arXiv subjects

Xue Li

Publications and source records attributed to Xue Li.

At least 127 records · Page 7Linked to original sources

arXiv2022

Tired of Over-smoothing? Stress Graph Drawing Is All You Need!

In designing and applying graph neural networks, we often fall into some optimization pitfalls, the most deceptive of which is that we can only build a deep model by solving over-smoothing. The fundamental reason is that we do not understand how graph neural networks work. Stress graph drawing can offer a unique viewpoint to message iteration in the graph, such as the root of the over-smoothing problem lies in the inability of graph models to maintain an ideal distance between nodes. We further elucidate the trigger conditions of over-smoothing and propose Stress Graph Neural Networks. By introducing the attractive and repulsive message passing from stress iteration, we show how to build a deep model without preventing over-smoothing, how to use repulsive information, and how to optimize the current message-passing scheme to approximate the full stress message propagation. By performing different tasks on 23 datasets, we verified the effectiveness of our attractive and repulsive models and the derived relationship between stress iteration and graph neural networks. We believe that stress graph drawing will be a popular resource for understanding and designing graph neural networks.

cs.LG↗

arXiv2022

Causal Coupled Mechanisms: A Control Method with Cooperation and Competition for Complex System

Complex systems are ubiquitous in the real world and tend to have complicated and poorly understood dynamics. For their control issues, the challenge is to guarantee accuracy, robustness, and generalization in such bloated and troubled environments. Fortunately, a complex system can be divided into multiple modular structures that human cognition appears to exploit. Inspired by this cognition, a novel control method, Causal Coupled Mechanisms (CCMs), is proposed that explores the cooperation in division and competition in combination. Our method employs the theory of hierarchical reinforcement learning (HRL), in which 1) the high-level policy with competitive awareness divides the whole complex system into multiple functional mechanisms, and 2) the low-level policy finishes the control task of each mechanism. Specifically for cooperation, a cascade control module helps the series operation of CCMs, and a forward coupled reasoning module is used to recover the coupling information lost in the division process. On both synthetic systems and a real-world biological regulatory system, the CCM method achieves robust and state-of-the-art control results even with unpredictable random noise. Moreover, generalization results show that reusing prepared specialized CCMs helps to perform well in environments with different confounders and dynamics.

cs.AI↗

arXiv2022

TEDL: A Two-stage Evidential Deep Learning Method for Classification Uncertainty Quantification

In this paper, we propose TEDL, a two-stage learning approach to quantify uncertainty for deep learning models in classification tasks, inspired by our findings in experimenting with Evidential Deep Learning (EDL) method, a recently proposed uncertainty quantification approach based on the Dempster-Shafer theory. More specifically, we observe that EDL tends to yield inferior AUC compared with models learnt by cross-entropy loss and is highly sensitive in training. Such sensitivity is likely to cause unreliable uncertainty estimation, making it risky for practical applications. To mitigate both limitations, we propose a simple yet effective two-stage learning approach based on our analysis on the likely reasons causing such sensitivity, with the first stage learning from cross-entropy loss, followed by a second stage learning from EDL loss. We also re-formulate the EDL loss by replacing ReLU with ELU to avoid the Dying ReLU issue. Extensive experiments are carried out on varied sized training corpus collected from a large-scale commercial search engine, demonstrating that the proposed two-stage learning framework can increase AUC significantly and greatly improve training robustness.

cs.LG↗

arXiv2022

Real2Sim or Sim2Real: Robotics Visual Insertion using Deep Reinforcement Learning and Real2Sim Policy Adaptation

Reinforcement learning has shown a wide usage in robotics tasks, such as insertion and grasping. However, without a practical sim2real strategy, the policy trained in simulation could fail on the real task. There are also wide researches in the sim2real strategies, but most of those methods rely on heavy image rendering, domain randomization training, or tuning. In this work, we solve the insertion task using a pure visual reinforcement learning solution with minimum infrastructure requirement. We also propose a novel sim2real strategy, Real2Sim, which provides a novel and easier solution in policy adaptation. We discuss the advantage of Real2Sim compared with Sim2Real.

cs.RO↗

arXiv2022

Integrating Dependency Tree Into Self-attention for Sentence Representation

Recent progress on parse tree encoder for sentence representation learning is notable. However, these works mainly encode tree structures recursively, which is not conducive to parallelization. On the other hand, these works rarely take into account the labels of arcs in dependency trees. To address both issues, we propose Dependency-Transformer, which applies a relation-attention mechanism that works in concert with the self-attention mechanism. This mechanism aims to encode the dependency and the spatial positional relations between nodes in the dependency tree of sentences. By a score-based method, we successfully inject the syntax information without affecting Transformer's parallelizability. Our model outperforms or is comparable to the state-of-the-art methods on four tasks for sentence representation and has obvious advantages in computational efficiency.

