arXiv subjects

Ming Xu

Publications and source records attributed to Ming Xu.

At least 109 records · Page 6Linked to original sources

arXiv2023

GAME: Generalized deep learning model towards multimodal data integration for early screening of adolescent mental disorders

The timely identification of mental disorders in adolescents is a global public health challenge.Single factor is difficult to detect the abnormality due to its complex and subtle nature. Additionally, the generalized multimodal Computer-Aided Screening (CAS) systems with interactive robots for adolescent mental disorders are not available. Here, we design an android application with mini-games and chat recording deployed in a portable robot to screen 3,783 middle school students and construct the multimodal screening dataset, including facial images, physiological signs, voice recordings, and textual transcripts.We develop a model called GAME (Generalized Model with Attention and Multimodal EmbraceNet) with novel attention mechanism that integrates cross-modal features into the model. GAME evaluates adolescent mental conditions with high accuracy (73.34%-92.77%) and F1-Score (71.32%-91.06%).We find each modality contributes dynamically to the mental disorders screening and comorbidities among various mental disorders, indicating the feasibility of explainable model. This study provides a system capable of acquiring multimodal information and constructs a generalized multimodal integration algorithm with novel attention mechanisms for the early screening of adolescent mental disorders.

cs.LG↗

arXiv2023

Towards Understanding Gradient Approximation in Equality Constrained Deep Declarative Networks

We explore conditions for when the gradient of a deep declarative node can be approximated by ignoring constraint terms and still result in a descent direction for the global loss function. This has important practical application when training deep learning models since the approximation is often computationally much more efficient than the true gradient calculation. We provide theoretical analysis for problems with linear equality constraints and normalization constraints, and show examples where the approximation works well in practice as well as some cautionary tales for when it fails.

cs.LG↗

arXiv2023

Heintze-Kobayashi-Wolf theory for negatively curved homogeneous Finsler manifolds

In this paper, we generalize the Heintze-Kobayashi-Wolf theory to homogeneous Finsler geometry, by proving two main theorems. First, any connected negatively curved homogeneous Finsler manifold is isometric to a Lie group endowed with a left invariant metric, and that Lie group must be simply connected and solvable. Second, the requirement in Heintze's criterion is necessary and sufficient for a real solvable Lie algebra to generate a Lie group which admits negatively curved left invariant Finsler metrics.

math.DG↗

arXiv2023

Adaptive Frequency Green Light Optimal Speed Advisory based on Hybrid Actor-Critic Reinforcement Learning

Green Light Optimal Speed Advisory (GLOSA) system suggests speeds to vehicles to assist them in passing through intersections during green intervals, thus reducing traffic congestion and fuel consumption by minimizing the number of stops and idle times at intersections. However, previous research has focused on optimizing the GLOSA algorithm, neglecting the frequency of speed advisory by the GLOSA system. Specifically, some studies provide speed advisory profile at each decision step, resulting in redundant advisory, while others calculate the optimal speed for the vehicle only once, which cannot adapt to dynamic traffic. In this paper, we propose an Adaptive Frequency GLOSA (AF-GLOSA) model based on Hybrid Proximal Policy Optimization (H-PPO) method, which employs an actor-critic architecture with a hybrid actor network. The hybrid actor network consists of a discrete actor that outputs control gap and a continuous actor that outputs acceleration profiles. Additionally, we design a novel reward function that considers both travel efficiency and fuel consumption. The AF-GLOSA model is evaluated in comparison to traditional GLOSA and learning-based GLOSA methods in a three-lane intersection with a traffic signal in SUMO. The results demonstrate that the AF-GLOSA model performs best in reducing average stop times, fuel consumption and CO2 emissions.

cs.LG↗

arXiv2023

Spin glass behavior in amorphous Cr2Ge2Te6 phase-change alloy

The layered crystal structure of Cr2Ge2Te6 shows ferromagnetic ordering at the two-dimensional limit, which holds promise for spintronic applications. However, external voltage pulses can trigger amorphization of the material in nanoscale electronic devices, and it is unclear whether the loss of structural ordering leads to a change in magnetic properties. Here, we demonstrate that Cr2Ge2Te6 preserves the spin-polarized nature in the amorphous phase, but undergoes a magnetic transition to a spin glass state below 20 K. Quantum-mechanical computations reveal the microscopic origin of this transition in spin configuration: it is due to strong distortions of the Cr-Te-Cr bonds, connecting chromium-centered octahedra, and to the overall increase in disorder upon amorphization. The tunable magnetic properties of Cr2Ge2Te6 could be exploited for multifunctional, magnetic phase-change devices that switch between crystalline and amorphous states.

