arXiv subjects

Yong Xu

Publications and source records attributed to Yong Xu.

At least 307 records · Page 17Linked to original sources

arXiv2021

Pulsating propagation and extinction of hydrogen detonations in ultrafine water sprays

The Eulerian-Lagrangian method is applied to simulate pulsating propagation and extinction of stoichiometric hydrogen/oxygen/argon detonations in ultrafine water sprays. Three detonation propagation modes are found: (1) pulsating propagation, (2) propagation followed by extinction, and (3) immediate extinction. For pulsating detonation, within one cycle, the propagation speeds and the distance between reaction front (RF) and shock front (SF) change periodically. The pulsating phenomenon originates from the interactions between gas dynamics, chemical kinetics, and droplet dynamics inside the induction zone. Multiple pressure waves are emanated from the RF within one cycle, which overtake and intensify the lead SF. An autoigniting spot arises in the shocked gas after the contact surface. The relative locations of SF, RF, shock-frame sonic point, and two-phase contact surface remain unchanged in a pulsating cycle, but their distances have periodic variations. Moreover, the unsteady behaviors of detonation extinction include continuously increased distance between the RF and SF and quickly reduced pressure peaks, temperature, and combustion heat release. The decoupling of RF and SF leads to significantly increasing chemical timescale of the shocked mixture. The hydrodynamic structure also changes considerably when detonation extinction occurs. Moreover, the predicted map of detonation propagation and extinction illustrates that the critical mass loading for detonation extinction reduces significantly when the droplet size becomes smaller. It is also found that for the same droplet size, the average detonation speed monotonically decreases with water mass loading. However, detonation speed and pulsating frequency have a non-monotonic dependence on droplet size under a constant water mass loading.

physics.flu-dyn↗

arXiv2021

Critical condition and transient evolution of methane detonation extinction by fine water droplet curtains

Two-dimensional numerical simulations with Eulerian-Lagrangian method and detailed chemical mechanism are conducted to study the methane detonation propagation across a water curtain with finite thickness. The critical length of the water curtain with sprayed droplets is determined through parametric simulations with different water mass loadings and droplet sizes. The influence of water curtain length on the methane detonation is examined by the trajectories of peak pressure and time history of average heat release rate. The results indicate that the water curtain not only inhibit the incident detonation wave, but also prevent the detonation re-ignition after the incident wave is quenched. Moreover, unsteady response of gaseous methane detonation to water curtain are analyzed. The detonation re-initiation process behind the water curtain near the critical loading is also captured. In addition, mechanism of detonation inhibition with fine water droplets are discussed. It is found that energy and momentum exchanges start immediately when the detonation wave enters the water curtain area, but the mass transfer starts well behind the detonation wave due to the finitely long droplet heating duration. It is shown that the convective heat transfer by water droplets plays a significant role in quenching a detonation.

physics.flu-dyn↗

arXiv2021

Knowledge-aware Coupled Graph Neural Network for Social Recommendation

Social recommendation task aims to predict users' preferences over items with the incorporation of social connections among users, so as to alleviate the sparse issue of collaborative filtering. While many recent efforts show the effectiveness of neural network-based social recommender systems, several important challenges have not been well addressed yet: (i) The majority of models only consider users' social connections, while ignoring the inter-dependent knowledge across items; (ii) Most of existing solutions are designed for singular type of user-item interactions, making them infeasible to capture the interaction heterogeneity; (iii) The dynamic nature of user-item interactions has been less explored in many social-aware recommendation techniques. To tackle the above challenges, this work proposes a Knowledge-aware Coupled Graph Neural Network (KCGN) that jointly injects the inter-dependent knowledge across items and users into the recommendation framework. KCGN enables the high-order user- and item-wise relation encoding by exploiting the mutual information for global graph structure awareness. Additionally, we further augment KCGN with the capability of capturing dynamic multi-typed user-item interactive patterns. Experimental studies on real-world datasets show the effectiveness of our method against many strong baselines in a variety of settings. Source codes are available at: https://github.com/xhcdream/KCGN.

cs.IR↗

arXiv2021

Graph-Enhanced Multi-Task Learning of Multi-Level Transition Dynamics for Session-based Recommendation

