arXiv subjects

Gang Li

Publications and source records attributed to Gang Li.

At least 253 records · Page 14Linked to original sources

arXiv2024

FastGL: A GPU-Efficient Framework for Accelerating Sampling-Based GNN Training at Large Scale

Graph Neural Networks (GNNs) have shown great superiority on non-Euclidean graph data, achieving ground-breaking performance on various graph-related tasks. As a practical solution to train GNN on large graphs with billions of nodes and edges, the sampling-based training is widely adopted by existing training frameworks. However, through an in-depth analysis, we observe that the efficiency of existing sampling-based training frameworks is still limited due to the key bottlenecks lying in all three phases of sampling-based training, i.e., subgraph sample, memory IO, and computation. To this end, we propose FastGL, a GPU-efficient Framework for accelerating sampling-based training of GNN at Large scale by simultaneously optimizing all above three phases, taking into account both GPU characteristics and graph structure. Specifically, by exploiting the inherent overlap within graph structures, FastGL develops the Match-Reorder strategy to reduce the data traffic, which accelerates the memory IO without incurring any GPU memory overhead. Additionally, FastGL leverages a Memory-Aware computation method, harnessing the GPU memory's hierarchical nature to mitigate irregular data access during computation. FastGL further incorporates the Fused-Map approach aimed at diminishing the synchronization overhead during sampling. Extensive experiments demonstrate that FastGL can achieve an average speedup of 11.8x, 2.2x and 1.5x over the state-of-the-art frameworks PyG, DGL, and GNNLab, respectively.Our code is available at https://github.com/a1bc2def6g/fastgl-ae.

cs.LG↗

arXiv2024

Increased resistance to photooxidation in Dion-Jacobson lead halide perovskites -- implication for perovskite device stability

2D metal halide perovskites have enabled significant stability improvements in perovskite devices, particularly in resistance to moisture. However, some 2D perovskites are even more susceptible to photooxidation compared to 3D perovskites. This is particularly true for more commonly investigated Ruddlesden-Popper (RP) perovskites that exhibit increased susceptibility to photoinduced degradation compared to Dion-Jacobson (DJ) perovskites. Comparisons between different RP and DJ perovskites reveal that this phenomenon cannot be explained by commonly proposed differences in superoxide ion generation, interlayer distance and lattice structural rigidity differences. Instead, the resistance to photooxidation of DJ perovskites can be attributed to decreased likelihood of double deprotonation events (compared to single deprotonation events in RP perovskites) required for the loss of organic cations and the perovskite decomposition. Consequently, DJ perovskites are less susceptible to oxidative degradation (both photo- and electrochemically induced), which leads to improved operational stability of solar cells based on these materials.

cond-mat.mtrl-sci↗

arXiv2024

NN-Copula-CD: A Copula-Guided Interpretable Neural Network for Change Detection in Heterogeneous Remote Sensing Images

Change detection (CD) in heterogeneous remote sensing images has been widely used for disaster monitoring and land-use management. In the past decade, the heterogeneous CD problem has significantly benefited from the development of deep neural networks (DNNs). However, the purely data-driven DNNs perform like a black box where the lack of interpretability limits the trustworthiness and controllability of DNNs in most practical CD applications. As a powerful knowledge-driven tool, copula theory performs well in modeling relationships among random variables. To enhance the interpretability of existing neural networks for CD, we propose a knowledge-data-driven heterogeneous CD method based on a copula-guided neural network, named NN-Copula-CD. In our NN-Copula-CD, the mathematical characteristics of copula are employed as the loss functions to supervise a neural network to learn the dependence between bi-temporal heterogeneous superpixel pairs, and then the changed regions are identified via binary classification based on the degrees of dependence of all the superpixel pairs in the bi-temporal images. We conduct in-depth experiments on three datasets with heterogeneous images, where both quantitative and visual results demonstrate the effectiveness of our proposed NN-Copula-CD method.

cs.CV↗

arXiv2024

Evidence for field induced quantum spin liquid behavior in a spin-1/2 honeycomb magnet

One of the most important issues in modern condensed matter physics is the realization of fractionalized excitations, such as the Majorana excitations in the Kitaev quantum spin liquid. To this aim, the 3d-based Kitaev material Na2Co2TeO6 is a promising candidate whose magnetic phase diagram of B // a* contains a field-induced intermediate magnetically disordered phase within 7.5 T < |B| < 10 T. The experimental observations, including the restoration of the crystalline point group symmetry in the angle-dependent torque and the coexisting magnon excitations and spinon-continuum in the inelastic neutron scattering spectrum, provide strong evidence that this disordered phase is a field induced quantum spin liquid with partially polarized spins. Our variational Monte Carlo simulation with the effective K-J1-Γ-Γ'-J3 model reproduces the experimental data and further supports this conclusion.

