arXiv subjects

Tao Zhang

Publications and source records attributed to Tao Zhang.

At least 469 records · Page 26Linked to original sources

arXiv2022

Coevolutionary Framework for Generalized Multimodal Multi-objective Optimization

Most multimodal multi-objective evolutionary algorithms (MMEAs) aim to find all global Pareto optimal sets (PSs) for a multimodal multi-objective optimization problem (MMOP). However, in real-world problems, decision makers (DMs) may be also interested in local PSs. Also, searching for both global and local PSs is more general in view of dealing with MMOPs, which can be seen as a generalized MMOP. In addition, the state-of-the-art MMEAs exhibit poor convergence on high-dimension MMOPs. To address the above two issues, in this study, a novel coevolutionary framework termed CoMMEA for multimodal multi-objective optimization is proposed to better obtain both global and local PSs, and simultaneously, to improve the convergence performance in dealing with high-dimension MMOPs. Specifically, the CoMMEA introduces two archives to the search process, and coevolves them simultaneously through effective knowledge transfer. The convergence archive assists the CoMMEA to quickly approaching the Pareto optimal front (PF). The knowledge of the converged solutions is then transferred to the diversity archive which utilizes the local convergence indicator and the $ε$-dominance-based method to obtain global and local PSs effectively. Experimental results show that CoMMEA is competitive compared to seven state-of-the-art MMEAs on fifty-four complex MMOPs.

cs.NE↗

arXiv2022

Extending structures for left-symmetric bialgebras

We introduce the concept of braided left-symmetric bialgebras and construct cocycle bicrossproduct left-symmetric bialgebras. As an application, we solve the extending problem for left-symmetric bialgebras by using some non-abelian cohomology theory.

math.RA↗

arXiv2022

Do Pre-trained Language Models Indeed Understand Software Engineering Tasks?

Artificial intelligence (AI) for software engineering (SE) tasks has recently achieved promising performance. In this paper, we investigate to what extent the pre-trained language model truly understands those SE tasks such as code search, code summarization, etc. We conduct a comprehensive empirical study on a board set of AI for SE (AI4SE) tasks by feeding them with variant inputs: 1) with various masking rates and 2) with sufficient input subset method. Then, the trained models are evaluated on different SE tasks, including code search, code summarization, and duplicate bug report detection. Our experimental results show that pre-trained language models are insensitive to the given input, thus they achieve similar performance in these three SE tasks. We refer to this phenomenon as overinterpretation, where a model confidently makes a decision without salient features, or where a model finds some irrelevant relationships between the final decision and the dataset. Our study investigates two approaches to mitigate the overinterpretation phenomenon: whole word mask strategy and ensembling. To the best of our knowledge, we are the first to reveal this overinterpretation phenomenon to the AI4SE community, which is an important reminder for researchers to design the input for the models and calls for necessary future work in understanding and implementing AI4SE tasks.

cs.SE↗

arXiv2022

Geo-MOEA: A Multi-Objective Evolutionary Algorithm with Geo-obfuscation for Mobile Crowdsourcing Workers

The rapid development of mobile Internet and sharing economy brings the prosperity of Spatial Crowdsourcing (SC). SC applications assign various tasks according to reported location information of task's requesters and outsourced workers (such as DiDi, MeiTuan and Uber). However, SC-servers are often untrustworthy and the exposure of users' locations raises privacy concerns. In this paper, we design a framework called Geo-MOEA (Multi-Objective Evolutionary Algorithm with Geo-obfuscation) to protect location privacy of workers involved on SC platform in mobile networks environment. We propose an adaptive regionalized obfuscation approach with inference error bounds based on geo-indistinguishability (a strong notion of differential privacy), which is suitable for the context of large-scale location data and task allocations. This enables each worker to report a pseudo-location that is adaptively generated with a personalized inference error threshold. Moreover, as a popular computational intelligence method, MOEA is introduced to optimize the trade-off between SC service availability and privacy protection while ensuring theoretically the most general condition on protection location sets for larger search space. Finally, the experimental results on two public datasets show that our Geo-MOEA approach achieves up to 20% reduction in service quality loss while guaranteeing differential and geo-distortion location privacy.

