arXiv subjects

Zhiqiang Zhang

Publications and source records attributed to Zhiqiang Zhang.

At least 163 records · Page 9Linked to original sources

arXiv2020

Heterogeneous Graph Neural Network for Recommendation

The prosperous development of e-commerce has spawned diverse recommendation systems. As a matter of fact, there exist rich and complex interactions among various types of nodes in real-world recommendation systems, which can be constructed as heterogeneous graphs. How learn representative node embedding is the basis and core of the personalized recommendation system. Meta-path is a widely used structure to capture the semantics beneath such interactions and show potential ability in improving node embedding. In this paper, we propose Heterogeneous Graph neural network for Recommendation (HGRec) which injects high-order semantic into node embedding via aggregating multi-hops meta-path based neighbors and fuses rich semantics via multiple meta-paths based on attention mechanism to get comprehensive node embedding. Experimental results demonstrate the importance of rich high-order semantics and also show the potentially good interpretability of HGRec.

cs.SI↗

arXiv2020

Precision measurement of the $^3D_1$ and $^3D_2$ quadrupole moments in Lu$^+$

Precision measurements of the Lu$^+$ $^3D_1$ and $^3D_2$ quadrupole moments have been carried out giving $Θ(^3D_1)=0.63862(74)\,e a_0^2$ and $Θ(^3D_2)=0.8602(14)\,e a_0^2$, respectively. The measurements utilize the differential shift between ions in a multi-ion crystal so that effects of external field gradients do not contribute leaving only the well defined Coulomb interaction. At this level of precision, hyperfine-mediated corrections will likely be important.

physics.atom-ph↗

arXiv2020

The cause of extremely long-lasting room-temperature persistent photoconductivity in SrTiO$_3$ and related materials

It has been recently revealed that strontium titanate (SrTiO$_3$) displays persistent photoconductivity with unique characteristics: it occurs at room temperature and lasts over a very long period of time. Illumination of SrTiO$_3$ crystals at room temperature with sub-bandgap light reduces the electrical resistance by three orders of magnitude and persists for weeks or longer (Tarun ${\it et\: al.}$, Phys. Rev. Lett. ${\bf 111}$, 187403 (2013)). Experiments indicate that oxygen vacancy and hydrogen play important roles, yet the microscopic mechanism responsible for this remarkable effect has remained unidentified. Using hybrid density functional theory calculations we show that an instability associated with substitutional hydrogen H$_{\rm O}^+$ under illumination, which becomes doubly ionized and leaves the oxygen site, can explain the experimental observations. H$_{\rm O}$ then turns into an interstitial hydrogen and an oxygen vacancy, leading to excess carriers in the conduction band. This phenomenon is not exclusive to SrTiO$_3$, but it is also predicted to occur in other oxides. Interestingly, this phenomenon represents an elegant way of proving the existence of hydrogen substituting on an oxygen site (H$_{\rm O}$), forming an interesting, and rarely observed, type of three-center two-electron bond.

cond-mat.mtrl-sci↗

arXiv2020

Bandit Samplers for Training Graph Neural Networks

Several sampling algorithms with variance reduction have been proposed for accelerating the training of Graph Convolution Networks (GCNs). However, due to the intractable computation of optimal sampling distribution, these sampling algorithms are suboptimal for GCNs and are not applicable to more general graph neural networks (GNNs) where the message aggregator contains learned weights rather than fixed weights, such as Graph Attention Networks (GAT). The fundamental reason is that the embeddings of the neighbors or learned weights involved in the optimal sampling distribution are changing during the training and not known a priori, but only partially observed when sampled, thus making the derivation of an optimal variance reduced samplers non-trivial. In this paper, we formulate the optimization of the sampling variance as an adversary bandit problem, where the rewards are related to the node embeddings and learned weights, and can vary constantly. Thus a good sampler needs to acquire variance information about more neighbors (exploration) while at the same time optimizing the immediate sampling variance (exploit). We theoretically show that our algorithm asymptotically approaches the optimal variance within a factor of 3. We show the efficiency and effectiveness of our approach on multiple datasets.

cs.LG↗

arXiv2020

ATBRG: Adaptive Target-Behavior Relational Graph Network for Effective Recommendation

