine industry. The classical paradigm mainly relies on the flat Euclidean geometry. In recent years, hyperbolic (negative curvature) and spherical (positive curvature) representation methods have shown their superiority to capture hierarchical and cyclic data structures respectively. However, in industrial scenarios such as e-commerce sponsored search platforms, the large-scale heterogeneous query-item-advertisement interaction graphs often have multiple structures coexisting. Existing methods either only consider a single geometry space, or combine several spaces manually, which are incapable and inflexible to model the complexity and heterogeneity in the real scenario. To tackle this challenge, we present a web-scale Adaptive Mixed-Curvature ADvertisement retrieval system (AMCAD) to automatically capture the complex and heterogeneous graph structures in non-Euclidean spaces. Specifically, entities are represented in adaptive mixed-curvature spaces, where the types and curvatures of the subspaces are trained to be optimal combinations. Besides, an attentive edge-wise space projector is designed to model the similarities between heterogeneous nodes according to local graph structures and the relation types. Moreover, to deploy AMCAD in Taobao, one of the largest ecommerce platforms with hundreds of million users, we design an efficient two-layer online retrieval framework for the task of graph based advertisement retrieval. Extensive evaluations on real-world datasets and A/B tests on online traffic are conducted to illustrate the effectiveness of the proposed system.

cs.IR↗