cs.CR↗

arXiv2022

BuildMapper: A Fully Learnable Framework for Vectorized Building Contour Extraction

Deep learning based methods have significantly boosted the study of automatic building extraction from remote sensing images. However, delineating vectorized and regular building contours like a human does remains very challenging, due to the difficulty of the methodology, the diversity of building structures, and the imperfect imaging conditions. In this paper, we propose the first end-to-end learnable building contour extraction framework, named BuildMapper, which can directly and efficiently delineate building polygons just as a human does. BuildMapper consists of two main components: 1) a contour initialization module that generates initial building contours; and 2) a contour evolution module that performs both contour vertex deformation and reduction, which removes the need for complex empirical post-processing used in existing methods. In both components, we provide new ideas, including a learnable contour initialization method to replace the empirical methods, dynamic predicted and ground truth vertex pairing for the static vertex correspondence problem, and a lightweight encoder for vertex information extraction and aggregation, which benefit a general contour-based method; and a well-designed vertex classification head for building corner vertices detection, which casts light on direct structured building contour extraction. We also built a suitable large-scale building dataset, the WHU-Mix (vector) building dataset, to benefit the study of contour-based building extraction methods. The extensive experiments conducted on the WHU-Mix (vector) dataset, the WHU dataset, and the CrowdAI dataset verified that BuildMapper can achieve a state-of-the-art performance, with a higher mask average precision (AP) and boundary AP than both segmentation-based and contour-based methods.

cs.CV↗

arXiv2022

Braided anti-flexible bialgebras

We introduce the concept of braided anti-flexible bialgebra and construct cocycle bicrossproduct anti-flexible bialgebras. As an application, we solve the extending problem for anti-flexible bialgebras by using some non-abelian cohomology theory.

math.RA↗

arXiv2022

A group ring approach to Fuglede's conjecture in cyclic groups

Fuglede's conjecture states that a subset $Ω\subseteq\mathbb{R}^{n}$ of positive and finite Lebesgue measure is a spectral set if and only if it tiles $\mathbb{R}^{n}$ by translation. The conjecture does not hold in both directions for $\mathbb{R}^n$, $n\ge3$. However, this conjecture remains open in $\mathbb{R}$ and $\mathbb{R}^2$. Cyclic groups play important roles in the study of Fuglede's conjecture in $\mathbb{R}$. In this paper, we introduce a new tool to study the spectral sets in cyclic groups. In particular, we prove that Fuglede's conjecture holds in $\mathbb{Z}_{p^{n}qr}$.

math.CO↗

arXiv2022

A Unified Positive-Unlabeled Learning Framework for Document-Level Relation Extraction with Different Levels of Labeling

Document-level relation extraction (RE) aims to identify relations between entities across multiple sentences. Most previous methods focused on document-level RE under full supervision. However, in real-world scenario, it is expensive and difficult to completely label all relations in a document because the number of entity pairs in document-level RE grows quadratically with the number of entities. To solve the common incomplete labeling problem, we propose a unified positive-unlabeled learning framework - shift and squared ranking loss positive-unlabeled (SSR-PU) learning. We use positive-unlabeled (PU) learning on document-level RE for the first time. Considering that labeled data of a dataset may lead to prior shift of unlabeled data, we introduce a PU learning under prior shift of training data. Also, using none-class score as an adaptive threshold, we propose squared ranking loss and prove its Bayesian consistency with multi-label ranking metrics. Extensive experiments demonstrate that our method achieves an improvement of about 14 F1 points relative to the previous baseline with incomplete labeling. In addition, it outperforms previous state-of-the-art results under both fully supervised and extremely unlabeled settings as well.