Recommender system (RS) devotes to predicting user preference to a given item and has been widely deployed in most web-scale applications. Recently, knowledge graph (KG) attracts much attention in RS due to its abundant connective information. Existing methods either explore independent meta-paths for user-item pairs over KG, or employ graph neural network (GNN) on whole KG to produce representations for users and items separately. Despite effectiveness, the former type of methods fails to fully capture structural information implied in KG, while the latter ignores the mutual effect between target user and item during the embedding propagation. In this work, we propose a new framework named Adaptive Target-Behavior Relational Graph network (ATBRG for short) to effectively capture structural relations of target user-item pairs over KG. Specifically, to associate the given target item with user behaviors over KG, we propose the graph connect and graph prune techniques to construct adaptive target-behavior relational graph. To fully distill structural information from the sub-graph connected by rich relations in an end-to-end fashion, we elaborate on the model design of ATBRG, equipped with relation-aware extractor layer and representation activation layer. We perform extensive experiments on both industrial and benchmark datasets. Empirical results show that ATBRG consistently and significantly outperforms state-of-the-art methods. Moreover, ATBRG has also achieved a performance improvement of 5.1% on CTR metric after successful deployment in one popular recommendation scenario of Taobao APP.

cs.IR↗

arXiv2020

NetDP: An Industrial-Scale Distributed Network Representation Framework for Default Prediction in Ant Credit Pay

Ant Credit Pay is a consumer credit service in Ant Financial Service Group. Similar to credit card, loan default is one of the major risks of this credit product. Hence, effective algorithm for default prediction is the key to losses reduction and profits increment for the company. However, the challenges facing in our scenario are different from those in conventional credit card service. The first one is scalability. The huge volume of users and their behaviors in Ant Financial requires the ability to process industrial-scale data and perform model training efficiently. The second challenges is the cold-start problem. Different from the manual review for credit card application in conventional banks, the credit limit of Ant Credit Pay is automatically offered to users based on the knowledge learned from big data. However, default prediction for new users is suffered from lack of enough credit behaviors. It requires that the proposal should leverage other new data source to alleviate the cold-start problem. Considering the above challenges and the special scenario in Ant Financial, we try to incorporate default prediction with network information to alleviate the cold-start problem. In this paper, we propose an industrial-scale distributed network representation framework, termed NetDP, for default prediction in Ant Credit Pay. The proposal explores network information generated by various interaction between users, and blends unsupervised and supervised network representation in a unified framework for default prediction problem. Moreover, we present a parameter-server-based distributed implement of our proposal to handle the scalability challenge. Experimental results demonstrate the effectiveness of our proposal, especially in cold-start problem, as well as the efficiency for industrial-scale dataset.

cs.LG↗

arXiv2020

Distributed Deep Forest and its Application to Automatic Detection of Cash-out Fraud

Internet companies are facing the need for handling large-scale machine learning applications on a daily basis and distributed implementation of machine learning algorithms which can handle extra-large scale tasks with great performance is widely needed. Deep forest is a recently proposed deep learning framework which uses tree ensembles as its building blocks and it has achieved highly competitive results on various domains of tasks. However, it has not been tested on extremely large scale tasks. In this work, based on our parameter server system, we developed the distributed version of deep forest. To meet the need for real-world tasks, many improvements are introduced to the original deep forest model, including MART (Multiple Additive Regression Tree) as base learners for efficiency and effectiveness consideration, the cost-based method for handling prevalent class-imbalanced data, MART based feature selection for high dimension data and different evaluation metrics for automatically determining of the cascade level. We tested the deep forest model on an extra-large scale task, i.e., automatic detection of cash-out fraud, with more than 100 millions of training samples. Experimental results showed that the deep forest model has the best performance according to the evaluation metrics from different perspectives even with very little effort for parameter tuning. This model can block fraud transactions in a large amount of money each day. Even compared with the best-deployed model, the deep forest model can additionally bring into a significant decrease in economic loss each day.

cs.LG↗

arXiv2020

AGL: a Scalable System for Industrial-purpose Graph Machine Learning

Machine learning over graphs have been emerging as powerful learning tools for graph data. However, it is challenging for industrial communities to leverage the techniques, such as graph neural networks (GNNs), and solve real-world problems at scale because of inherent data dependency in the graphs. As such, we cannot simply train a GNN with classic learning systems, for instance parameter server that assumes data parallel. Existing systems store the graph data in-memory for fast accesses either in a single machine or graph stores from remote. The major drawbacks are in three-fold. First, they cannot scale because of the limitations on the volume of the memory, or the bandwidth between graph stores and workers. Second, they require extra development of graph stores without well exploiting mature infrastructures such as MapReduce that guarantee good system properties. Third, they focus on training but ignore the optimization of inference over graphs, thus makes them an unintegrated system. In this paper, we design AGL, a scalable, fault-tolerance and integrated system, with fully-functional training and inference for GNNs. Our system design follows the message passing scheme underlying the computations of GNNs. We design to generate the $k$-hop neighborhood, an information-complete subgraph for each node, as well as do the inference simply by merging values from in-edge neighbors and propagating values to out-edge neighbors via MapReduce. In addition, the $k$-hop neighborhood contains information-complete subgraphs for each node, thus we simply do the training on parameter servers due to data independency. Our system AGL, implemented on mature infrastructures, can finish the training of a 2-layer graph attention network on a graph with billions of nodes and hundred billions of edges in 14 hours, and complete the inference in 1.2 hour.