cond-mat.mtrl-sci↗

arXiv2023

Phase diagrams and superconductivity of ternary Ca-Al-H compounds under high pressure

The search for high-temperature superconductors in hydrides under high pressure has always been a research hotspot. Hydrogen-based superconductors offer an avenue to achieve the long-sought goal of superconductivity at room temperature. We systematically explore the high-pressure phase diagram, electronic properties, lattice dynamics and superconductivity of the ternary Ca-Al-H system using ab initio methods. We found two stable ternary hydrides at 50 GPa: Cmcm-CaAlH5 and Pnnm-CaAl2H8, which both are semiconductors. At 200 GPa, a new phase of P21/m-CaAlH5, P4/mmm-CaAlH7 and a metastable compound Immm-Ca2AlH12 were found. Furthermore, P4/mmm-CaAlH7 has obvious phonon softening of high frequency vibrations along the Z-A direction, point A and point X, which improves the strength of electron-phonon coupling. Therefore, a superconducting transition temperature Tc of 71 K is generated at 50 GPa. In addition, the thermodynamic metastable Immm-Ca2AlH12 exhibits a superconducting transition temperature of 118 K at 250 GPa. These results are very useful for the experimental searching of new high-Tc superconductors in ternary hydrides.

cond-mat.supr-con↗

arXiv2023

Cyclic Finser metrics on homogeneous spaces

In this paper, we generalize the notion of cyclic metric to homogeneous Finsler geometry. Firstly, we prove that a homogeneous Finsler space $(G/H, F)$ must be symmetric when it satisfies the naturally reductive and cyclic conditions simultaneously. Then we prove that a Finsler cyclic Lie group which is either flat or nilpotent must have an Abelian Lie algebra. Finally, we show how to induce a cyclic $(α,β)$ metric from a cyclic Riemannian metric. Using this method, we construct a Randers cyclic Lie group.

math.DG↗

arXiv2023

Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths

This paper addresses learning end-to-end models for time series data that include a temporal alignment step via dynamic time warping (DTW). Existing approaches to differentiable DTW either differentiate through a fixed warping path or apply a differentiable relaxation to the min operator found in the recursive steps used to solve the DTW problem. We instead propose a DTW layer based around bi-level optimisation and deep declarative networks, which we name DecDTW. By formulating DTW as a continuous, inequality constrained optimisation problem, we can compute gradients for the solution of the optimal alignment (with respect to the underlying time series) using implicit differentiation. An interesting byproduct of this formulation is that DecDTW outputs the optimal warping path between two time series as opposed to a soft approximation, recoverable from Soft-DTW. We show that this property is particularly useful for applications where downstream loss functions are defined on the optimal alignment path itself. This naturally occurs, for instance, when learning to improve the accuracy of predicted alignments against ground truth alignments. We evaluate DecDTW on two such applications, namely the audio-to-score alignment task in music information retrieval and the visual place recognition task in robotics, demonstrating state-of-the-art results in both.

cs.LG↗

arXiv2023

Cognitive Semantic Communication Systems Driven by Knowledge Graph: Principle, Implementation, and Performance Evaluation

Semantic communication is envisioned as a promising technique to break through the Shannon limit. However, semantic inference and semantic error correction have not been well studied. Moreover, error correction methods of existing semantic communication frameworks are inexplicable and inflexible, which limits the achievable performance. In this paper, to tackle this issue, a knowledge graph is exploited to develop semantic communication systems. Two cognitive semantic communication frameworks are proposed for the single-user and multiple-user communication scenarios. Moreover, a simple, general, and interpretable semantic alignment algorithm for semantic information detection is proposed. Furthermore, an effective semantic correction algorithm is proposed by mining the inference rule from the knowledge graph. Additionally, the pre-trained model is fine-tuned to recover semantic information. For the multi-user cognitive semantic communication system, a message recovery algorithm is proposed to distinguish messages of different users by matching the knowledge level between the source and the destination. Extensive simulation results conducted on a public dataset demonstrate that our proposed single-user and multi-user cognitive semantic communication systems are superior to benchmark communication systems in terms of the data compression rate and communication reliability. Finally, we present realistic single-user and multi-user cognitive semantic communication systems results by building a software-defined radio prototype system.

cs.AI↗

arXiv2023

Futuristic Variations and Analysis in Fundus Images Corresponding to Biological Traits

