arXiv subjects

Xinyu Wang

Publications and source records attributed to Xinyu Wang.

At least 325 records · Page 18Linked to original sources

arXiv2022

Static Knowledge vs. Dynamic Argumentation: A Dual Theory Based on Kripke Semantics

This paper establishes a dual theory about knowledge and argumentation. Our idea is rooted at both epistemic logic and argumentation theory, and we aim to merge these two fields, not just in a superficial way but to thoroughly disclose the intrinsic relevance between knowledge and argumentation. Specifically, we define epistemic Kripke models and argument Kripke models as a dual pair, and then work out a two-way generation method between these two types of Kripke models. Such generation is rigorously justified by a duality theorem on modal formulae's invariance. We also provide realistic examples to demonstrate our generation, through which our framework's practical utility gets strongly advocated. We finally propose a philosophical thesis that knowledge is essentially dynamic, and we draw certain connection to Maxwell's demon as well as the well-known proverb "knowledge is power".

cs.LO↗

arXiv2022

ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition

Recently, Multi-modal Named Entity Recognition (MNER) has attracted a lot of attention. Most of the work utilizes image information through region-level visual representations obtained from a pretrained object detector and relies on an attention mechanism to model the interactions between image and text representations. However, it is difficult to model such interactions as image and text representations are trained separately on the data of their respective modality and are not aligned in the same space. As text representations take the most important role in MNER, in this paper, we propose {\bf I}mage-{\bf t}ext {\bf A}lignments (ITA) to align image features into the textual space, so that the attention mechanism in transformer-based pretrained textual embeddings can be better utilized. ITA first aligns the image into regional object tags, image-level captions and optical characters as visual contexts, concatenates them with the input texts as a new cross-modal input, and then feeds it into a pretrained textual embedding model. This makes it easier for the attention module of a pretrained textual embedding model to model the interaction between the two modalities since they are both represented in the textual space. ITA further aligns the output distributions predicted from the cross-modal input and textual input views so that the MNER model can be more practical in dealing with text-only inputs and robust to noises from images. In our experiments, we show that ITA models can achieve state-of-the-art accuracy on multi-modal Named Entity Recognition datasets, even without image information.

cs.CL↗

arXiv2022

SPTS: Single-Point Text Spotting

Existing scene text spotting (i.e., end-to-end text detection and recognition) methods rely on costly bounding box annotations (e.g., text-line, word-level, or character-level bounding boxes). For the first time, we demonstrate that training scene text spotting models can be achieved with an extremely low-cost annotation of a single-point for each instance. We propose an end-to-end scene text spotting method that tackles scene text spotting as a sequence prediction task. Given an image as input, we formulate the desired detection and recognition results as a sequence of discrete tokens and use an auto-regressive Transformer to predict the sequence. The proposed method is simple yet effective, which can achieve state-of-the-art results on widely used benchmarks. Most significantly, we show that the performance is not very sensitive to the positions of the point annotation, meaning that it can be much easier to be annotated or even be automatically generated than the bounding box that requires precise positions. We believe that such a pioneer attempt indicates a significant opportunity for scene text spotting applications of a much larger scale than previously possible. The code is available at https://github.com/shannanyinxiang/SPTS.

cs.CV↗

arXiv2022

Statistical Attention Localization (SAL): Methodology and Application to Object Classification

A statistical attention localization (SAL) method is proposed to facilitate the object classification task in this work. SAL consists of three steps: 1) preliminary attention window selection via decision statistics, 2) attention map refinement, and 3) rectangular attention region finalization. SAL computes soft-decision scores of local squared windows and uses them to identify salient regions in Step 1. To accommodate object of various sizes and shapes, SAL refines the preliminary result and obtain an attention map of more flexible shape in Step 2. Finally, SAL yields a rectangular attention region using the refined attention map and bounding box regularization in Step 3. As an application, we adopt E-PixelHop, which is an object classification solution based on successive subspace learning (SSL), as the baseline. We apply SAL so as to obtain a cropped-out and resized attention region as an alternative input. Classification results of the whole image as well as the attention region are ensembled to achieve the highest classification accuracy. Experiments on the CIFAR-10 dataset are given to demonstrate the advantage of the SAL-assisted object classification method.

cs.CV↗

arXiv2022

A comprehensive assessment of accuracy of adaptive integration of cut cells for laminar fluid-structure interaction problems

