arXiv subjects

Qi Zhang

Publications and source records attributed to Qi Zhang.

At least 955 records · Page 53Linked to original sources

arXiv2021

Searching for an Effective Defender: Benchmarking Defense against Adversarial Word Substitution

Recent studies have shown that deep neural networks are vulnerable to intentionally crafted adversarial examples, and various methods have been proposed to defend against adversarial word-substitution attacks for neural NLP models. However, there is a lack of systematic study on comparing different defense approaches under the same attacking setting. In this paper, we seek to fill the gap of systematic studies through comprehensive researches on understanding the behavior of neural text classifiers trained by various defense methods under representative adversarial attacks. In addition, we propose an effective method to further improve the robustness of neural text classifiers against such attacks and achieved the highest accuracy on both clean and adversarial examples on AGNEWS and IMDB datasets by a significant margin.

cs.CL↗

arXiv2021

Plant-Protein-Enabled Biodegradable Triboelectric Nanogenerator for Sustainable Agriculture

As the use of triboelectric nanogenerators (TENGs) increases, the generation of related electronic waste has been a major challenge. Therefore, the development of environmentally friendly, biodegradable, and low-cost TENGs must be prioritized. Having discovered that plant proteins, by-products of grain processing, possess excellent triboelectric properties, we explore these properties by evaluating the protein structure. The proteins are recycled to fabricate triboelectric layers, and the triboelectric series according to electrical properties is determined for the first time. Using a special structure design, we construct a plant-protein-enabled biodegradable TENG by integrating a polylactic acid film, which is used as a new type of mulch film to construct a growth-promoting system that generates space electric fields for agriculture. Thus, from the plant protein to the crop, a sustainable recycling loop is implemented. Using bean seedlings as a model to confirm the feasibility of the mulch film, we further use it in the cultivation of greenhouse vegetables. Experimental results demonstrate the applicability of the proposed plant-protein-enabled biodegradable TENG in sustainable agriculture.

physics.app-ph↗

arXiv2021

Disarranged Zone Learning (DZL): An unsupervised and dynamic automatic stenosis recognition methodology based on coronary angiography

We proposed a novel unsupervised methodology named Disarranged Zone Learning (DZL) to automatically recognize stenosis in coronary angiography. The methodology firstly disarranges the frames in a video, secondly it generates an effective zone and lastly trains an encoder-decoder GRU model to learn the capability to recover disarranged frames. The breakthrough of our study is to discover and validate the Sequence Intensity (Recover Difficulty) is a measure of Coronary Artery Stenosis Status. Hence, the prediction accuracy of DZL is used as an approximator of coronary stenosis indicator. DZL is an unsupervised methodology and no label engineering effort is needed, the sub GRU model in DZL works as a self-supervised approach. So DZL could theoretically utilize infinitely huge amounts of coronary angiographies to learn and improve performance without laborious data labeling. There is no data preprocessing precondition to run DZL as it dynamically utilizes the whole video, hence it is easy to be implemented and generalized to overcome the data heterogeneity of coronary angiography. The overall average precision score achieves 0.93, AUC achieves 0.8 for this pure methodology. The highest segmented average precision score is 0.98 and the highest segmented AUC is 0.87 for coronary occlusion indicator. Finally, we developed a software demo to implement DZL methodology.

eess.IV↗

arXiv2021

Robust High-Dimensional Regression with Coefficient Thresholding and its Application to Imaging Data Analysis

It is of importance to develop statistical techniques to analyze high-dimensional data in the presence of both complex dependence and possible outliers in real-world applications such as imaging data analyses. We propose a new robust high-dimensional regression with coefficient thresholding, in which an efficient nonconvex estimation procedure is proposed through a thresholding function and the robust Huber loss. The proposed regularization method accounts for complex dependence structures in predictors and is robust against outliers in outcomes. Theoretically, we analyze rigorously the landscape of the population and empirical risk functions for the proposed method. The fine landscape enables us to establish both {statistical consistency and computational convergence} under the high-dimensional setting. The finite-sample properties of the proposed method are examined by extensive simulation studies. An illustration of real-world application concerns a scalar-on-image regression analysis for an association of psychiatric disorder measured by the general factor of psychopathology with features extracted from the task functional magnetic resonance imaging data in the Adolescent Brain Cognitive Development study.