Fundus image captures rear of an eye, and which has been studied for the diseases identification, classification, segmentation, generation, and biological traits association using handcrafted, conventional, and deep learning methods. In biological traits estimation, most of the studies have been carried out for the age prediction and gender classification with convincing results. However, the current study utilizes the cutting-edge deep learning (DL) algorithms to estimate biological traits in terms of age and gender together with associating traits to retinal visuals. For the traits association, our study embeds aging as the label information into the proposed DL model to learn knowledge about the effected regions with aging. Our proposed DL models, named FAG-Net and FGC-Net, correspondingly estimate biological traits (age and gender) and generates fundus images. FAG-Net can generate multiple variants of an input fundus image given a list of ages as conditions. Our study analyzes fundus images and their corresponding association with biological traits, and predicts of possible spreading of ocular disease on fundus images given age as condition to the generative model. Our proposed models outperform the randomly selected state of-the-art DL models.

eess.IV↗

arXiv2023

Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noise

Noisy labels damage the performance of deep networks. For robust learning, a prominent two-stage pipeline alternates between eliminating possible incorrect labels and semi-supervised training. However, discarding part of noisy labels could result in a loss of information, especially when the corruption has a dependency on data, e.g., class-dependent or instance-dependent. Moreover, from the training dynamics of a representative two-stage method DivideMix, we identify the domination of confirmation bias: pseudo-labels fail to correct a considerable amount of noisy labels, and consequently, the errors accumulate. To sufficiently exploit information from noisy labels and mitigate wrong corrections, we propose Robust Label Refurbishment (Robust LR) a new hybrid method that integrates pseudo-labeling and confidence estimation techniques to refurbish noisy labels. We show that our method successfully alleviates the damage of both label noise and confirmation bias. As a result, it achieves state-of-the-art performance across datasets and noise types, namely CIFAR under different levels of synthetic noise and Mini-WebVision and ANIMAL-10N with real-world noise.

cs.LG↗

arXiv2022

Interactive Model with Structural Loss for Language-based Abductive Reasoning

The abductive natural language inference task ($α$NLI) is proposed to infer the most plausible explanation between the cause and the event. In the $α$NLI task, two observations are given, and the most plausible hypothesis is asked to pick out from the candidates. Existing methods model the relation between each candidate hypothesis separately and penalize the inference network uniformly. In this paper, we argue that it is unnecessary to distinguish the reasoning abilities among correct hypotheses; and similarly, all wrong hypotheses contribute the same when explaining the reasons of the observations. Therefore, we propose to group instead of ranking the hypotheses and design a structural loss called ``joint softmax focal loss'' in this paper. Based on the observation that the hypotheses are generally semantically related, we have designed a novel interactive language model aiming at exploiting the rich interaction among competing hypotheses. We name this new model for $α$NLI: Interactive Model with Structural Loss (IMSL). The experimental results show that our IMSL has achieved the highest performance on the RoBERTa-large pretrained model, with ACC and AUC results increased by about 1\% and 5\% respectively.

cs.CL↗

arXiv2022

Special left invariant conic Finsler metrics and homogeneous conic Landsberg Problem in two dimension

In this paper, we study left invariant conic Finsler metrics on the 2-dimensional non-Abelian Lie group $G$ with nowhere vanishing spray vector fields, and classify those satisfying the constant curvature condition, the Landsberg condition or the Berwald condition respectively. We prove that any left invariant conic Landsberg metric on $G$ must be Berwald. This discovery enable us to propose a homogeneous conic Landsberg Conjecture, which guesses that every homogeneous conic Landsberg metric is Berwald, and prove the 2-dimensional case for it.

math.DG↗

arXiv2022

Symmetric space, strongly isotropy irreducibility and equigeodesic properties

A smooth curve on a homogeneous manifold $G/H$ is called a Riemannian equigeo-desic if it is a homogeneous geodesic for any $G$-invariant Riemannian metric. The homogeneous manifold $G/H$ is called Riemannian equigeodesic, if for any $x\in G/H$ and any nonzero $y\in T_x(G/H)$, there exists a Riemannian equigeodesic $c(t)$ with $c(0)=x$ and $\dot{c}(0)=y$. These two notions can be naturally transferred to the Finsler setting, which provides the definitions for Finsler equigeodesic and Finsler equigeodesic space. We prove two classification theorems for Riemannian equigeodesic spaces and Finsler equigeodesic spaces respectively. Firstly, a homogeneous manifold $G/H$ with connected simply connected quasi compact $G$ and connected $H$ is Riemannian equigeodesic if and only if it can be decomposed as a product of Euclidean factors and compact strongly isotropy irreducible factors. Secondly, a homogeneous manifold $G/H$ with a compact semi simple $G$ is Finsler equigeodesic if and only if it can be locally decomposed as a product, in which each factor is $Spin(7)/G_2$, $G_2/SU(3)$ or a symmetric space of compact type. These results imply that symmetric space and strongly isotropy irreducible space of compact type can be interpreted by equigeodesic properties. As an application, we classify the homogeneous manifold $G/H$ with a compact semi simple $G$, such that all $G$-invariant Finsler metrics on $G/H$ are Berwald. It suggests a new project in homogeneous Finsler geometry, to systematically study the homogeneous manifold $G/H$ on which all $G$-invariant Finsler metrics satisfy certain geometric property.