Finite element methods based on cut-cells are becoming increasingly popular because of their advantages over formulations based on body-fitted meshes for problems with moving interfaces. In such methods, the cells (or elements) which are cut by the interface between two different domains need to be integrated using special techniques in order to obtain optimal convergence rates and accurate fluxes across the interface. The adaptive integration technique in which the cells are recursively subdivided is one of the popular techniques for the numerical integration of cut-cells due to its advantages over tessellation, particularly for problems involving complex geometries in three dimensions. Although adaptive integration does not impose any limitations on the representation of the geometry of immersed solids as it requires only point location algorithms, it becomes computationally expensive for recovering optimal convergence rates. This paper presents a comprehensive assessment of the adaptive integration of cut-cells for applications in computational fluid dynamics and fluid-structure interaction. We assess the effect of the accuracy of integration of cut cells on convergence rates in velocity and pressure fields, and then on forces and displacements for fluid-structure interaction problems by studying several examples in two and three dimensions. By taking the computational cost and the accuracy of forces and displacements into account, we demonstrate that numerical results of acceptable accuracy for FSI problems involving laminar flows can be obtained with only fewer levels of refinement. In particular, we show that three levels of adaptive refinement are sufficient for obtaining force and displacement values of acceptable accuracy for laminar fluid-structure interaction problems.

cs.CE↗

arXiv2022

From Bitcoin to Solana -- Innovating Blockchain towards Enterprise Applications

This survey presents a comprehensive study of recent advances in block-chain technologies, focusing on how issues that affecting the enterprise adoption were progressively addressed from the original Bitcoin system to Ethereum, to Solana etc. Key issues preventing the wide adoption are scala-bility and performance, while recent advances in Solana has clearly demon-strated that it is possible to significantly improve on those issues by innovat-ing on data structure, processes and algorithms by consolidating various time-consuming algorithms and security enforcements, and differentiate and balance users and their responsibilities and rights, while maintaining the re-quired security and integrity that blockchain systems inherently offer.

cs.CR↗

arXiv2022

DAMO-NLP at SemEval-2022 Task 11: A Knowledge-based System for Multilingual Named Entity Recognition

The MultiCoNER shared task aims at detecting semantically ambiguous and complex named entities in short and low-context settings for multiple languages. The lack of contexts makes the recognition of ambiguous named entities challenging. To alleviate this issue, our team DAMO-NLP proposes a knowledge-based system, where we build a multilingual knowledge base based on Wikipedia to provide related context information to the named entity recognition (NER) model. Given an input sentence, our system effectively retrieves related contexts from the knowledge base. The original input sentences are then augmented with such context information, allowing significantly better contextualized token representations to be captured. Our system wins 10 out of 13 tracks in the MultiCoNER shared task.

cs.CL↗

arXiv2022

Final bound-state formation effect on dark matter annihilation

If the annihilation products of dark matter (DM) are non-relativistic and couples directly to a light force mediator, the non-perturbation effect like final state bound state (FBS) formation and final state Sommerfeld (FSS) effect must be considered. Non-relativistic region of final particles will appear when there is small mass split between DM and products, so we study those effects in the degenerate region of mass (including kinematics forbidden case) using two specific models. We demonstrate that FBS effect will significantly modify the DM relic abundance comparing to the standard perturbation calculation in some mass split region. We emphasize that FBS effect is comparable to the FSS effect in those mass split. The conservation angular momentum are subtle considering FBS formation, in some cases there may be not $s$-wave, so we use two models exhibit the different partial wave FBS effect contribution. We also show that the FBS formation with vector boson emission process also contributes in DM relic abundance, and first calculate the $p$-wave FSS effect in the specific model.

hep-ph↗

arXiv2022

WebRobot: Web Robotic Process Automation using Interactive Programming-by-Demonstration

It is imperative to democratize robotic process automation (RPA), as RPA has become a main driver of the digital transformation but is still technically very demanding to construct, especially for non-experts. In this paper, we study how to automate an important class of RPA tasks, dubbed web RPA, which are concerned with constructing software bots that automate interactions across data and a web browser. Our main contributions are twofold. First, we develop a formal foundation which allows semantically reasoning about web RPA programs and formulate its synthesis problem in a principled manner. Second, we propose a web RPA program synthesis algorithm based on a new idea called speculative rewriting. This leads to a novel speculate-and-validate methodology in the context of rewrite-based program synthesis, which has also shown to be both theoretically simple and practically efficient for synthesizing programs from demonstrations. We have built these ideas in a new interactive synthesizer called WebRobot and evaluate it on 76 web RPA benchmarks. Our results show that WebRobot automated a majority of them effectively. Furthermore, we show that WebRobot compares favorably with a conventional rewrite-based synthesis baseline implemented using egg. Finally, we conduct a small user study demonstrating WebRobot is also usable.

cs.PL↗

arXiv2022

Automated Evaluation for Student Argumentative Writing: A Survey

This paper surveys and organizes research works in an under-studied area, which we call automated evaluation for student argumentative writing. Unlike traditional automated writing evaluation that focuses on holistic essay scoring, this field is more specific: it focuses on evaluating argumentative essays and offers specific feedback, including argumentation structures, argument strength trait score, etc. The focused and detailed evaluation is useful for helping students acquire important argumentation skill. In this paper we organize existing works around tasks, data and methods. We further experiment with BERT on representative datasets, aiming to provide up-to-date baselines for this field.

