arXiv subjects

Wen Zhang

Publications and source records attributed to Wen Zhang.

At least 235 records · Page 13Linked to original sources

arXiv2019

Bridging the Gap between Training and Inference for Neural Machine Translation

Neural Machine Translation (NMT) generates target words sequentially in the way of predicting the next word conditioned on the context words. At training time, it predicts with the ground truth words as context while at inference it has to generate the entire sequence from scratch. This discrepancy of the fed context leads to error accumulation among the way. Furthermore, word-level training requires strict matching between the generated sequence and the ground truth sequence which leads to overcorrection over different but reasonable translations. In this paper, we address these issues by sampling context words not only from the ground truth sequence but also from the predicted sequence by the model during training, where the predicted sequence is selected with a sentence-level optimum. Experiment results on Chinese->English and WMT'14 English->German translation tasks demonstrate that our approach can achieve significant improvements on multiple datasets.

cs.CL↗

arXiv2019

Neural Learning of Online Consumer Credit Risk

This paper takes a deep learning approach to understand consumer credit risk when e-commerce platforms issue unsecured credit to finance customers' purchase. The "NeuCredit" model can capture both serial dependences in multi-dimensional time series data when event frequencies in each dimension differ. It also captures nonlinear cross-sectional interactions among different time-evolving features. Also, the predicted default probability is designed to be interpretable such that risks can be decomposed into three components: the subjective risk indicating the consumers' willingness to repay, the objective risk indicating their ability to repay, and the behavioral risk indicating consumers' behavioral differences. Using a unique dataset from one of the largest global e-commerce platforms, we show that the inclusion of shopping behavioral data, besides conventional payment records, requires a deep learning approach to extract the information content of these data, which turns out significantly enhancing forecasting performance than the traditional machine learning methods.

q-fin.RM↗

arXiv2019

Fixed-price Diffusion Mechanism Design

We consider a fixed-price mechanism design setting where a seller sells one item via a social network, but the seller can only directly communicate with her neighbours initially. Each other node in the network is a potential buyer with a valuation derived from a common distribution. With a standard fixed-price mechanism, the seller can only sell the item among her neighbours. To improve her revenue, she needs more buyers to join in the sale. To achieve this, we propose the very first fixed-price mechanism to incentivize the seller's neighbours to inform their neighbours about the sale and to eventually inform all buyers in the network to improve seller's revenue. Compared with the existing mechanisms for the same purpose, our mechanism does not require the buyers to reveal their valuations and it is computationally easy. More importantly, it guarantees that the improved revenue is at least 1/2 of the optimal.

cs.GT↗

arXiv2019

Iteratively Learning Embeddings and Rules for Knowledge Graph Reasoning

Reasoning is essential for the development of large knowledge graphs, especially for completion, which aims to infer new triples based on existing ones. Both rules and embeddings can be used for knowledge graph reasoning and they have their own advantages and difficulties. Rule-based reasoning is accurate and explainable but rule learning with searching over the graph always suffers from efficiency due to huge search space. Embedding-based reasoning is more scalable and efficient as the reasoning is conducted via computation between embeddings, but it has difficulty learning good representations for sparse entities because a good embedding relies heavily on data richness. Based on this observation, in this paper we explore how embedding and rule learning can be combined together and complement each other's difficulties with their advantages. We propose a novel framework IterE iteratively learning embeddings and rules, in which rules are learned from embeddings with proper pruning strategy and embeddings are learned from existing triples and new triples inferred by rules. Evaluations on embedding qualities of IterE show that rules help improve the quality of sparse entity embeddings and their link prediction results. We also evaluate the efficiency of rule learning and quality of rules from IterE compared with AMIE+, showing that IterE is capable of generating high quality rules more efficiently. Experiments show that iteratively learning embeddings and rules benefit each other during learning and prediction.