cs.CL↗

arXiv2022

A Penalized Inequality-Constrained Approach for Robust Beamforming with DoF Limitation

A well-known challenge in beamforming is how to optimally utilize the degrees of freedom (DoF) of the array to design a robust beamformer, especially when the array DoF is limited. In this paper, we leverage the tool of constrained convex optimization and propose a penalized inequality-constrained minimum variance (P-ICMV) beamformer to address this challenge. Specifically, a well-targeted objective function and inequality constraints are proposed to achieve the design goals. By penalizing the maximum gain of the beamformer at any interfering directions, the total interference power can be efficiently mitigated with limited DoF. Multiple robust constraints on the target protection and interference suppression can be introduced to increase the robustness of the beamformer against steering vector mismatch. By integrating the noise reduction, interference suppression, and target protection, the proposed formulation can efficiently obtain a robust beamformer design while optimally trading off various design goals. To numerically solve this problem, we formulate the P-ICMV beamformer design as a convex second-order cone program (SOCP) and propose a low complexity iterative algorithm based on the alternating direction method of multipliers (ADMM). Three applications are simulated to demonstrate the effectiveness of the proposed beamformer.

cs.IT↗

arXiv2022

First search for the absorption of fermionic dark matter with the PandaX-4T experiment

Compared with the signature of dark matter elastic scattering off nuclei, the absorption of fermionic dark matter by nuclei opens up a new searching channel for light dark matter with a characteristic monoenergetic signal. In this Letter, we explore the $95.0$-day data from the PandaX-4T commissioning run and report the first dedicated searching results of the fermionic dark matter absorption signal through a neutral current process. No significant signal was found, and the lowest limit on the dark matter-nucleon interaction cross section is set to be $1.5\times10^{-50}$ cm$^2$ for a fermionic dark matter mass of $40$ MeV/$c^2$ with 90\% confidence level.

hep-ex↗

arXiv2022

A Complementary Framework for Human-Robot Collaboration with a Mixed AR-Haptic Interface

There is invariably a trade-off between safety and efficiency for collaborative robots (cobots) in human-robot collaborations. Robots that interact minimally with humans can work with high speed and accuracy but cannot adapt to new tasks or respond to unforeseen changes, whereas robots that work closely with humans can but only by becoming passive to humans, meaning that their main tasks suspended and efficiency compromised. Accordingly, this paper proposes a new complementary framework for human-robot collaboration that balances the safety of humans and the efficiency of robots. In this framework, the robot carries out given tasks using a vision-based adaptive controller, and the human expert collaborates with the robot in the null space. Such a decoupling drives the robot to deal with existing issues in task space (e.g., uncalibrated camera, limited field of view) and in null space (e.g., joint limits) by itself while allowing the expert to adjust the configuration of the robot body to respond to unforeseen changes (e.g., sudden invasion, change of environment) without affecting the robot's main task. Additionally, the robot can simultaneously learn the expert's demonstration in task space and null space beforehand with dynamic movement primitives (DMP). Therefore, an expert's knowledge and a robot's capability are both explored and complementary. Human demonstration and involvement are enabled via a mixed interaction interface, i.e., augmented reality (AR) and haptic devices. The stability of the closed-loop system is rigorously proved with Lyapunov methods. Experimental results in various scenarios are presented to illustrate the performance of the proposed method.

cs.RO↗

arXiv2022

Locally finite infinity-modules and weak Loday-Pirashvili modules over differential graded Lie algebras

Motivated by recent developments of $\infty$-categorical theories related to differential graded (dg for short) Lie algebras, we develop a general framework for locally finite $\infty$-$\mathfrak{g}$-modules over a dg Lie algebra $\mathfrak{g}$. We show that the category of such locally finite $\infty$-$\mathfrak{g}$-modules is almost a model category in the sense of Vallette. As a homotopy theoretical generalization of Loday and Pirashvili's Lie algebra objects in the tensor category of linear maps, we further study weak Loday-Pirashvili modules consisting of $\infty$-morphisms from locally finite $\infty$-$\mathfrak{g}$-modules to the adjoint module $\mathfrak{g}$. From the category of such weak Loday-Pirashvili modules over $\mathfrak{g}$, we find a functor that maps to the category of Leibniz$_\infty$ algebras enriched over the Chevalley-Eilenberg dg algebra of $\mathfrak{g}$. This functor can be regarded as the homotopy lifting of Loday and Pirashvili's original method to realize Leibniz algebras from Lie algebra objects in the category of linear maps.