cs.SI↗

arXiv2020

Precision measurements on the $^{138}$Ba$^+$ $6s^2S_{1/2}-5d^2D_{5/2}$ clock transition

Measurement of the $^{138}$Ba$^+$ ${}^2S_{1/2} - {}^2D_{5/2}$ clock transition frequency and $D_{5/2}$ Landé $g_J$ factor are reported. The clock transition frequency $ν_{\mathrm{Ba}^+}=170\,126\,432\,449\,333.31\pm(0.39)_\mathrm{stat}\pm(0.29)_\mathrm{sys}\,$Hz, is obtained with accuracy limited by the frequency calibration of the maser used as a reference oscillator. The Landé $g_J$-factor for the ${}^2D_{5/2}$ level is determined to be $g_{D}=1.200\,367\,39(24)$, which is a 30-fold improvement on previous measurements. The $g$-factor measurements are corrected for an ac-magnetic field from trap-drive-induced currents in the electrodes, and data taken over a range of magnetic fields underscores the importance of accounting for this systematic.

physics.atom-ph↗

arXiv2020

DSSLP: A Distributed Framework for Semi-supervised Link Prediction

Link prediction is widely used in a variety of industrial applications, such as merchant recommendation, fraudulent transaction detection, and so on. However, it's a great challenge to train and deploy a link prediction model on industrial-scale graphs with billions of nodes and edges. In this work, we present a scalable and distributed framework for semi-supervised link prediction problem (named DSSLP), which is able to handle industrial-scale graphs. Instead of training model on the whole graph, DSSLP is proposed to train on the \emph{$k$-hops neighborhood} of nodes in a mini-batch setting, which helps reduce the scale of the input graph and distribute the training procedure. In order to generate negative examples effectively, DSSLP contains a distributed batched runtime sampling module. It implements uniform and dynamic sampling approaches, and is able to adaptively construct positive and negative examples to guide the training process. Moreover, DSSLP proposes a model-split strategy to accelerate the speed of inference process of the link prediction task. Experimental results demonstrate that the effectiveness and efficiency of DSSLP in serval public datasets as well as real-world datasets of industrial-scale graphs.

cs.SI↗

arXiv2020

Magic wavelength of the $^{138}$Ba$^+$ $6s\;{}^2S_{1/2}-5d\;{}^2D_{5/2}$ clock transition

The zero crossing of the dynamic differential scalar polarizability of the $S_{1/2}-D_{5/2}$ clock transition in $^{138}$Ba$^+$ has been determined to be $459.1614(28)\,$THz. Together with previously determined matrix elements and branching ratios, this tightly constrains the dynamic differential scalar polarizability of the clock transition over a large wavelength range ($\gtrsim 700\,$nm). In particular it allows an estimate of the blackbody radiation shift of the clock transition at room temperature.

physics.atom-ph↗

arXiv2020

Branching fractions for $P_{3/2}$ decays in Ba$^+$

Branching fractions for decays from the $P_{3/2}$ level in $^{138}$Ba$^+$ have been measured with a single laser-cooled ion. Decay probabilities to $S_{1/2}$, $D_{3/2}$ and $D_{5/2}$ are determined to be $0.741716(71)$, $0.028031(23)$ and $0.230253(61)$, respectively, which are an order of magnitude improvement over previous results. Our methodology only involves optical pumping and state detection, and is hence relatively free of systematic effects. Measurements are carried out in two different ways to check for consistency. Our analysis also includes a measurement of the $D_{5/2}$ lifetime, for which we obtain 30.14(40)\,s.

physics.atom-ph↗

arXiv2020

Graph Representation Learning for Merchant Incentive Optimization in Mobile Payment Marketing

Mobile payment such as Alipay has been widely used in our daily lives. To further promote the mobile payment activities, it is important to run marketing campaigns under a limited budget by providing incentives such as coupons, commissions to merchants. As a result, incentive optimization is the key to maximizing the commercial objective of the marketing campaign. With the analyses of online experiments, we found that the transaction network can subtly describe the similarity of merchants' responses to different incentives, which is of great use in the incentive optimization problem. In this paper, we present a graph representation learning method atop of transaction networks for merchant incentive optimization in mobile payment marketing. With limited samples collected from online experiments, our end-to-end method first learns merchant representations based on an attributed transaction networks, then effectively models the correlations between the commercial objectives each merchant may achieve and the incentives under varying treatments. Thus we are able to model the sensitivity to incentive for each merchant, and spend the most budgets on those merchants that show strong sensitivities in the marketing campaign. Extensive offline and online experimental results at Alipay demonstrate the effectiveness of our proposed approach.