cs.CL↗

arXiv2022

Attack Detection for Networked Control Systems Using Event-Triggered Dynamic Watermarking

Dynamic watermarking schemes can enhance the cyber attack detection capability of networked control systems (NCSs). This paper presents a linear event-triggered solution to conventional dynamic watermarking (CDW) schemes. Firstly, the limitations of CDW schemes for event-triggered state estimation based NCSs are investigated. Secondly, a new event-triggered dynamic watermarking (ETDW) scheme is designed by treating watermarking as symmetric key encryption, based on the limit convergence theorem in probability. Its security property against the generalized replay attacks (GRAs) is also discussed in the form of bounded asymptotic attack power. Thirdly, finite sample ETDW tests are designed with matrix concentration inequalities. Finally, experimental results of a networked inverted pendulum system demonstrate the validity of our proposed scheme.

cs.CR↗

arXiv2022

Recovery Time Metric Demonstrated on Real-world Electric Grid for Hurricane Impacted Outages

This work proposes a methodology for estimating recovery times for transmission lines and substations, and is demonstrated on a real-world 1269-bus power system model of Puerto Rico under 20 hurricane scenarios, or stochastic realizations of asset failure under the meteorological conditions of Hurricane Maria. The method defines base recovery times for system components and identifies factors that impact these base values by means of multipliers. While the method is tested on transmission lines and substation failures due to hurricanes, it is based on a generic process that could be applied to any system component or event as a general recovery time estimation framework. The results show that given the two failure modes under study (transmission towers and substations), transmission towers appear to have a greater impact on recovery time estimates despite substations being given longer base outage times. Additionally, average recovery times for the simulated hurricanes across 20 scenarios is ~28,000 work crew days.

eess.SY↗

arXiv2022

Signature Entrenchment and Conceptual Changes in Automated Theory Repair

Human beliefs change, but so do the concepts that underpin them. The recent Abduction, Belief Revision and Conceptual Change (ABC) repair system combines several methods from automated theory repair to expand, contract, or reform logical structures representing conceptual knowledge in artificial agents. In this paper we focus on conceptual change: repair not only of the membership of logical concepts, such as what animals can fly, but also concepts themselves, such that birds may be divided into flightless and flying birds, by changing the signature of the logical theory used to represent them. We offer a method for automatically evaluating entrenchment in the signature of a Datalog theory, in order to constrain automated theory repair to succinct and intuitive outcomes. Formally, signature entrenchment measures the inferential contributions of every logical language element used to express conceptual knowledge, i.e., predicates and the arguments, ranking possible repairs to retain valuable logical concepts and reject redundant or implausible alternatives. This quantitative measurement of signature entrenchment offers a guide to the plausibility of conceptual changes, which we aim to contrast with human judgements of concept entrenchment in future work.

cs.CL↗

arXiv2022

Observation of short-period helical spin order and magnetic transition in a non-chiral centrosymmetric helimagnet

The search for materials exhibiting nanoscale spiral order continues to be fuelled by the promise of emergent inductors. Although such spin textures have been reported in many materials, most of them exhibit long periods or are limited to operate far below room temperature. Here, we present the real-space observation of an ordered helical spin order with a period of 3.2 nm in a non-chiral centrosymmetric helimagnet MnCoSi at room temperature via multi-angle and multi-azimuth approach of Lorentz transmission electron microscopy (TEM). A magnetic transition from the ordered helical spin order to a cycloidal spin order below 228 K is clearly revealed by in situ neutron powder diffraction and Lorentz TEM, which is closely correlated with temperature-induced variation in magneto-crystalline anisotropy. These results reveal the origin of spiral ordered spin textures in non-chiral centrosymmetric helimagnet, which can serve as a new strategy for searching materials with nanoscale spin order with potential applications in emergent electromagnetism.

cond-mat.mtrl-sci↗

arXiv2021

Camera-aware Style Separation and Contrastive Learning for Unsupervised Person Re-identification

Unsupervised person re-identification (ReID) is a challenging task without data annotation to guide discriminative learning. Existing methods attempt to solve this problem by clustering extracted embeddings to generate pseudo labels. However, most methods ignore the intra-class gap caused by camera style variance, and some methods are relatively complex and indirect although they try to solve the negative impact of the camera style on feature distribution. To solve this problem, we propose a camera-aware style separation and contrastive learning method (CA-UReID), which directly separates camera styles in the feature space with the designed camera-aware attention module. It can explicitly divide the learnable feature into camera-specific and camera-agnostic parts, reducing the influence of different cameras. Moreover, to further narrow the gap across cameras, we design a camera-aware contrastive center loss to learn more discriminative embedding for each identity. Extensive experiments demonstrate the superiority of our method over the state-of-the-art methods on the unsupervised person ReID task.