Session-based recommendation plays a central role in a wide spectrum of online applications, ranging from e-commerce to online advertising services. However, the majority of existing session-based recommendation techniques (e.g., attention-based recurrent network or graph neural network) are not well-designed for capturing the complex transition dynamics exhibited with temporally-ordered and multi-level inter-dependent relation structures. These methods largely overlook the relation hierarchy of item transitional patterns. In this paper, we propose a multi-task learning framework with Multi-level Transition Dynamics (MTD), which enables the jointly learning of intra- and inter-session item transition dynamics in automatic and hierarchical manner. Towards this end, we first develop a position-aware attention mechanism to learn item transitional regularities within individual session. Then, a graph-structured hierarchical relation encoder is proposed to explicitly capture the cross-session item transitions in the form of high-order connectivities by performing embedding propagation with the global graph context. The learning process of intra- and inter-session transition dynamics are integrated, to preserve the underlying low- and high-level item relationships in a common latent space. Extensive experiments on three real-world datasets demonstrate the superiority of MTD as compared to state-of-the-art baselines.

cs.IR↗

arXiv2021

Knowledge-Enhanced Hierarchical Graph Transformer Network for Multi-Behavior Recommendation

Accurate user and item embedding learning is crucial for modern recommender systems. However, most existing recommendation techniques have thus far focused on modeling users' preferences over singular type of user-item interactions. Many practical recommendation scenarios involve multi-typed user interactive behaviors (e.g., page view, add-to-favorite and purchase), which presents unique challenges that cannot be handled by current recommendation solutions. In particular: i) complex inter-dependencies across different types of user behaviors; ii) the incorporation of knowledge-aware item relations into the multi-behavior recommendation framework; iii) dynamic characteristics of multi-typed user-item interactions. To tackle these challenges, this work proposes a Knowledge-Enhanced Hierarchical Graph Transformer Network (KHGT), to investigate multi-typed interactive patterns between users and items in recommender systems. Specifically, KHGT is built upon a graph-structured neural architecture to i) capture type-specific behavior characteristics; ii) explicitly discriminate which types of user-item interactions are more important in assisting the forecasting task on the target behavior. Additionally, we further integrate the graph attention layer with the temporal encoding strategy, to empower the learned embeddings be reflective of both dedicated multiplex user-item and item-item relations, as well as the underlying interaction dynamics. Extensive experiments conducted on three real-world datasets show that KHGT consistently outperforms many state-of-the-art recommendation methods across various evaluation settings. Our implementation code is available at https://github.com/akaxlh/KHGT.

cs.IR↗

arXiv2021

Traffic Flow Forecasting with Spatial-Temporal Graph Diffusion Network

Accurate forecasting of citywide traffic flow has been playing critical role in a variety of spatial-temporal mining applications, such as intelligent traffic control and public risk assessment. While previous work has made significant efforts to learn traffic temporal dynamics and spatial dependencies, two key limitations exist in current models. First, only the neighboring spatial correlations among adjacent regions are considered in most existing methods, and the global inter-region dependency is ignored. Additionally, these methods fail to encode the complex traffic transition regularities exhibited with time-dependent and multi-resolution in nature. To tackle these challenges, we develop a new traffic prediction framework-Spatial-Temporal Graph Diffusion Network (ST-GDN). In particular, ST-GDN is a hierarchically structured graph neural architecture which learns not only the local region-wise geographical dependencies, but also the spatial semantics from a global perspective. Furthermore, a multi-scale attention network is developed to empower ST-GDN with the capability of capturing multi-level temporal dynamics. Experiments on several real-life traffic datasets demonstrate that ST-GDN outperforms different types of state-of-the-art baselines. Source codes of implementations are available at https://github.com/jill001/ST-GDN.

cs.LG↗

arXiv2021

Global Context Enhanced Social Recommendation with Hierarchical Graph Neural Networks

Social recommendation which aims to leverage social connections among users to enhance the recommendation performance. With the revival of deep learning techniques, many efforts have been devoted to developing various neural network-based social recommender systems, such as attention mechanisms and graph-based message passing frameworks. However, two important challenges have not been well addressed yet: (i) Most of existing social recommendation models fail to fully explore the multi-type user-item interactive behavior as well as the underlying cross-relational inter-dependencies. (ii) While the learned social state vector is able to model pair-wise user dependencies, it still has limited representation capacity in capturing the global social context across users. To tackle these limitations, we propose a new Social Recommendation framework with Hierarchical Graph Neural Networks (SR-HGNN). In particular, we first design a relation-aware reconstructed graph neural network to inject the cross-type collaborative semantics into the recommendation framework. In addition, we further augment SR-HGNN with a social relation encoder based on the mutual information learning paradigm between low-level user embeddings and high-level global representation, which endows SR-HGNN with the capability of capturing the global social contextual signals. Empirical results on three public benchmarks demonstrate that SR-HGNN significantly outperforms state-of-the-art recommendation methods. Source codes are available at: https://github.com/xhcdream/SR-HGNN.