math.DG↗

arXiv2022

Residual Skill Policies: Learning an Adaptable Skill-based Action Space for Reinforcement Learning for Robotics

Skill-based reinforcement learning (RL) has emerged as a promising strategy to leverage prior knowledge for accelerated robot learning. Skills are typically extracted from expert demonstrations and are embedded into a latent space from which they can be sampled as actions by a high-level RL agent. However, this skill space is expansive, and not all skills are relevant for a given robot state, making exploration difficult. Furthermore, the downstream RL agent is limited to learning structurally similar tasks to those used to construct the skill space. We firstly propose accelerating exploration in the skill space using state-conditioned generative models to directly bias the high-level agent towards only sampling skills relevant to a given state based on prior experience. Next, we propose a low-level residual policy for fine-grained skill adaptation enabling downstream RL agents to adapt to unseen task variations. Finally, we validate our approach across four challenging manipulation tasks that differ from those used to build the skill space, demonstrating our ability to learn across task variations while significantly accelerating exploration, outperforming prior works. Code and videos are available on our project website: https://krishanrana.github.io/reskill.

cs.RO↗

arXiv2022

Magnetic island formation and rotation braking induced by low-Z impurity penetration in an EAST plasma

Recent observations of the successive formations of the 4=1; 3=1, and 2=1 magnetic islands as well as the subsequent braking of the 2=1 mode during a low-Z impurity penetration process in EAST experiments are well reproduced in our 3D resistive MHD simulations. The enhanced parallel current perturbation induced by impurity radiation predominately contributes to the tearing mode growth, and the 2=1 island rotation is mainly damped by the impurity accumulation as results of the influence from high n modes.

physics.plasm-ph↗

arXiv2022

Pressure-induced high-temperature superconductivity in ternary Y-Zr-H compounds

Compressed hydrogen-rich compounds have received extensive attention as appealing contenders for superconductors, and further challenges are maintaining the stability and superconductivity of hydrides at lower pressures. In this work, we found several novel hydrides YZrH6, YZrH8 and YZrH12 with excellent superconductivity in the Y-Zr-H ternary system. Interestingly, YZrH6 with an A15-type structure can maintain dynamic stability down to 0.01 GPa and still with a critical temperature (Tc) of 16 K. YZrH8 and YZrH12 have high Tc of 70 K and 183 K at 200 GPa and 160 GPa, respectively. The phonon modes associated with H atoms contribute significantly to the electron-phonon coupling, and the H-driven electronic density of states play an important role in superconductivity. These findings highlight relationship between the H-driven electronic density of states, electron-phonon coupling and the superconductivity in a distinct class of hydrides, opening new avenues for designing and optimizing new hydrogen-rich high temperature superconductors.

cond-mat.supr-con↗

arXiv2022

Girth of the algebraic bipartite graph $D(k,q)$

For integer $k\geq2$ and prime power $q$, the algebraic bipartite graph $D(k,q)$ proposed by Lazebnik and Ustimenko (1995) is meaningful not only in extremal graph theory but also in coding theory and cryptography. This graph is $q$-regular, edge-transitive and of girth at least $k+4$. Its exact girth $g=g(D(k,q))$ was conjectured in 1995 to be $k+5$ for odd $k$ and $q\geq4$. This conjecture was shown to be valid in 2016 when $\frac{k+5}{2}|_p(q-1)$, where $p$ is the characteristic of $\mathbb{F}_q$ and $m|_pn$ means that $m$ divides $p^r n$ for some nonnegative integer $r$. In this paper, for $t\geq 1$ we prove that (a) $g(D(4t+2,q))=g(D(4t+1,q))$; (b) $g(D(4t+3,q))=4t+8$ if $g(D(2t,q))=2t+4$; (c) $g(D(8t,q))=8t+4$ if $g(D(4t-2,q))=4t+2$; (d) $g(D(2^{s+2}(2t-1)-5,q))=2^{s+2}(2t-1)$ if $p\geq 3$, $(2t-1)|_p(q-1)$ and $2^s\|(q-1)$. A simple upper bound for the girth of $D(k,q)$ is proposed in the end of this paper.

math.CO↗