stat.ME↗

arXiv2021

Why Do We Click: Visual Impression-aware News Recommendation

There is a soaring interest in the news recommendation research scenario due to the information overload. To accurately capture users' interests, we propose to model multi-modal features, in addition to the news titles that are widely used in existing works, for news recommendation. Besides, existing research pays little attention to the click decision-making process in designing multi-modal modeling modules. In this work, inspired by the fact that users make their click decisions mostly based on the visual impression they perceive when browsing news, we propose to capture such visual impression information with visual-semantic modeling for news recommendation. Specifically, we devise the local impression modeling module to simultaneously attend to decomposed details in the impression when understanding the semantic meaning of news title, which could explicitly get close to the process of users reading news. In addition, we inspect the impression from a global view and take structural information, such as the arrangement of different fields and spatial position of different words on the impression, into the modeling of multiple modalities. To accommodate the research of visual impression-aware news recommendation, we extend the text-dominated news recommendation dataset MIND by adding snapshot impression images and will release it to nourish the research field. Extensive comparisons with the state-of-the-art news recommenders along with the in-depth analyses demonstrate the effectiveness of the proposed method and the promising capability of modeling visual impressions for the content-based recommenders.

cs.IR↗

arXiv2021

$\texttt{express}$: extensible, high-level workflows for swifter $\textit{ab initio}$ materials modeling

In this work, we introduce an open-source $\texttt{Julia}$ project, $\texttt{express}$, an extensible, high-throughput, high-level workflow framework that aims to automate $\textit{ab initio}$ calculations for the materials science community. $\texttt{Express}$ is shipped with well-tested workflow templates, including structure optimization, equation of state (EOS) fitting, phonon spectrum (lattice dynamics) calculation, and thermodynamic property calculation in the framework of the quasi-harmonic approximation (QHA). It is designed to be highly modularized so that its components can be reused across various occasions, and customized workflows can be built on top of that. Users can also track the status of workflows in real-time, and rerun failed jobs thanks to the data lineage feature $\texttt{express}$ provides. Two working examples, i.e., all workflows applied to lime and akimotoite, are also presented in the code and this paper.

physics.comp-ph↗

arXiv2021

A Relation-Oriented Clustering Method for Open Relation Extraction

The clustering-based unsupervised relation discovery method has gradually become one of the important methods of open relation extraction (OpenRE). However, high-dimensional vectors can encode complex linguistic information which leads to the problem that the derived clusters cannot explicitly align with the relational semantic classes. In this work, we propose a relation-oriented clustering model and use it to identify the novel relations in the unlabeled data. Specifically, to enable the model to learn to cluster relational data, our method leverages the readily available labeled data of pre-defined relations to learn a relation-oriented representation. We minimize distance between the instance with same relation by gathering the instances towards their corresponding relation centroids to form a cluster structure, so that the learned representation is cluster-friendly. To reduce the clustering bias on predefined classes, we optimize the model by minimizing a joint objective on both labeled and unlabeled data. Experimental results show that our method reduces the error rate by 29.2% and 15.7%, on two datasets respectively, compared with current SOTA methods.

cs.CL↗

arXiv2021

Reconfigurable Intelligent Surface-assisted Edge Computing to Minimize Delay in Task Offloading

The advantage of computational resources in edge computing near the data source has kindled growing interest in delay-sensitive Internet of Things (IoT) applications. However, the benefit of the edge server is limited by the uploading and downloading links between end-users and edge servers when these end-users seek computational resources from edge servers. The scenario becomes more severe when the user-end's devices are in the shaded region resulting in low uplink/downlink quality. In this paper, we consider a reconfigurable intelligent surface (RIS)-assisted edge computing system, where the benefits of RIS are exploited to improve the uploading transmission rate. We further aim to minimize the delay of worst-case in the network when the end-users either compute task data in their local CPU or offload task data to the edge server. Next, we optimize the uploading bandwidth allocation for every end-user's task data to minimize the maximum delay in the network. The above optimization problem is formulated as quadratically constrained quadratic programming. Afterward, we solve this problem by semidefinite relaxation. Finally, the simulation results demonstrate that the proposed strategy is scalable under various network settings.

cs.IT↗

arXiv2021

DLB: Deep Learning Based Load Balancing

In this paper, we introduce DLB, a Deep Learning based load Balancing mechanism, to effectively address the data skew problem. The key idea of DLB is to replace hash functions in the load balancing mechanisms with deep learning models, which are trained to be able to map different distributions of workloads and data to the servers in a uniform manner. We implemented DLB and deployed it on a practical Cloud environment using CloudSim. Experimental results using both synthetic and real-world data sets show that compared with traditional hash function-based load balancing methods, DLB is able to achieve more balanced mappings, especially when the workload is highly skewed.