cs.AI↗

arXiv2019

Interaction Embeddings for Prediction and Explanation in Knowledge Graphs

Knowledge graph embedding aims to learn distributed representations for entities and relations, and is proven to be effective in many applications. Crossover interactions --- bi-directional effects between entities and relations --- help select related information when predicting a new triple, but haven't been formally discussed before. In this paper, we propose CrossE, a novel knowledge graph embedding which explicitly simulates crossover interactions. It not only learns one general embedding for each entity and relation as most previous methods do, but also generates multiple triple specific embeddings for both of them, named interaction embeddings. We evaluate embeddings on typical link prediction tasks and find that CrossE achieves state-of-the-art results on complex and more challenging datasets. Furthermore, we evaluate embeddings from a new perspective --- giving explanations for predicted triples, which is important for real applications. In this work, an explanation for a triple is regarded as a reliable closed-path between the head and the tail entity. Compared to other baselines, we show experimentally that CrossE, benefiting from interaction embeddings, is more capable of generating reliable explanations to support its predictions.

cs.AI↗

arXiv2019

Graph Neural Networks for User Identity Linkage

The increasing popularity and diversity of social media sites has encouraged more and more people to participate in multiple online social networks to enjoy their services. Each user may create a user identity to represent his or her unique public figure in every social network. User identity linkage across online social networks is an emerging task and has attracted increasing attention, which could potentially impact various domains such as recommendations and link predictions. The majority of existing work focuses on mining network proximity or user profile data for discovering user identity linkages. With the recent advancements in graph neural networks (GNNs), it provides great potential to advance user identity linkage since users are connected in social graphs, and learning latent factors of users and items is the key. However, predicting user identity linkages based on GNNs faces challenges. For example, the user social graphs encode both \textit{local} structure such as users' neighborhood signals, and \textit{global} structure with community properties. To address these challenges simultaneously, in this paper, we present a novel graph neural network framework ({\m}) for user identity linkage. In particular, we provide a principled approach to jointly capture local and global information in the user-user social graph and propose the framework {\m}, which jointly learning user representations for user identity linkage. Extensive experiments on real-world datasets demonstrate the effectiveness of the proposed framework.

cs.SI↗

arXiv2019

Real-time separation of non-stationary sound fields on spheres

The sound field separation methods can separate the target field from the interfering noises, facilitating the study of the acoustic characteristics of the target source, which is placed in a noisy environment. However, most of the existing sound field separation methods are derived in the frequency-domain, thus are best suited for separating stationary sound fields. In this paper, a time-domain sound field separation method is developed that can separate the non-stationary sound field generated by the target source over a sphere in real-time. A spherical array sets up a boundary between the target source and the interfering sources, such that the outgoing field on the array is only generated by the target source. The proposed method decomposes the pressure and the radial particle velocity measured by the array into spherical harmonics coefficients, and recoveries the target outgoing field based on the time-domain relationship between the decomposition coefficients and the theoretically derived spatial filter responses. Simulations show the proposed method can separate non-stationary sound fields both in free field and room environments, and over a longer duration with small errors. The proposed method could serve as a foundation for developing future time-domain spatial sound field manipulation algorithms.

eess.AS↗

arXiv2019

End-to-End Model for Speech Enhancement by Consistent Spectrogram Masking

Recently, phase processing is attracting increasinginterest in speech enhancement community. Some researchersintegrate phase estimations module into speech enhancementmodels by using complex-valued short-time Fourier transform(STFT) spectrogram based training targets, e.g. Complex RatioMask (cRM) [1]. However, masking on spectrogram would violentits consistency constraints. In this work, we prove that theinconsistent problem enlarges the solution space of the speechenhancement model and causes unintended artifacts. ConsistencySpectrogram Masking (CSM) is proposed to estimate the complexspectrogram of a signal with the consistency constraint in asimple but not trivial way. The experiments comparing ourCSM based end-to-end model with other methods are conductedto confirm that the CSM accelerate the model training andhave significant improvements in speech quality. From ourexperimental results, we assured that our method could enha

cs.SD↗

arXiv2018

Refining Source Representations with Relation Networks for Neural Machine Translation