cs.CL↗

arXiv2022

Stability of China's Stock Market: Measure and Forecast by Ricci Curvature on Network

The systemic stability of a stock market is one of the core issues in the financial field. The market can be regarded as a complex network whose nodes are stocks connected by edges that signify their correlation strength. Since the market is a strongly nonlinear system, it is difficult to measure the macroscopic stability and depict market fluctuations in time. In this paper, we use a geometric measure derived from discrete Ricci curvature to capture the higher-order nonlinear architecture of financial networks. In order to confirm the effectiveness of our method, we use it to analyze the CSI 300 constituents of China's stock market from 2005--2020 and the systemic stability of the market is quantified through the network's Ricci type curvatures. Furthermore, we use a hybrid model to analyze the curvature time series and predict the future trends of the market accurately. As far as we know, this is the first paper to apply Ricci curvature to forecast the systemic stability of domestic stock market, and our results show that Ricci curvature has good explanatory power for the market stability and can be a good indicator to judge the future risk and volatility of the domestic market.

q-fin.ST↗

arXiv2022

Transfinite Modal Logic: a Semi-quantitative Explanation for Bayesian Reasoning

Bayesian reasoning plays a significant role both in human rationality and in machine learning. In this paper, we introduce transfinite modal logic, which combines modal logic with ordinal arithmetic, in order to formalize Bayesian reasoning semi-quantitatively. Technically, we first investigate some nontrivial properties of ordinal arithmetic, which then enable us to expand normal modal logic's semantics naturally and elegantly onto the novel transfinite modal logic, while still keeping the ordinary definition of Kripke models totally intact. Despite all the transfinite mathematical definition, we argue that in practice, this logic can actually fit into a completely finite interpretation as well. We suggest that transfinite modal logic captures the essence of Bayesian reasoning in a rather clear and simple form, in particular, it provides a perfect explanation for Sherlock Holmes' famous saying, "When you have eliminated the impossible, whatever remains, however improbable, must be the truth." We also prove a counterpart of finite model property theorem for our logic.

cs.AI↗

arXiv2022

Design of a Biomimetic Tactile Sensor for Material Classification

Tactile sensing typically involves active exploration of unknown surfaces and objects, making it especially effective at processing the characteristics of materials and textures. A key property extracted by human tactile perception is surface roughness, which relies on measuring vibratory signals using the multi-layered fingertip structure. Existing robotic systems lack tactile sensors that are able to provide high dynamic sensing ranges, perceive material properties, and maintain a low hardware cost. In this work, we introduce the reference design and fabrication procedure of a miniature and low-cost tactile sensor consisting of a biomimetic cutaneous structure, including the artificial fingerprint, dermis, epidermis, and an embedded magnet-sensor structure which serves as a mechanoreceptor for converting mechanical information to digital signals. The presented sensor is capable of detecting high-resolution magnetic field data through the Hall effect and creating high-dimensional time-frequency domain features for material texture classification. Additionally, we investigate the effects of different superficial sensor fingerprint patterns for classifying materials through both simulation and physical experimentation. After extracting time series and frequency domain features, we assess a k-nearest neighbors classifier for distinguishing between different materials. The results from our experiments show that our biomimetic tactile sensors with fingerprint ridges can classify materials with more than 8% higher accuracy and lower variability than ridge-less sensors. These results, along with the low cost and customizability of our sensor, demonstrate high potential for lowering the barrier to entry for a wide array of robotic applications, including model-less tactile sensing for texture classification, material inspection, and object recognition.

cs.RO↗

arXiv2021

Repairing Adversarial Texts through Perturbation

It is known that neural networks are subject to attacks through adversarial perturbations, i.e., inputs which are maliciously crafted through perturbations to induce wrong predictions. Furthermore, such attacks are impossible to eliminate, i.e., the adversarial perturbation is still possible after applying mitigation methods such as adversarial training. Multiple approaches have been developed to detect and reject such adversarial inputs, mostly in the image domain. Rejecting suspicious inputs however may not be always feasible or ideal. First, normal inputs may be rejected due to false alarms generated by the detection algorithm. Second, denial-of-service attacks may be conducted by feeding such systems with adversarial inputs. To address the gap, in this work, we propose an approach to automatically repair adversarial texts at runtime. Given a text which is suspected to be adversarial, we novelly apply multiple adversarial perturbation methods in a positive way to identify a repair, i.e., a slightly mutated but semantically equivalent text that the neural network correctly classifies. Our approach has been experimented with multiple models trained for natural language processing tasks and the results show that our approach is effective, i.e., it successfully repairs about 80\% of the adversarial texts. Furthermore, depending on the applied perturbation method, an adversarial text could be repaired in as short as one second on average.

