arXiv subjects

Qi Zhang

Publications and source records attributed to Qi Zhang.

At least 991 records · Page 55Linked to original sources

arXiv2021

AdsGNN: Behavior-Graph Augmented Relevance Modeling in Sponsored Search

Sponsored search ads appear next to search results when people look for products and services on search engines. In recent years, they have become one of the most lucrative channels for marketing. As the fundamental basis of search ads, relevance modeling has attracted increasing attention due to the significant research challenges and tremendous practical value. Most existing approaches solely rely on the semantic information in the input query-ad pair, while the pure semantic information in the short ads data is not sufficient to fully identify user's search intents. Our motivation lies in incorporating the tremendous amount of unsupervised user behavior data from the historical search logs as the complementary graph to facilitate relevance modeling. In this paper, we extensively investigate how to naturally fuse the semantic textual information with the user behavior graph, and further propose three novel AdsGNN models to aggregate topological neighborhood from the perspectives of nodes, edges and tokens. Furthermore, two critical but rarely investigated problems, domain-specific pre-training and long-tail ads matching, are studied thoroughly. Empirically, we evaluate the AdsGNN models over the large industry dataset, and the experimental results of online/offline tests consistently demonstrate the superiority of our proposal.

cs.IR↗

arXiv2021

Improving the Accuracy of Early Exits in Multi-Exit Architectures via Curriculum Learning

Deploying deep learning services for time-sensitive and resource-constrained settings such as IoT using edge computing systems is a challenging task that requires dynamic adjustment of inference time. Multi-exit architectures allow deep neural networks to terminate their execution early in order to adhere to tight deadlines at the cost of accuracy. To mitigate this cost, in this paper we introduce a novel method called Multi-Exit Curriculum Learning that utilizes curriculum learning, a training strategy for neural networks that imitates human learning by sorting the training samples based on their difficulty and gradually introducing them to the network. Experiments on CIFAR-10 and CIFAR-100 datasets and various configurations of multi-exit architectures show that our method consistently improves the accuracy of early exits compared to the standard training approach.

cs.LG↗

arXiv2021

Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure

Numerous online conversations are produced on a daily basis, resulting in a pressing need to conversation understanding. As a basis to structure a discussion, we identify the responding relations in the conversation discourse, which link response utterances to their initiations. To figure out who responded to whom, here we explore how the consistency of topic contents and dependency of discourse roles indicate such interactions, whereas most prior work ignore the effects of latent factors underlying word occurrences. We propose a model to learn latent topics and discourse in word distributions, and predict pairwise initiation-response links via exploiting topic consistency and discourse dependency. Experimental results on both English and Chinese conversations show that our model significantly outperforms the previous state of the arts, such as 79 vs. 73 MRR on Chinese customer service dialogues. We further probe into our outputs and shed light on how topics and discourse indicate conversational user interactions.

cs.CL↗

arXiv2021

Larger-Context Tagging: When and Why Does It Work?

The development of neural networks and pretraining techniques has spawned many sentence-level tagging systems that achieved superior performance on typical benchmarks. However, a relatively less discussed topic is what if more context information is introduced into current top-scoring tagging systems. Although several existing works have attempted to shift tagging systems from sentence-level to document-level, there is still no consensus conclusion about when and why it works, which limits the applicability of the larger-context approach in tagging tasks. In this paper, instead of pursuing a state-of-the-art tagging system by architectural exploration, we focus on investigating when and why the larger-context training, as a general strategy, can work. To this end, we conduct a thorough comparative study on four proposed aggregators for context information collecting and present an attribute-aided evaluation method to interpret the improvement brought by larger-context training. Experimentally, we set up a testbed based on four tagging tasks and thirteen datasets. Hopefully, our preliminary observations can deepen the understanding of larger-context training and enlighten more follow-up works on the use of contextual information.

cs.CL↗

arXiv2021

Deep-AIR: A Hybrid CNN-LSTM Framework for Air Quality Modeling in Metropolitan Cities

Air pollution has long been a serious environmental health challenge, especially in metropolitan cities, where air pollutant concentrations are exacerbated by the street canyon effect and high building density. Whilst accurately monitoring and forecasting air pollution are highly crucial, existing data-driven models fail to fully address the complex interaction between air pollution and urban dynamics. Our Deep-AIR, a novel hybrid deep learning framework that combines a convolutional neural network with a long short-term memory network, aims to address this gap to provide fine-grained city-wide air pollution estimation and station-wide forecast. Our proposed framework creates 1x1 convolution layers to strengthen the learning of cross-feature spatial interaction between air pollution and important urban dynamic features, particularly road density, building density/height, and street canyon effect. Using Hong Kong and Beijing as case studies, Deep-AIR achieves a higher accuracy than our baseline models. Our model attains an accuracy of 67.6%, 77.2%, and 66.1% in fine-grained hourly estimation, 1-hr, and 24-hr air pollution forecast for Hong Kong, and an accuracy of 65.0%, 75.3%, and 63.5% for Beijing. Our saliency analysis has revealed that for Hong Kong, street canyon and road density are the best estimators for NO2, while meteorology is the best estimator for PM2.5.