Although neural machine translation with the encoder-decoder framework has achieved great success recently, it still suffers drawbacks of forgetting distant information, which is an inherent disadvantage of recurrent neural network structure, and disregarding relationship between source words during encoding step. Whereas in practice, the former information and relationship are often useful in current step. We target on solving these problems and thus introduce relation networks to learn better representations of the source. The relation networks are able to facilitate memorization capability of recurrent neural network via associating source words with each other, this would also help retain their relationships. Then the source representations and all the relations are fed into the attention component together while decoding, with the main encoder-decoder framework unchanged. Experiments on several datasets show that our method can improve the translation performance significantly over the conventional encoder-decoder model and even outperform the approach involving supervised syntactic knowledge.

cs.CL↗

arXiv2018

Speeding Up Neural Machine Translation Decoding by Cube Pruning

Although neural machine translation has achieved promising results, it suffers from slow translation speed. The direct consequence is that a trade-off has to be made between translation quality and speed, thus its performance can not come into full play. We apply cube pruning, a popular technique to speed up dynamic programming, into neural machine translation to speed up the translation. To construct the equivalence class, similar target hidden states are combined, leading to less RNN expansion operations on the target side and less \$\mathrm{softmax}\$ operations over the large target vocabulary. The experiments show that, at the same or even better translation quality, our method can translate faster compared with naive beam search by \$3.3\times\$ on GPUs and \$3.5\times\$ on CPUs.

cs.CL↗

arXiv2018

Brain Morphometry Analysis with Surface Foliation Theory

Brain morphometry study plays a fundamental role in neuroimaging research. In this work, we propose a novel method for brain surface morphometry analysis based on surface foliation theory. Given brain cortical surfaces with automatically extracted landmark curves, we first construct finite foliations on surfaces. A set of admissible curves and a height parameter for each loop are provided by users. The admissible curves cut the surface into a set of pairs of pants. A pants decomposition graph is then constructed. Strebel differential is obtained by computing a unique harmonic map from surface to pants decomposition graph. The critical trajectories of Strebel differential decompose the surface into topological cylinders. After conformally mapping those topological cylinders to standard cylinders, parameters of standard cylinders (height, circumference) are intrinsic geometric features of the original cortical surfaces and thus can be used for morphometry analysis purpose. In this work, we propose a set of novel surface features rooted in surface foliation theory. To the best of our knowledge, this is the first work to make use of surface foliation theory for brain morphometry analysis. The features we computed are intrinsic and informative. The proposed method is rigorous, geometric, and automatic. Experimental results on classifying brain cortical surfaces between patients with Alzheimer's disease and healthy control subjects demonstrate the efficiency and efficacy of our method.

cs.CG↗

arXiv2018

Variational Wasserstein Clustering

We propose a new clustering method based on optimal transportation. We solve optimal transportation with variational principles, and investigate the use of power diagrams as transportation plans for aggregating arbitrary domains into a fixed number of clusters. We iteratively drive centroids through target domains while maintaining the minimum clustering energy by adjusting the power diagrams. Thus, we simultaneously pursue clustering and the Wasserstein distances between the centroids and the target domains, resulting in a measure-preserving mapping. We demonstrate the use of our method in domain adaptation, remeshing, and representation learning on synthetic and real data.

cs.CV↗

arXiv2018

Instabilities in a combustion model with two free interfaces

We study in a strip of $\mathbb R^2$ a combustion model of flame propagation with stepwise temperature kinetics and zero-order reaction, characterized by two free interfaces, respectively the ignition and the trailing fronts. The latter interface presents an additional difficulty because the non-degeneracy condition is not met. We turn the system to a fully nonlinear problem which is thoroughly investigated. When the width $\ell$ of the strip is sufficiently large, we prove the existence of a critical value $Le_c$ of the Lewis number $Le$, such that the one-dimensional, planar, solution is unstable for $0<Le<Le_c$. Some numerical simulations confirm the analysis.