cs.IR↗

arXiv2021

Multiplex Behavioral Relation Learning for Recommendation via Memory Augmented Transformer Network

Capturing users' precise preferences is of great importance in various recommender systems (eg., e-commerce platforms), which is the basis of how to present personalized interesting product lists to individual users. In spite of significant progress has been made to consider relations between users and items, most of the existing recommendation techniques solely focus on singular type of user-item interactions. However, user-item interactive behavior is often exhibited with multi-type (e.g., page view, add-to-favorite and purchase) and inter-dependent in nature. The overlook of multiplex behavior relations can hardly recognize the multi-modal contextual signals across different types of interactions, which limit the feasibility of current recommendation methods. To tackle the above challenge, this work proposes a Memory-Augmented Transformer Networks (MATN), to enable the recommendation with multiplex behavioral relational information, and joint modeling of type-specific behavioral context and type-wise behavior inter-dependencies, in a fully automatic manner. In our MATN framework, we first develop a transformer-based multi-behavior relation encoder, to make the learned interaction representations be reflective of the cross-type behavior relations. Furthermore, a memory attention network is proposed to supercharge MATN capturing the contextual signals of different types of behavior into the category-specific latent embedding space. Finally, a cross-behavior aggregation component is introduced to promote the comprehensive collaboration across type-aware interaction behavior representations, and discriminate their inherent contributions in assisting recommendations. Extensive experiments on two benchmark datasets and a real-world e-commence user behavior data demonstrate significant improvements obtained by MATN over baselines. Codes are available at: https://github.com/akaxlh/MATN.

cs.IR↗

arXiv2021

Graph Meta Network for Multi-Behavior Recommendation

Modern recommender systems often embed users and items into low-dimensional latent representations, based on their observed interactions. In practical recommendation scenarios, users often exhibit various intents which drive them to interact with items with multiple behavior types (e.g., click, tag-as-favorite, purchase). However, the diversity of user behaviors is ignored in most of the existing approaches, which makes them difficult to capture heterogeneous relational structures across different types of interactive behaviors. Exploring multi-typed behavior patterns is of great importance to recommendation systems, yet is very challenging because of two aspects: i) The complex dependencies across different types of user-item interactions; ii) Diversity of such multi-behavior patterns may vary by users due to their personalized preference. To tackle the above challenges, we propose a Multi-Behavior recommendation framework with Graph Meta Network to incorporate the multi-behavior pattern modeling into a meta-learning paradigm. Our developed MB-GMN empowers the user-item interaction learning with the capability of uncovering type-dependent behavior representations, which automatically distills the behavior heterogeneity and interaction diversity for recommendations. Extensive experiments on three real-world datasets show the effectiveness of MB-GMN by significantly boosting the recommendation performance as compared to various state-of-the-art baselines. The source code is available athttps://github.com/akaxlh/MB-GMN.

cs.IR↗

arXiv2021

Social Recommendation with Self-Supervised Metagraph Informax Network

In recent years, researchers attempt to utilize online social information to alleviate data sparsity for collaborative filtering, based on the rationale that social networks offers the insights to understand the behavioral patterns. However, due to the overlook of inter-dependent knowledge across items (e.g., categories of products), existing social recommender systems are insufficient to distill the heterogeneous collaborative signals from both user and item sides. In this work, we propose a Self-Supervised Metagraph Infor-max Network (SMIN) which investigates the potential of jointly incorporating social- and knowledge-aware relational structures into the user preference representation for recommendation. To model relation heterogeneity, we design a metapath-guided heterogeneous graph neural network to aggregate feature embeddings from different types of meta-relations across users and items, em-powering SMIN to maintain dedicated representations for multi-faceted user- and item-wise dependencies. Additionally, to inject high-order collaborative signals, we generalize the mutual information learning paradigm under the self-supervised graph-based collaborative filtering. This endows the expressive modeling of user-item interactive patterns, by exploring global-level collaborative relations and underlying isomorphic transformation property of graph topology. Experimental results on several real-world datasets demonstrate the effectiveness of our SMIN model over various state-of-the-art recommendation methods. We release our source code at https://github.com/SocialRecsys/SMIN.

cs.IR↗

arXiv2021

Dual-Stream Reciprocal Disentanglement Learning for Domain Adaptation Person Re-Identification