cs.LG↗

arXiv2021

Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting

Multivariate time-series forecasting plays a crucial role in many real-world applications. It is a challenging problem as one needs to consider both intra-series temporal correlations and inter-series correlations simultaneously. Recently, there have been multiple works trying to capture both correlations, but most, if not all of them only capture temporal correlations in the time domain and resort to pre-defined priors as inter-series relationships. In this paper, we propose Spectral Temporal Graph Neural Network (StemGNN) to further improve the accuracy of multivariate time-series forecasting. StemGNN captures inter-series correlations and temporal dependencies \textit{jointly} in the \textit{spectral domain}. It combines Graph Fourier Transform (GFT) which models inter-series correlations and Discrete Fourier Transform (DFT) which models temporal dependencies in an end-to-end framework. After passing through GFT and DFT, the spectral representations hold clear patterns and can be predicted effectively by convolution and sequential learning modules. Moreover, StemGNN learns inter-series correlations automatically from the data without using pre-defined priors. We conduct extensive experiments on ten real-world datasets to demonstrate the effectiveness of StemGNN. Code is available at https://github.com/microsoft/StemGNN/

cs.LG↗

arXiv2021

Study of $qqq\bar{q}Q$ pentaquark system in the Chiral Quark Model

With the discovery of some hidden-charm pentaquark resonances by the LHCb Collaboration, investigations of pentaquark states containing heavy quarks have aroused the interest of theorists. We study herein $qqq\bar{q}Q$ ($q = u$ or $d$, $Q=c$ or $b$) pentaquark system, in the framework of the chiral quark model. In consequence, some charmed and bottomed pentaquarks are considered to exist by five-body dynamical calculations. In the charm sector, $Σ_cπ(IJ^P=0\frac{1}{2}^-)$ and $Σ_c^*π(IJ^P=0\frac{3}{2}^-)$ are possible candidates of $Λ_c(2595)$ and $Λ_c(2625)$, respectively. Besides, two high-spin states, $Σ_c^*ρ(IJ^P=0\frac{5}{2}^-)$ and $ΔD^*(IJ^P=1\frac{5}{2}^-)$, are also found in the energy region of $3.2 \sim 3.3$ GeV. In the bottom sector, $Σ_bπ(IJ^P=0\frac{1}{2}^-)$, $Σ_b^*π(IJ^P=0\frac{3}{2}^-)$ could be candidates of $Λ_b(5912)$ and $Λ_b(5920)$, respectively. And $Σ_b^*ρ(IJ^P=0\frac{5}{2}^-)$ and $ΔB^*(IJ^P=1\frac{5}{2}^-)$ are found in the energy region of $6.5 \sim 6.6$ GeV. $Σ_c^{(*)}π$ and $Σ_b^{(*)}π$ are expected as compact states, while $Σ_c^*ρ$, $Σ_b^*ρ$, $ΔD^*$ and $ΔB^*$ are expected as molecular states.

hep-ph↗

arXiv2021

Robust Consumption Portfolio Optimization with Stochastic Differential Utility

This paper examines a continuous time intertemporal consumption and portfolio choice problem with a stochastic differential utility preference of Epstein-Zin type for a robust investor, who worries about model misspecification and seeks robust decision rules. We provide a verification theorem which formulates the Hamilton-Jacobi-Bellman-Isaacs equation under a non-Lipschitz condition. Then, with the verification theorem, the explicit closed-form optimal robust consumption and portfolio solutions to a Heston model are given. Also we compare our robust solutions with the non-robust ones, and the comparisons shown in a few figures coincide with our common sense.

math.OC↗

arXiv2021

Highly Anisotropic Excitons and Multiple Phonon Bound States in a Van der Waals Antiferromagnetic Insulator