cs.CV↗

arXiv2021

Minute-cadence Observations of the LAMOST Fields with the TMTS: I. Methodology of Detecting Short-period Variables and Results from the first-year Survey

Tsinghua University-Ma Huateng Telescopes for Survey (TMTS), located at Xinglong Station of NAOC, has a field of view upto 18 deg^2. The TMTS has started to monitor the LAMOST sky areas since 2020, with the uninterrupted observations lasting for about 6 hours on average for each sky area and a cadence of about 1 minute. Here we introduce the data analysis and preliminary scientific results for the first-year observations, which covered 188 LAMOST plates ( about 1970 deg^2). These observations have generated over 4.9 million uninterrupted light curves, with at least 100 epochs for each of them. These light curves correspond to 4.26 million Gaia-DR2 sources, among which 285 thousand sources are found to have multi-epoch spectra from the LAMOST. By analysing these light curves with the Lomb-Scargle periodograms, we identify more than 3700 periodic variable star candidates with periods below 7.5 hours, primarily consisting of eclipsing binaries and Delta Scuti stars. Those short-period binaries will provide important constraints on theories of binary evolution and possible sources for space gravitational wave experiments in the future. Moreover, we also identified 42 flare stars by searching rapidly-evolving signals in the light curves. The densely-sampled light curves from the TMTS allow us to better quantify the shapes and durations for these flares.

astro-ph.IM↗

arXiv2021

Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning

Federated learning (FL) is a novel machine learning setting that enables on-device intelligence via decentralized training and federated optimization. Deep neural networks' rapid development facilitates the learning techniques for modeling complex problems and emerges into federated deep learning under the federated setting. However, the tremendous amount of model parameters burdens the communication network with a high load of transportation. This paper introduces two approaches for improving communication efficiency by dynamic sampling and top-$k$ selective masking. The former controls the fraction of selected client models dynamically, while the latter selects parameters with top-$k$ largest values of difference for federated updating. Experiments on convolutional image classification and recurrent language modeling are conducted on three public datasets to show our proposed methods' effectiveness.

cs.LG↗

arXiv2021

Secure Control of Networked Control Systems Using Dynamic Watermarking

We here investigate secure control of networked control systems developing a new dynamic watermarking (DW) scheme. Firstly, the weaknesses of the conventional DW scheme are revealed, and the tradeoff between the effectiveness of false data injection attack (FDIA) detection and system performance loss is analysed. Secondly, we propose a new DW scheme, and its attack detection capability is interrogated using the additive distortion power of a closed-loop system. Furthermore, the FDIA detection effectiveness of the closed-loop system is analysed using auto/cross covariance of the signals, where the positive correlation between the FDIA detection effectiveness and the watermarking intensity is measured. Thirdly, the tolerance capacity of FDIA against the closed-loop system is investigated, and theoretical analysis shows that the system performance can be recovered from FDIA using our new DW scheme. Finally, experimental results from a networked inverted pendulum system demonstrate the validity of our proposed scheme.

eess.SY↗

arXiv2021

En route to high Tc superconductivity via Rb substitution of guest metal atoms in SrB3C3 clathrate

Recently, a host/guest clathrate SrB3C3 with sp3-bonded boron-carbon framework was synthesized at around 50 GPa. On the basis of electron count, the structure is understood as guest Sr2+ cations intercalated in the (B3C3)3- framework. Previous calculations suggest that SrB3C3 is a hole conductor with an estimated superconducting critical temperature (Tc) of 42 K at ambient pressure. If atoms with similar radius, such as Rb, can substitute Sr2+ in the lattice, the electronic as well as superconductivity properties of this material will be modified significantly. Here, we perform extensive simulations on the stability and physical properties of Rb-Sr-B3C3 system using first-principles density functional calculation in combination with cluster expansion and CALYPSO structure prediction method. We predict a phonon-mediated superconductor Rb0.5Sr0.5B3C3 with a remarkably high Tc of 78 K at ambient pressure, which is a significant improvement from the estimated value (42 K) in SrB3C3. The current results suggest that substitution of alkali atom in synthesized clathrate SrB3C3 is a viable route toward high-Tc compounds.

cond-mat.mtrl-sci↗

arXiv2021

Magnetic anisotropy and critical behavior of the quaternary van der Waals ferromagnetic material $\bf CrGe_δSi_{1-δ}Te_3$