Since human-labeled samples are free for the target set, unsupervised person re-identification (Re-ID) has attracted much attention in recent years, by additionally exploiting the source set. However, due to the differences on camera styles, illumination and backgrounds, there exists a large gap between source domain and target domain, introducing a great challenge on cross-domain matching. To tackle this problem, in this paper we propose a novel method named Dual-stream Reciprocal Disentanglement Learning (DRDL), which is quite efficient in learning domain-invariant features. In DRDL, two encoders are first constructed for id-related and id-unrelated feature extractions, which are respectively measured by their associated classifiers. Furthermore, followed by an adversarial learning strategy, both streams reciprocally and positively effect each other, so that the id-related features and id-unrelated features are completely disentangled from a given image, allowing the encoder to be powerful enough to obtain the discriminative but domain-invariant features. In contrast to existing approaches, our proposed method is free from image generation, which not only reduces the computational complexity remarkably, but also removes redundant information from id-related features. Extensive experiments substantiate the superiority of our proposed method compared with the state-of-the-arts. The source code has been released in https://github.com/lhf12278/DRDL.

cs.CV↗

arXiv2021

Polynomial Inflation and Dark Matter

We present a minimal UV complete framework to embed inflation and dark matter by extending the standard model with a singlet real scalar field (the inflaton) and a singlet fermonic field acting as dark matter. The inflaton features the most general renormalizable polynomial up to quartic order, which is flat due to the existence of a perturbed inflection-point, comfortably fitting CMB measurements. We also analyze (p)reheating by considering the Higgs production via inflaton decay. In the early universe, dark matter can be generated by the mediation of gravitons or inflatons. However, the production via the direct decay of the inflatons dominates, making viable a large range of dark matter masses, from $\mathcal{O}(10^{-5})$ GeV to $\mathcal{O}(10^{11})$ GeV.

hep-ph↗

arXiv2021

Axion Dark Matter in the Time of Primordial Black Holes

We investigate the production of QCD axion dark matter in a nonstandard cosmological era triggered by primordial black holes (PBHs) that fully evaporate before the onset of BBN. Even if PBHs cannot emit the whole axion cold dark matter abundance through Hawking radiation, they can have a strong impact on the dark matter produced via the misalignment mechanism. First, the oscillation temperature of axions reduces if there is a PBH dominated era, and second, PBH evaporation injects entropy to the standard model, diluting the axion relic abundance originally produced. The axion window is therefore enlarged, reaching masses as light as $\sim 10^{-8}$ eV and decay constants as large as $f_{a}\sim 10^{14}$ GeV without fine tuning the misalignment angle. Such small masses are in the reach of future detectors as ABRACADABRA, KLASH, and ADMX, if the axion couples to photons. Additionally, the axions radiated by PBHs contribute to $ΔN_\text{eff}$ within the projected reach of the future CMB Stage 4 experiment.

hep-ph↗

arXiv2021

Heterogeneous relational message passing networks for molecular dynamics simulations

With many frameworks based on message passing neural networks proposed to predict molecular and bulk properties, machine learning methods have tremendously shifted the paradigms of computational sciences underpinning physics, material science, chemistry, and biology. While existing machine learning models have yielded superior performances in many occasions, most of them model and process molecular systems in terms of homogeneous graph, which severely limits the expressive power for representing diverse interactions. In practice, graph data with multiple node and edge types is ubiquitous and more appropriate for molecular systems. Thus, we propose the heterogeneous relational message passing network (HermNet), an end-to-end heterogeneous graph neural networks, to efficiently express multiple interactions in a single model with {\it ab initio} accuracy. HermNet performs impressively against many top-performing models on both molecular and extended systems. Specifically, HermNet outperforms other tested models in nearly 75\%, 83\% and 94\% of tasks on MD17, QM9 and extended systems datasets, respectively. Finally, we elucidate how the design of HermNet is compatible with quantum mechanics from the perspective of the density functional theory. Besides, HermNet is a universal framework, whose sub-networks could be replaced by other advanced models.

cs.LG↗

arXiv2021

TeCANet: Temporal-Contextual Attention Network for Environment-Aware Speech Dereverberation