Two-dimensional semiconducting systems, such as quantum wells and transition metal dichalcogenides, are the foundations to investigate low dimensional light-matter interactions. To date, the study of elementary photoexcitation, namely the exciton, in 2D semiconductors with intrinsic magnetic order remains a challenge due to the lack of suitable material platforms. Here, we report an observation of excitons coupled to zigzag antiferromagnetic order in the layered antiferromagnetic insulator NiPS3 using both photoluminescence (PL) and optical reflection spectroscopy. The exciton exhibits a linewidth as narrow as ~350 ueV with near unity linear polarization in the PL spectrum. As the thicknesses of samples is reduced from five layers to bilayers, the PL intensity is drastically suppressed and eventually vanishes in monolayers, consistent with the calculated bandgap being highly indirect for both bilayer and monolayer. We observed strong linear dichroism (LD) over a broad spectra range, which shares the same optical anisotropy axis, being locked to the zigzag direction, as the exciton PL. Both LD and the degree of linear polarization in the exciton PL decrease as the temperature increases and become negligible above the Neel temperature. These observations suggest both optical quantities are probes of the symmetry breaking magnetic order parameter. In addition, a sharp resonance in the LD spectrum is observed with an energy near the exciton PL. There exist over ten exciton-A1g phonon bound states on its high energy side, which likely result from the strong modulation of the ligand-to-metal charge transfer energy by strong electron-lattice interactions. Our work establishes NiPS3 as a new 2D platform for exploring magneto-exciton physics with strong correlations, as well as a building block for 2D heterostructures for engineering physical phenomena with time reversal symmetry breaking.

cond-mat.mes-hall↗

arXiv2021

Thermodynamic properties of ε-Fe with thermal electronic excitation effects on vibrational spectra

The thermodynamic properties of hcp-iron (ε-Fe) are essential for investigating planetary cores' internal structure and dynamic properties. Despite their importance to planetary sciences, experimental investigations of ε-Fe at relevant conditions are still challenging. Therefore, ab initio calculations are crucial to elucidating the thermodynamic properties of this system. Here we use a free energy calculation scheme based on the phonon gas model compatible with temperature-dependent phonon frequencies. We investigate the effects of electronic thermal excitations, which introduces a temperature dependence on phonon frequencies, and the implication for the thermodynamic properties of ε-Fe at extreme pressure (P) and temperature (T) conditions. We disregard phonon-phonon interactions, i.e., anharmonicity and their effect on phonon frequencies. Nevertheless, the current scheme is also applicable to T-dependent anharmonic frequencies. We conclude that the impact of thermal electronic excitations on vibrational properties is not significant up to ~ 4,000 K at 200 GPa but should not be ignored at higher temperatures or pressures. However, the static free energy, Fst, must always include the effect of thermal excitation fully in a continuum of Ts. Our results for isentropic equations of state show good agreement with data from recent ramp compression experiments up to 1,400 GPa conducted at the National Ignition Facility (NIF).

cond-mat.mtrl-sci↗

arXiv2021

Knowledge Infused Policy Gradients for Adaptive Pandemic Control

COVID-19 has impacted nations differently based on their policy implementations. The effective policy requires taking into account public information and adaptability to new knowledge. Epidemiological models built to understand COVID-19 seldom provide the policymaker with the capability for adaptive pandemic control (APC). Among the core challenges to be overcome include (a) inability to handle a high degree of non-homogeneity in different contributing features across the pandemic timeline, (b) lack of an approach that enables adaptive incorporation of public health expert knowledge, and (c) transparent models that enable understanding of the decision-making process in suggesting policy. In this work, we take the early steps to address these challenges using Knowledge Infused Policy Gradient (KIPG) methods. Prior work on knowledge infusion does not handle soft and hard imposition of varying forms of knowledge in disease information and guidelines to necessarily comply with. Furthermore, the models do not attend to non-homogeneity in feature counts, manifesting as partial observability in informing the policy. Additionally, interpretable structures are extracted post-learning instead of learning an interpretable model required for APC. To this end, we introduce a mathematical framework for KIPG methods that can (a) induce relevant feature counts over multi-relational features of the world, (b) handle latent non-homogeneous counts as hidden variables that are linear combinations of kernelized aggregates over the features, and (b) infuse knowledge as functional constraints in a principled manner. The study establishes a theory for imposing hard and soft constraints and simulates it through experiments. In comparison with knowledge-intensive baselines, we show quick sample efficient adaptation to new knowledge and interpretability in the learned policy, especially in a pandemic context.

cs.AI↗

arXiv2021

Fluid flow through anisotropic and deformable double porosity media with ultra-low matrix permeability: A continuum framework

Fractured porous media or double porosity media are common in nature. At the same time, accurate modeling remains a significant challenge due to bi-modal pore size distribution, anisotropy, multi-field coupling, and various flow patterns. This study aims to formulate a comprehensive coupled continuum framework that could adequately consider these critical characteristics. In our framework, fluid flow in the micro-fracture network is modeled with the generalized Darcy's law, in which the equivalent fracture permeability is upscaled from the detailed geological characterizations. The liquid in the much less permeable matrix follows a low-velocity non-Darcy flow characterized by threshold values and non-linearity. The fluid mass transfer is assumed to be a function of the shape factor, pressure difference, and (variable) interface permeability. The solid deformation relies on a thermodynamically consistent effective stress derived from the energy balance equation, and it is modeled following anisotropic poroelastic theory. The discussion revolves around generic double porosity media. Model applications reveal the capability of our framework to capture the crucial roles of coupling, poroelastic coefficients, anisotropy, and ultra-low matrix permeability in dictating the pressure and displacement fields.