math.AP↗

arXiv2018

Griffiths phase and symmetry breaking in the hidden-order phase of URu2Si2

The heavy-fermion compound URu2Si2 exhibits a hidden-order phase below the temperature, ~ 17.5 K. In spite of intense research for past three decades, no consensus on the order parameter exists and the nature has posed a long-standing mystery. Here we report the discovery of a Griffiths phase within the hidden-order phase, characterized by residual short-range correlations on the collapse of long-range orders due to the dilution effects. In the Griffiths phase scenario, strong evidence are provided for those cluster-like spins, such as the unique power-law behavior of magnetic susceptibility and specific heat as well as the frequency dispersion of AC susceptibility. In this way, the existence of an order parameter is excluded, and the hidden order has a significant kinship with the long-range large-moment antiferromagnetism which is accessible by tuning the hydrostatic pressure or the chemical pressure (i.e., isoelectronic Fe doping). Moreover, an unidirectional anisotropy of resistivity measurements in rotating magnetic fields is observed in the hidden-order phase. The anisotropic magnetoresistance and the associated broken symmetries directly reflect the freezing behavior of at least part of magnetic clusters. Thus, the demonstrations of the Griffiths phase as an alternative proposal for the hidden-order phase of URu2Si2 are very promising, challenging the understanding of exotic electronic states in correlated matter and quantum materials.

cond-mat.str-el↗

arXiv2018

Information-Propogation-Enhanced Neural Machine Translation by Relation Model

Even though sequence-to-sequence neural machine translation (NMT) model have achieved state-of-art performance in the recent fewer years, but it is widely concerned that the recurrent neural network (RNN) units are very hard to capture the long-distance state information, which means RNN can hardly find the feature with long term dependency as the sequence becomes longer. Similarly, convolutional neural network (CNN) is introduced into NMT for speeding recently, however, CNN focus on capturing the local feature of the sequence; To relieve this issue, we incorporate a relation network into the standard encoder-decoder framework to enhance information-propogation in neural network, ensuring that the information of the source sentence can flow into the decoder adequately. Experiments show that proposed framework outperforms the statistical MT model and the state-of-art NMT model significantly on two data sets with different scales.

cs.CL↗

arXiv2018

Refining Source Representations with Relation Networks for Neural Machine Translation

Although neural machine translation (NMT) with the encoder-decoder framework has achieved great success in recent times, it still suffers from some drawbacks: RNNs tend to forget old information which is often useful and the encoder only operates through words without considering word relationship. To solve these problems, we introduce a relation networks (RN) into NMT to refine the encoding representations of the source. In our method, the RN first augments the representation of each source word with its neighbors and reasons all the possible pairwise relations between them. Then the source representations and all the relations are fed to the attention module and the decoder together, keeping the main encoder-decoder architecture unchanged. Experiments on two Chinese-to-English data sets in different scales both show that our method can outperform the competitive baselines significantly.

cs.CL↗

arXiv2017

Intrinsic Light Field Images

We present a method to automatically decompose a light field into its intrinsic shading and albedo components. Contrary to previous work targeted to 2D single images and videos, a light field is a 4D structure that captures non-integrated incoming radiance over a discrete angular domain. This higher dimensionality of the problem renders previous state-of-the-art algorithms impractical either due to their cost of processing a single 2D slice, or their inability to enforce proper coherence in additional dimensions. We propose a new decomposition algorithm that jointly optimizes the whole light field data for proper angular coherence. For efficiency, we extend Retinex theory, working on the gradient domain, where new albedo and occlusion terms are introduced. Results show our method provides 4D intrinsic decompositions difficult to achieve with previous state-of-the-art algorithms. We further provide a comprehensive analysis and comparisons with existing intrinsic image/video decomposition methods on light field images.

cs.CV↗

arXiv2016

Towards Evidence-Based Ontology for Supporting Systematic Literature Review

[Background]: Systematic Literature Review (SLR) has become an important software engineering research method but costs tremendous efforts. [Aim]: This paper proposes an approach to leverage on empirically evolved ontology to support automating key SLR activities. [Method]: First, we propose an ontology, SLRONT, built on SLR experiences and best practices as a groundwork to capture common terminologies and their relationships during SLR processes; second, we present an extended version of SLRONT, the COSONT and instantiate it with the knowledge and concepts extracted from structured abstracts. Case studies illustrate the details of applying it for supporting SLR steps. [Results]: Results show that through using COSONT, we acquire the same conclusion compared with sheer manual works, but the efforts involved is significantly reduced. [Conclusions]: The approach of using ontology could effectively and efficiently support the conducting of systematic literature review.

cs.DL↗