math.RT↗

arXiv2022

Spiking SiamFC++: Deep Spiking Neural Network for Object Tracking

Spiking neural network (SNN) is a biologically-plausible model and exhibits advantages of high computational capability and low power consumption. While the training of deep SNN is still an open problem, which limits the real-world applications of deep SNN. Here we propose a deep SNN architecture named Spiking SiamFC++ for object tracking with end-to-end direct training. Specifically, the AlexNet network is extended in the time domain to extract the feature, and the surrogate gradient function is adopted to realize direct supervised training of the deep SNN. To examine the performance of the Spiking SiamFC++, several tracking benchmarks including OTB2013, OTB2015, VOT2015, VOT2016, and UAV123 are considered. It is found that, the precision loss is small compared with the original SiamFC++. Compared with the existing SNN-based target tracker, e.g., the SiamSNN, the precision (succession) of the proposed Spiking SiamFC++ reaches 85.24% (64.37%), which is much higher than that of 52.78% (44.32%) achieved by the SiamSNN. To our best knowledge, the performance of the Spiking SiamFC++ outperforms the existing state-of-the-art approaches in SNN-based object tracking, which provides a novel path for SNN application in the field of target tracking. This work may further promote the development of SNN algorithms and neuromorphic chips.

cs.CV↗

arXiv2022

Design and Operation of the PandaX-4T High Speed Ultra-high Purity Xenon Recuperation System

In order to recuperate the ultra-high purity xenon from PandaX-4T dark matter detector to high-pressure gas cylinders in emergency or at the end-of-run situation, a high speed ultra-high purity xenon recuperation system is designed and developed. This system includes a diaphragm pump, the heat management system, the main recuperation pipeline, the reflux pipeline, the auxiliary recuperation pipeline and the automatic control system. The liquid xenon in the detector is vaporized by the heat management system, and the gaseous xenon is compressed to 6 MPa at the flow rate of 200 standard litres per minute (SLPM) using the diaphragm compressor. The high-pressure xenon is filled into 128 gas cylinders via the main recuperation pipeline. During the recuperation, the low pressure and temperature conditions of 2 ~ 3 atmospheres and 178 ~ 186.5 K in PandaX-4T dark matter detector are kept by the cooperation of the main recuperation pipeline, reflux pipeline and the auxiliary recuperation pipeline to guarantee the safety, and the purity of the recuperated xenon gas is measured to ensure no contamination happened. The development of the high speed ultra-high purity xenon recuperation system is important for the operation of large-scale dark matter detectors with the requirements of strict temperature and pressure environment and low background.

physics.ins-det↗

arXiv2022

SelfAPR: Self-supervised Program Repair with Test Execution Diagnostics

Learning-based program repair has achieved good results in a recent series of papers. Yet, we observe that the related work fails to repair some bugs because of a lack of knowledge about 1) the application domain of the program being repaired, and 2) the fault type being repaired. In this paper, we solve both problems by changing the learning paradigm from supervised training to self-supervised training in an approach called SelfAPR. First, SelfAPR generates training samples on disk by perturbing a previous version of the program being repaired, enforcing the neural model to capture projectspecific knowledge. This is different from the previous work based on mined past commits. Second, SelfAPR executes all training samples and extracts and encodes test execution diagnostics into the input representation, steering the neural model to fix the kind of fault. This is different from the existing studies that only consider static source code as input. We implement SelfAPR and evaluate it in a systematic manner. We generate 1 039 873 training samples obtained by perturbing 17 open-source projects. We evaluate SelfAPR on 818 bugs from Defects4J, SelfAPR correctly repairs 110 of them, outperforming all the supervised learning repair approaches.