Recently, two-dimensional ferromagnetism in the family of Chromium compounds $\rm CrXTe_3 (X=Si, Ge)$ has attracted a broad research interest. Despite the structural similarity in $\rm CrTe_6$ octahedra, the size effect of inserted Ge or Si dimer contributes to significant differences in magnetism. Here, we report a new quaternary van der Waals ferromagnetic material $\rm CrGe_δSi_{1-δ}Te_3$ synthesized by flux method. Ge substitution in Si site results in the lattice expansion, further increasing the Curie temperature and reducing the magnetic anisotropy. The critical behavior of $\rm Cr_{0.96}Ge_{0.17}Si_{0.82}Te_3$ has been studied by specific heat as well as magnetization measurements. And the extracted critical exponents are self-consistent and well-obeying the scaling laws, which are closer to the 2D Ising model with interaction decaying as $J(r)\approx r^{-3.44}$.

physics.app-ph↗

arXiv2021

SN 2015bf: a fast declining type II supernova with flash-ionised signatures

We present optical and ultraviolet photometry, as well as optical spectra, for the type II supernova (SN) 2015bf. Our observations cover the phases from $\sim 2$ to $\sim 200$ d after explosion. The first spectrum is characterised by a blue continuum with a blackbody temperature of $\sim 24,000$K and flash-ionised emission lines. After about one week, the spectra of SN 2015bf evolve like those of a regular SN II. From the luminosity of the narrow emission component of H$α$, we deduce that the mass-loss rate is larger than $\sim 3.7\times10^{-3}\,{\rm M_\odot\,yr^{-1}}$. The disappearance of the flash features in the first week after explosion indicates that the circumstellar material is confined within $\sim 6 \times 10^{14}$ cm. Thus, we suggest that the progenitor of SN 2015bf experienced violent mass loss shortly before the supernova explosion. The multiband light curves show that SN 2015bf has a high peak luminosity with an absolute visual magnitude $M_V = -18.11 \pm 0.08$ mag and a fast post-peak decline with a $V$-band decay of $1.22 \pm 0.09$ mag within $\sim 50$ d after maximum light. Moreover, the $R$-band tail luminosity of SN 2015bf is fainter than that of SNe~II with similar peak by 1--2 mag, suggesting a small amount of ${\rm ^{56}Ni}$ ($\sim 0.009\,{\rm M_\odot}$) synthesised during the explosion. Such a low nickel mass indicates that the progenitor of SN 2015bf could be a super-asymptotic-giant-branch star that collapsed owing to electron capture.

astro-ph.HE↗

arXiv2021

Suicidal Ideation and Mental Disorder Detection with Attentive Relation Networks

Mental health is a critical issue in modern society, and mental disorders could sometimes turn to suicidal ideation without effective treatment. Early detection of mental disorders and suicidal ideation from social content provides a potential way for effective social intervention. However, classifying suicidal ideation and other mental disorders is challenging as they share similar patterns in language usage and sentimental polarity. This paper enhances text representation with lexicon-based sentiment scores and latent topics and proposes using relation networks to detect suicidal ideation and mental disorders with related risk indicators. The relation module is further equipped with the attention mechanism to prioritize more critical relational features. Through experiments on three real-world datasets, our model outperforms most of its counterparts.

cs.CL↗

arXiv2021

Heralded entanglement distribution between two absorptive quantum memories

Owing to the inevitable loss in communication channels, the distance of entanglement distribution is limited to approximately 100 kilometres on the ground. Quantum repeaters can circumvent this problem by using quantum memory and entanglement swapping. As the elementary link of a quantum repeater, the heralded distribution of two-party entanglement between two remote nodes has only been realized with built-in-type quantum memories. These schemes suffer from the trade-off between multiplexing capacity and deterministic properties and hence hinder the development of efficient quantum repeaters. Quantum repeaters based on absorptive quantum memories can overcome such limitations because they separate the quantum memories and the quantum light sources. Here we present an experimental demonstration of heralded entanglement between absorptive quantum memories. We build two nodes separated by 3.5 metres, each containing a polarization-entangled photon-pair source and a solid-state quantum memory with bandwidth up to 1 gigahertz. A joint Bell-state measurement in the middle station heralds the successful distribution of maximally entangled states between the two quantum memories with a fidelity of 80.4 $\pm$ 2.2 per cent ($\pm$1 standard deviation). The quantum nodes and channels demonstrated here can serve as an elementary link of a quantum repeater. Moreover, the wideband absorptive quantum memories used in the nodes are compatible with deterministic entanglement sources and can simultaneously support multiplexing, which paves the way for the construction of practical solid-state quantum repeaters and high-speed quantum networks.

quant-ph↗