In this paper, we exploit the effective way to leverage contextual information to improve the speech dereverberation performance in real-world reverberant environments. We propose a temporal-contextual attention approach on the deep neural network (DNN) for environment-aware speech dereverberation, which can adaptively attend to the contextual information. More specifically, a FullBand based Temporal Attention approach (FTA) is proposed, which models the correlations between the fullband information of the context frames. In addition, considering the difference between the attenuation of high frequency bands and low frequency bands (high frequency bands attenuate faster than low frequency bands) in the room impulse response (RIR), we also propose a SubBand based Temporal Attention approach (STA). In order to guide the network to be more aware of the reverberant environments, we jointly optimize the dereverberation network and the reverberation time (RT60) estimator in a multi-task manner. Our experimental results indicate that the proposed method outperforms our previously proposed reverberation-time-aware DNN and the learned attention weights are fully physical consistent. We also report a preliminary yet promising dereverberation and recognition experiment on real test data.

eess.AS↗

arXiv2021

Fully Non-Homogeneous Atmospheric Scattering Modeling with Convolutional Neural Networks for Single Image Dehazing

In recent years, single image dehazing models (SIDM) based on atmospheric scattering model (ASM) have achieved remarkable results. However, it is noted that ASM-based SIDM degrades its performance in dehazing real world hazy images due to the limited modelling ability of ASM where the atmospheric light factor (ALF) and the angular scattering coefficient (ASC) are assumed as constants for one image. Obviously, the hazy images taken in real world cannot always satisfy this assumption. Such generating modelling mismatch between the real-world images and ASM sets up the upper bound of trained ASM-based SIDM for dehazing. Bearing this in mind, in this study, a new fully non-homogeneous atmospheric scattering model (FNH-ASM) is proposed for well modeling the hazy images under complex conditions where ALF and ASC are pixel dependent. However, FNH-ASM brings difficulty in practical application. In FNH-ASM based SIDM, the estimation bias of parameters at different positions lead to different distortion of dehazing result. Hence, in order to reduce the influence of parameter estimation bias on dehazing results, two new cost sensitive loss functions, beta-Loss and D-Loss, are innovatively developed for limiting the parameter bias of sensitive positions that have a greater impact on the dehazing result. In the end, based on FNH-ASM, an end-to-end CNN-based dehazing network, FNHD-Net, is developed, which applies beta-Loss and D-Loss. Experimental results demonstrate the effectiveness and superiority of our proposed FNHD-Net for dehazing on both synthetic and real-world images. And the performance improvement of our method increases more obviously in dense and heterogeneous haze scenes.

cs.CV↗

arXiv2021

Small Field Polynomial Inflation: Reheating, Radiative Stability and Lower Bound

We revisit the renormalizable polynomial inflection point model of inflation, focusing on the small field scenario which can be treated fully analytically. In particular, the running of the spectral index is predicted to be $α= -1.43 \times 10^{-3} +5.56 \times 10^{-5} \left(N_{\rm CMB}-65 \right)$, which might be tested in future. We also analyze reheating through perturbative inflaton decays to either fermionic or bosonic final states via a trilinear coupling. The lower bound on the reheating temperature from successful Big Bang nucleosynthesis gives lower bounds for these couplings; on the other hand radiative stability of the inflaton potential leads to upper bounds. In combination this leads to a lower bound on the location $ϕ_0$ of the near inflection point, $ϕ_0 > 3 \cdot 10^{-5}$ in Planckian units. The Hubble parameter during inflation can be as low as $H_{\rm inf} \sim 1$ MeV, or as high as $\sim 10^{10}$ GeV. Similarly, the reheating temperature can lie between its lower bound of $\sim 4$ MeV and about $4 \cdot 10^8 \ (10^{11})$ GeV for fermionic (bosonic) inflaton decays. We finally speculate on the "prehistory" of the universe in this scenario, which might have included an epoch of eternal inflation.

hep-ph↗

arXiv2021

Light-Tunable Surface State and Hybridization Gap in Magnetic Topological Insulator MnBi$_8$Te$_{13}$

MnBi$_8$Te$_{13}$ is an intrinsic ferromagnetic (FM) topological insulator with different complex surface terminations. Resolving the electronic structures of different termination surfaces and manipulation of the electronic state are important. Here, by using micrometer spot time- and angle-resolved photoemission spectroscopy ($μ$-TrARPES), we resolve the electronic structures and reveal the ultrafast dynamics upon photoexcitation. Photoinduced filling of the surface state hybridization gap is observed for the Bi$_2$Te$_3$ quintuple layer directly above MnBi$_2$Te$_4$ accompanied by a nontrivial shift of the surface state, suggesting light-tunable interlayer interaction. Relaxation of photoexcited electrons and holes is observed within 1-2 ps. Our work reveals photoexcitation as a potential control knob for tailoring the interlayer interaction and surface state of MnBi$_8$Te$_{13}$.

cond-mat.mtrl-sci↗