cs.SE↗

arXiv2022

Kernel-Function Based Quantum Algorithms for Finite Temperature Quantum Simulation

Computing finite temperature properties of a quantum many-body system is key to describing a broad range of correlated quantum many-body physics from quantum chemistry and condensed matter to thermal quantum field theories. Quantum computing with rapid developments in recent years has a huge potential to impact the computation of quantum thermodynamics. To fulfill the potential impacts, it is crucial to design quantum algorithms that utilize the computation power of the quantum computing devices. Here we present a quantum kernel function expansion (QKFE) algorithm for solving thermodynamic properties of quantum many-body systems. In this quantum algorithm, the many-body density of states is approximated by a kernel-Fourier expansion, whose expansion moments are obtained by random state sampling and quantum interferometric measurements. As compared to its classical counterpart, namely the kernel polynomial method (KPM), QKFE has an exponential advantage in the cost of both time and memory. In computing low temperature properties, QKFE becomes inefficient, as similar to classical KPM. To resolve this difficulty, we further construct a thermal ensemble and approaches the low temperature regime step-by-step. For quantum Hamiltonians, whose ground states are preparable with polynomial quantum circuits, THEI has an overall polynomial complexity. We demonstrate its efficiency with applications to one and two-dimensional quantum spin models, and a fermionic lattice. With our analysis on the realization with digital and analogue quantum devices, we expect the quantum algorithm is accessible to current quantum technology.

quant-ph↗

arXiv2022

Modeling Two-Way Selection Preference for Person-Job Fit

Person-job fit is the core technique of online recruitment platforms, which can improve the efficiency of recruitment by accurately matching the job positions with the job seekers. Existing works mainly focus on modeling the unidirectional process or overall matching. However, recruitment is a two-way selection process, which means that both candidate and employer involved in the interaction should meet the expectation of each other, instead of unilateral satisfaction. In this paper, we propose a dual-perspective graph representation learning approach to model directed interactions between candidates and jobs. To model the two-way selection preference from the dual-perspective of job seekers and employers, we incorporate two different nodes for each candidate (or job) and characterize both successful matching and failed matching via a unified dual-perspective interaction graph. To learn dual-perspective node representations effectively, we design an effective optimization algorithm, which involves a quadruple-based loss and a dual-perspective contrastive learning loss. Extensive experiments on three large real-world recruitment datasets have shown the effectiveness of our approach.

cs.IR↗

arXiv2022

Patient-Specific Game-Based Transfer Method for Parkinson's Disease Severity Prediction

Dysphonia is one of the early symptoms of Parkinson's disease (PD). Most existing methods use feature selection methods to find the optimal subset of voice features for all PD patients. Few have considered the heterogeneity between patients, which implies the need to provide specific prediction models for different patients. However, building the specific model faces the challenge of small sample size, which makes it lack generalization ability. Instance transfer is an effective way to solve this problem. Therefore, this paper proposes a patient-specific game-based transfer (PSGT) method for PD severity prediction. First, a selection mechanism is used to select PD patients with similar disease trends to the target patient from the source domain, which greatly reduces the risk of negative transfer. Then, the contribution of the transferred subjects and their instances to the disease estimation of the target subject is fairly evaluated by the Shapley value, which improves the interpretability of the method. Next, the proportion of valid instances in the transferred subjects is determined, and the instances with higher contribution are transferred to further reduce the difference between the transferred instance subset and the target subject. Finally, the selected subset of instances is added to the training set of the target subject, and the extended data is fed into the random forest to improve the performance of the method. Parkinson's telemonitoring dataset is used to evaluate the feasibility and effectiveness. Experiment results show that the PSGT has better performance in both prediction error and stability over compared methods.

cs.LG↗