cs.SI↗

arXiv2020

A CNN-LSTM Hybrid Framework for Wrist Kinematics Estimation Using Surface Electromyography

Convolutional neural network (CNN) has been widely exploited for simultaneous and proportional myoelectric control due to its capability of deriving informative, representative and transferable features from surface electromyography (sEMG). However, muscle contractions have strong temporal dependencies but conventional CNN can only exploit spatial correlations. Considering that long short-term memory neural network (LSTM) is able to capture long-term and non-linear dynamics of time-series data, in this paper we propose a CNNLSTM hybrid framework to fully explore the temporal-spatial information in sEMG. Firstly, CNN is utilized to extract deep features from sEMG spectrum, then these features are processed via LSTM-based sequence regression to estimate wrist kinematics. Six healthy participants are recruited for the participatory collection and motion analysis under various experimental setups. Estimation results in both intra-session and inter-session evaluations illustrate that CNN-LSTM significantly outperforms CNN and conventional machine learning approaches, particularly when complex wrist movements are activated.

eess.SP↗

arXiv2019

Real-Time Semantic Segmentation via Multiply Spatial Fusion Network

Real-time semantic segmentation plays a significant role in industry applications, such as autonomous driving, robotics and so on. It is a challenging task as both efficiency and performance need to be considered simultaneously. To address such a complex task, this paper proposes an efficient CNN called Multiply Spatial Fusion Network (MSFNet) to achieve fast and accurate perception. The proposed MSFNet uses Class Boundary Supervision to process the relevant boundary information based on our proposed Multi-features Fusion Module which can obtain spatial information and enlarge receptive field. Therefore, the final upsampling of the feature maps of 1/8 original image size can achieve impressive results while maintaining a high speed. Experiments on Cityscapes and Camvid datasets show an obvious advantage of the proposed approach compared with the existing approaches. Specifically, it achieves 77.1% Mean IOU on the Cityscapes test dataset with the speed of 41 FPS for a 1024*2048 input, and 75.4% Mean IOU with the speed of 91 FPS on the Camvid test dataset.

cs.CV↗

arXiv2019

Progressive Feature Polishing Network for Salient Object Detection

Feature matters for salient object detection. Existing methods mainly focus on designing a sophisticated structure to incorporate multi-level features and filter out cluttered features. We present Progressive Feature Polishing Network (PFPN), a simple yet effective framework to progressively polish the multi-level features to be more accurate and representative. By employing multiple Feature Polishing Modules (FPMs) in a recurrent manner, our approach is able to detect salient objects with fine details without any post-processing. A FPM parallelly updates the features of each level by directly incorporating all higher level context information. Moreover, it can keep the dimensions and hierarchical structures of the feature maps, which makes it flexible to be integrated with any CNN-based models. Empirical experiments show that our results are monotonically getting better with increasing number of FPMs. Without bells and whistles, PFPN outperforms the state-of-the-art methods significantly on five benchmark datasets under various evaluation metrics.

cs.CV↗

arXiv2019

Measurements of the branching ratios for $6P_{1/2}$ decays in $^{138}$Ba$^+$

Measurement of the branching ratios for $6P_{1/2}$ decays to $6S_{1/2}$ and $5D_{3/2}$ in $^{138}$Ba$^+$ are reported with the decay probability from $6P_{1/2}$ to $5D_{3/2}$ measured to be $p=0.268177\pm(37)_\mathrm{stat}-(20)_\mathrm{sys}$. This result differs from a recent report by $12σ$. A detailed account of systematics is given and the likely source of the discrepancy is identified. The new value of the branching ratio is combined with a previous experimental results to give a new estimate of $τ=7.855(10)\,\mathrm{ns}$ for the $6P_{1/2}$ lifetime. In addition, ratios of matrix elements calculated from theory are combined with experimental results to provide improved theoretical estimates of the $6P_{3/2}$ lifetime and the associated matrix elements.

physics.atom-ph↗

arXiv2019

Hyperfine averaging by dynamic decoupling in a multi-ion lutetium clock

We propose and experimentally demonstrate a scheme which effects hyperfine averaging during a Ramsey interrogation of a clock transition. The method eliminates the need to average over multiple optical transitions, reduces the sensitivity of the clock to its environment, and reduces inhomogeneous broadening in a multi-ion clock. The method is compatible with auto-balanced Ramsey spectroscopy, which facilitates elimination of residual shifts due to imperfect implementation and ac Stark shifts from the optical probe. We demonstrate the scheme using correlation spectroscopy of the $^1S_0$-to-$^3D_1$ clock transition in a three-ion Lu+ clock. From the demonstration we are able to provide a measurement of the $^3D_1$ quadrupole moment, $Θ(^3D_1)=0.634(9)ea_0^2$.

quant-ph↗