physics.geo-ph↗

arXiv2021

Connection between inverse engineering and optimal control in shortcuts to adiabaticity

We consider fast high-fidelity quantum control by using a shortcut to adiabaticity (STA) technique and optimal control theory (OCT). Three specific examples, including expansion of cold atoms from the harmonic trap, atomic transport by moving harmonic trap, and spin dynamics in the presence of dissipation, are explicitly detailed. Using OCT as a qualitative guide, we demonstrate how STA protocols designed from inverse engineering method, can approach with very high precision optimal solutions built about physical constraints, by a proper choice of the interpolation function and with a very reduced number of adjustable parameters.

quant-ph↗

arXiv2020

Succinct and Robust Multi-Agent Communication With Temporal Message Control

Recent studies have shown that introducing communication between agents can significantly improve overall performance in cooperative Multi-agent reinforcement learning (MARL). However, existing communication schemes often require agents to exchange an excessive number of messages at run-time under a reliable communication channel, which hinders its practicality in many real-world situations. In this paper, we present \textit{Temporal Message Control} (TMC), a simple yet effective approach for achieving succinct and robust communication in MARL. TMC applies a temporal smoothing technique to drastically reduce the amount of information exchanged between agents. Experiments show that TMC can significantly reduce inter-agent communication overhead without impacting accuracy. Furthermore, TMC demonstrates much better robustness against transmission loss than existing approaches in lossy networking environments.

cs.AI↗

arXiv2020

Uncertainty-Aware Label Refinement for Sequence Labeling

Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks. However, the local label dependencies and inefficient Viterbi decoding have always been a problem to be solved. In this work, we introduce a novel two-stage label decoding framework to model long-term label dependencies, while being much more computationally efficient. A base model first predicts draft labels, and then a novel two-stream self-attention model makes refinements on these draft predictions based on long-range label dependencies, which can achieve parallel decoding for a faster prediction. In addition, in order to mitigate the side effects of incorrect draft labels, Bayesian neural networks are used to indicate the labels with a high probability of being wrong, which can greatly assist in preventing error propagation. The experimental results on three sequence labeling benchmarks demonstrated that the proposed method not only outperformed the CRF-based methods but also greatly accelerated the inference process.

cs.CL↗

arXiv2020

Efficient Querying for Cooperative Probabilistic Commitments

Multiagent systems can use commitments as the core of a general coordination infrastructure, supporting both cooperative and non-cooperative interactions. Agents whose objectives are aligned, and where one agent can help another achieve greater reward by sacrificing some of its own reward, should choose a cooperative commitment to maximize their joint reward. We present a solution to the problem of how cooperative agents can efficiently find an (approximately) optimal commitment by querying about carefully-selected commitment choices. We prove structural properties of the agents' values as functions of the parameters of the commitment specification, and develop a greedy method for composing a query with provable approximation bounds, which we empirically show can find nearly optimal commitments in a fraction of the time methods that lack our insights require.

cs.AI↗

arXiv2020

SenSeNet: Neural Keyphrase Generation with Document Structure

Keyphrase Generation (KG) is the task of generating central topics from a given document or literary work, which captures the crucial information necessary to understand the content. Documents such as scientific literature contain rich meta-sentence information, which represents the logical-semantic structure of the documents. However, previous approaches ignore the constraints of document logical structure, and hence they mistakenly generate keyphrases from unimportant sentences. To address this problem, we propose a new method called Sentence Selective Network (SenSeNet) to incorporate the meta-sentence inductive bias into KG. In SenSeNet, we use a straight-through estimator for end-to-end training and incorporate weak supervision in the training of the sentence selection module. Experimental results show that SenSeNet can consistently improve the performance of major KG models based on seq2seq framework, which demonstrate the effectiveness of capturing structural information and distinguishing the significance of sentences in KG task.

cs.CL↗

arXiv2020

RethinkCWS: Is Chinese Word Segmentation a Solved Task?

The performance of the Chinese Word Segmentation (CWS) systems has gradually reached a plateau with the rapid development of deep neural networks, especially the successful use of large pre-trained models. In this paper, we take stock of what we have achieved and rethink what's left in the CWS task. Methodologically, we propose a fine-grained evaluation for existing CWS systems, which not only allows us to diagnose the strengths and weaknesses of existing models (under the in-dataset setting), but enables us to quantify the discrepancy between different criterion and alleviate the negative transfer problem when doing multi-criteria learning. Strategically, despite not aiming to propose a novel model in this paper, our comprehensive experiments on eight models and seven datasets, as well as thorough analysis, could search for some promising direction for future research. We make all codes publicly available and release an interface that can quickly evaluate and diagnose user's models: https://github.com/neulab/InterpretEval.

cs.CL↗