cs.DC↗

arXiv2021

A Partition Filter Network for Joint Entity and Relation Extraction

In joint entity and relation extraction, existing work either sequentially encode task-specific features, leading to an imbalance in inter-task feature interaction where features extracted later have no direct contact with those that come first. Or they encode entity features and relation features in a parallel manner, meaning that feature representation learning for each task is largely independent of each other except for input sharing. We propose a partition filter network to model two-way interaction between tasks properly, where feature encoding is decomposed into two steps: partition and filter. In our encoder, we leverage two gates: entity and relation gate, to segment neurons into two task partitions and one shared partition. The shared partition represents inter-task information valuable to both tasks and is evenly shared across two tasks to ensure proper two-way interaction. The task partitions represent intra-task information and are formed through concerted efforts of both gates, making sure that encoding of task-specific features is dependent upon each other. Experiment results on six public datasets show that our model performs significantly better than previous approaches. In addition, contrary to what previous work has claimed, our auxiliary experiments suggest that relation prediction is contributory to named entity prediction in a non-negligible way. The source code can be found at https://github.com/Coopercoppers/PFN.

cs.CL↗

arXiv2021

Low-Resource Dialogue Summarization with Domain-Agnostic Multi-Source Pretraining

With the rapid increase in the volume of dialogue data from daily life, there is a growing demand for dialogue summarization. Unfortunately, training a large summarization model is generally infeasible due to the inadequacy of dialogue data with annotated summaries. Most existing works for low-resource dialogue summarization directly pretrain models in other domains, e.g., the news domain, but they generally neglect the huge difference between dialogues and conventional articles. To bridge the gap between out-of-domain pretraining and in-domain fine-tuning, in this work, we propose a multi-source pretraining paradigm to better leverage the external summary data. Specifically, we exploit large-scale in-domain non-summary data to separately pretrain the dialogue encoder and the summary decoder. The combined encoder-decoder model is then pretrained on the out-of-domain summary data using adversarial critics, aiming to facilitate domain-agnostic summarization. The experimental results on two public datasets show that with only limited training data, our approach achieves competitive performance and generalizes well in different dialogue scenarios.

cs.CL↗

arXiv2021

Keyphrase Generation with Fine-Grained Evaluation-Guided Reinforcement Learning

Aiming to generate a set of keyphrases, Keyphrase Generation (KG) is a classical task for capturing the central idea from a given document. Based on Seq2Seq models, the previous reinforcement learning framework on KG tasks utilizes the evaluation metrics to further improve the well-trained neural models. However, these KG evaluation metrics such as $F_1@5$ and $F_1@M$ are only aware of the exact correctness of predictions on phrase-level and ignore the semantic similarities between similar predictions and targets, which inhibits the model from learning deep linguistic patterns. In response to this problem, we propose a new fine-grained evaluation metric to improve the RL framework, which considers different granularities: token-level $F_1$ score, edit distance, duplication, and prediction quantities. On the whole, the new framework includes two reward functions: the fine-grained evaluation score and the vanilla $F_1$ score. This framework helps the model identifying some partial match phrases which can be further optimized as the exact match ones. Experiments on KG benchmarks show that our proposed training framework outperforms the previous RL training frameworks among all evaluation scores. In addition, our method can effectively ease the synonym problem and generate a higher quality prediction. The source code is available at \url{https://github.com/xuyige/FGRL4KG}.

cs.CL↗

arXiv2021

Heterogeneous Graph Neural Networks for Keyphrase Generation

The encoder-decoder framework achieves state-of-the-art results in keyphrase generation (KG) tasks by predicting both present keyphrases that appear in the source document and absent keyphrases that do not. However, relying solely on the source document can result in generating uncontrollable and inaccurate absent keyphrases. To address these problems, we propose a novel graph-based method that can capture explicit knowledge from related references. Our model first retrieves some document-keyphrases pairs similar to the source document from a pre-defined index as references. Then a heterogeneous graph is constructed to capture relationships of different granularities between the source document and its references. To guide the decoding process, a hierarchical attention and copy mechanism is introduced, which directly copies appropriate words from both the source document and its references based on their relevance and significance. The experimental results on multiple KG benchmarks show that the proposed model achieves significant improvements against other baseline models, especially with regard to the absent keyphrase prediction.

cs.CL↗

arXiv2021

Thinking Clearly, Talking Fast: Concept-Guided Non-Autoregressive Generation for Open-Domain Dialogue Systems

Human dialogue contains evolving concepts, and speakers naturally associate multiple concepts to compose a response. However, current dialogue models with the seq2seq framework lack the ability to effectively manage concept transitions and can hardly introduce multiple concepts to responses in a sequential decoding manner. To facilitate a controllable and coherent dialogue, in this work, we devise a concept-guided non-autoregressive model (CG-nAR) for open-domain dialogue generation. The proposed model comprises a multi-concept planning module that learns to identify multiple associated concepts from a concept graph and a customized Insertion Transformer that performs concept-guided non-autoregressive generation to complete a response. The experimental results on two public datasets show that CG-nAR can produce diverse and coherent responses, outperforming state-of-the-art baselines in both automatic and human evaluations with substantially faster inference speed.