cs.CL↗

arXiv2021

Two-dimensional Ferroelectric Ga2O3 Bilayers with Unusual Strain-engineered Interlayer Interactions

Two-dimensional (2D) van der Waals (vdW) materials and their bilayers have stimulated enormous interests in fundamental researches and technological applications. Recently, a group of 2D vdW III2-VI3 materials with out-of-plane ferroelectricity have attracted substantial attentions. In this work, the structural, electronic and optical properties of 2D ferroelectric Ga2O3 bilayer system are systematically studied using ab-initio computational method. Intrinsic dipoles of the two freestanding monolayers lead to three distinct dipole models (one ferroelectric and two antiferroelectric models). The stable stacking configurations of ferroelectric and antiferroelectric dipole models can be transferred with polarization reversal transition of the monolayers without additional operation. Interlayer perturbation effects combined with biaxial-strain engineering lead to high tunablility of the electronic and optical properties of the bilayer systems. Surprisingly, the results reveal a phase transition from vdW to ionic interlayer interaction induced by in-plane biaxial tensile strain. Detailed analyses suggest a transition mechanism based on the ionic bonding nature of the Ga2O3 system, involving interlayer rearrangement of anions to compensate the symmetry breaking of the heavily distorted ionic folding configurations. These insights can open new prospects for future experimental synthesis, characterization and application of 2D Ga2O3 atomic-thin layered systems.

cond-mat.mtrl-sci↗

arXiv2021

Fairness Testing of Deep Image Classification with Adequacy Metrics

As deep image classification applications, e.g., face recognition, become increasingly prevalent in our daily lives, their fairness issues raise more and more concern. It is thus crucial to comprehensively test the fairness of these applications before deployment. Existing fairness testing methods suffer from the following limitations: 1) applicability, i.e., they are only applicable for structured data or text without handling the high-dimensional and abstract domain sampling in the semantic level for image classification applications; 2) functionality, i.e., they generate unfair samples without providing testing criterion to characterize the model's fairness adequacy. To fill the gap, we propose DeepFAIT, a systematic fairness testing framework specifically designed for deep image classification applications. DeepFAIT consists of several important components enabling effective fairness testing of deep image classification applications: 1) a neuron selection strategy to identify the fairness-related neurons; 2) a set of multi-granularity adequacy metrics to evaluate the model's fairness; 3) a test selection algorithm for fixing the fairness issues efficiently. We have conducted experiments on widely adopted large-scale face recognition applications, i.e., VGGFace and FairFace. The experimental results confirm that our approach can effectively identify the fairness-related neurons, characterize the model's fairness, and select the most valuable test cases to mitigate the model's fairness issues.

cs.LG↗

arXiv2021

Learning Dynamic Preference Structure Embedding From Temporal Networks

The dynamics of temporal networks lie in the continuous interactions between nodes, which exhibit the dynamic node preferences with time elapsing. The challenges of mining temporal networks are thus two-fold: the dynamic structure of networks and the dynamic node preferences. In this paper, we investigate the dynamic graph sampling problem, aiming to capture the preference structure of nodes dynamically in cooperation with GNNs. Our proposed Dynamic Preference Structure (DPS) framework consists of two stages: structure sampling and graph fusion. In the first stage, two parameterized samplers are designed to learn the preference structure adaptively with network reconstruction tasks. In the second stage, an additional attention layer is designed to fuse two sampled temporal subgraphs of a node, generating temporal node embeddings for downstream tasks. Experimental results on many real-life temporal networks show that our DPS outperforms several state-of-the-art methods substantially owing to learning an adaptive preference structure. The code will be released soon at https://github.com/doujiang-zheng/Dynamic-Preference-Structure.

cs.IR↗

arXiv2021

Real-time intelligent big data processing: technology, platform, and applications

Human beings keep exploring the physical space using information means. Only recently, with the rapid development of information technologies and the increasing accumulation of data, human beings can learn more about the unknown world with data-driven methods. Given data timeliness, there is a growing awareness of the importance of real-time data. There are two categories of technologies accounting for data processing: batching big data and streaming processing, which have not been integrated well. Thus, we propose an innovative incremental processing technology named after Stream Cube to process both big data and stream data. Also, we implement a real-time intelligent data processing system, which is based on real-time acquisition, real-time processing, real-time analysis, and real-time decision-making. The real-time intelligent data processing technology system is equipped with a batching big data platform, data analysis tools, and machine learning models. Based on our applications and analysis, the real-time intelligent data processing system is a crucial solution to the problems of the national society and economy.

cs.DC↗