cs.CL↗

arXiv2021

Knowledge & Learning-based Adaptable System for Sensitive Information Identification and Handling

Diagnostic data such as logs and memory dumps from production systems are often shared with development teams to do root cause analysis of system crashes. Invariably such diagnostic data contains sensitive information and sharing it can lead to data leaks. To handle this problem we present Knowledge and Learning-based Adaptable System for Sensitive InFormation Identification and Handling (KLASSIFI) which is an end to end system capable of identifying and redacting sensitive information present in diagnostic data. KLASSIFI is highly customizable, allowing it to be used for various different business use cases by simply changing the configuration. KLASSIFI ensures that the output file is useful by retaining the metadata which is used by various debugging tools. Various optimizations have been done to improve the performance of KLASSIFI. Empirical evaluation of KLASSIFI shows that it is able to process large files (128 GB) in 84 minutes and its performance scales linearly with varying factors. This points to practicability of KLASSIFI

cs.CR↗

arXiv2021

Dynamic behavior of polar nanoregions in re-entrant relaxor 0.6Bi(Mg1/2Ti1/2)O3-0.4PbTiO3

The existence of polar nanoregions is the most important characteristic of ferroelectric relaxors, however, the size determination and dynamic of PNRs remains uncertain. We reveal a re-entrant relaxor behavior and ferroelectric-paraelectric transition coexists in complex perovskite oxide 0.6Bi(Mg1/2Ti1/2)O3-0.4PbTiO3. Two dielectric anomalies (i) the low-temperature re-entrant relaxor transition and (ii) the high-temperature diffuse phase transition (DPT) were described by the phenomenological statistical model. The sizes of the two kinds of polar nanoregions (PNRs) corresponding to two ferroelectric states were obtained. The dynamic of PNRs were analyzed using isothermal electrical modulus, which shows three critical temperatures associated with the diffuse phase transition, the formation and freezing of PNRs, respectively. The temperature evolution of the PNRs evolution depends on the stoichiometry of bismuth. The results provide new insights into the dynamic behavior of PNRs and the modification way of re-entrant relaxor behavior.

cond-mat.mtrl-sci↗

arXiv2021

Coherent strong-coupling of terahertz magnons and phonons in a Van der Waals antiferromagnetic insulator

Emergent cooperative motions of individual degrees of freedom, i.e. collective excitations, govern the low-energy response of system ground states under external stimulations and play essential roles for understanding many-body phenomena in low-dimensional materials. The hybridization of distinct collective modes provides a route towards coherent manipulation of coupled degrees of freedom and quantum phases. In magnets, strong coupling between collective spin and lattice excitations, i.e., magnons and phonons, can lead to coherent quasi-particle magnon polarons. Here, we report the direct observation of a series of terahertz magnon polarons in a layered zigzag antiferromagnet FePS3 via far-infrared (FIR) transmission measurements. The characteristic avoided-crossing behavior is clearly seen as the magnon-phonon detuning is continuously changed via Zeeman shift of the magnon mode. The coupling strength g is giant, achieving 120 GHz (0.5 meV), the largest value reported so far. Such a strong coupling leads to a large ratio of g to the resonance frequency (g/ω) of 4.5%, and a value of 29 in cooperativity (g^2/γ_{ph}γ_{mag}). Experimental results are well reproduced by first-principle calculations, where the strong coupling is identified to arise from phonon-modulated anisotropic magnetic interactions due to spin-orbit coupling. These findings establish FePS3 as an ideal testbed for exploring hybridization-induced topological magnonics in two dimensions and the coherent control of spin and lattice degrees of freedom in the terahertz regime.

cond-mat.mtrl-sci↗

arXiv2021

iBatch: Saving Ethereum Fees via Secure and Cost-Effective Batching of Smart-Contract Invocations

This paper presents iBatch, a middleware system running on top of an operational Ethereum network to enable secure batching of smart-contract invocations against an untrusted relay server off-chain. iBatch does so at a low overhead by validating the server's batched invocations in smart contracts without additional states. The iBatch mechanism supports a variety of policies, ranging from conservative to aggressive batching, and can be configured adaptively to the current workloads. iBatch automatically rewrites smart contracts to integrate with legacy applications and support large-scale deployment. For cost evaluation, we develop a platform with fast and cost-accurate transaction replaying, build real transaction benchmarks on popular Ethereum applications, and build a functional prototype of iBatch on Ethereum. The evaluation results show that iBatch saves 14.6%-59.1% Gas cost per invocation with a moderate 2-minute delay and 19.06%-31.52% Ether cost per invocation with a delay of 0.26-1.66 blocks.

cs.CR↗