cond-mat.str-el↗

arXiv2024

Pionic transitions of the spin-2 partner of $X(3872)$ to $χ_{cJ}$

We investigated the pionic transitions between the $X_2$ [spin-2 partner of the $X(3872)$] and $χ_{c1,2}$ using a nonrelativistic effective field theory. The $X_2$ is assumed to be a bound state of the $D^{*}$ and $\bar{D}^*$ mesons and to decay through several kinds of loops, including the bubble, triangle and box loops. Within the present model, the widths for the single-pion decays $X_2\toπ^0χ_{cJ}$ are predicted to be about $3$--$30$ keV. For the dipion decays, the widths are a few keVs. These widths yield a branching fraction of $10^{-3}$--$10^{-2}$. The ratio $R_{\mathrm{c}0}=Γ(X_2\toπ^+π^-χ_{cJ})/Γ(X_2\toπ^0π^0χ_{cJ}) \simeq 1.6$, which is a bit smaller than the expected value of $2$, and $R_{21}=Γ(X_2\toππχ_{c2})/Γ(X_2\toππχ_{c1}) \simeq 0.85$. These ratios are nearly independent of the $X_2$ mass and the coupling constants, which might be a good quantity for the experiments. Moreover, the invariant mass spectra of the $π^0χ_{cJ}$ final state for the dipion processes are presented, showing a cusp structure at the $D {\bar D}^*$ threshold enhanced and narrowed by the nearby triangle singularity.

hep-ph↗

arXiv2024

Leveraging Open Knowledge for Advancing Task Expertise in Large Language Models

The cultivation of expertise for large language models (LLMs) to solve tasks of specific areas often requires special-purpose tuning with calibrated behaviors on the expected stable outputs. To avoid huge cost brought by manual preparation of instruction datasets and training resources up to hundreds of hours, the exploitation of open knowledge including a wealth of low rank adaptation (LoRA) models and instruction datasets serves as a good starting point. However, existing methods on model and data selection focus on the performance of general-purpose capabilities while neglecting the knowledge gap exposed in domain-specific deployment. In the present study, we propose to bridge such gap by introducing few human-annotated samples (i.e., K-shot) for advancing task expertise of LLMs with open knowledge. Specifically, we develop an efficient and scalable pipeline to cost-efficiently produce task experts where K-shot data intervene in selecting the most promising expert candidates and the task-relevant instructions. A mixture-of-expert (MoE) system is built to make the best use of individual-yet-complementary knowledge between multiple experts. We unveil the two keys to the success of a MoE system, 1) the abidance by K-shot, and 2) the insistence on diversity. For the former, we ensure that models that truly possess problem-solving abilities on K-shot are selected rather than those blind guessers. Besides, during data selection, instructions that share task-relevant contexts with K-shot are prioritized. For the latter, we highlight the diversity of constituting experts and that of the fine-tuning instructions throughout the model and data selection process. Extensive experimental results confirm the superiority of our approach over existing methods on utilization of open knowledge across various tasks. Our codes will be available at https://github.com/Yaphabates/Rocket.

cs.CV↗

arXiv2024

Role of Data-driven Regional Growth Model in Shaping Brain Folding Patterns

The surface morphology of the developing mammalian brain is crucial for understanding brain function and dysfunction. Computational modeling offers valuable insights into the underlying mechanisms for early brain folding. Recent findings indicate significant regional variations in brain tissue growth, while the role of these variations in cortical development remains unclear. In this study, we unprecedently explored how regional cortical growth affects brain folding patterns using computational simulation. We first developed growth models for typical cortical regions using machine learning (ML)-assisted symbolic regression, based on longitudinal real surface expansion and cortical thickness data from prenatal and infant brains derived from over 1,000 MRI scans of 735 pediatric subjects with ages ranging from 29 post-menstrual weeks to 24 months. These models were subsequently integrated into computational software to simulate cortical development with anatomically realistic geometric models. We comprehensively quantified the resulting folding patterns using multiple metrics such as mean curvature, sulcal depth, and gyrification index. Our results demonstrate that regional growth models generate complex brain folding patterns that more closely match actual brains structures, both quantitatively and qualitatively, compared to conventional uniform growth models. Growth magnitude plays a dominant role in shaping folding patterns, while growth trajectory has a minor influence. Moreover, multi-region models better capture the intricacies of brain folding than single-region models. Our results underscore the necessity and importance of incorporating regional growth heterogeneity into brain folding simulations, which could enhance early diagnosis and treatment of cortical malformations and neurodevelopmental disorders such as cerebral palsy and autism.

q-bio.NC↗

arXiv2024

Asteroseismic Signatures of Core Magnetism and Rotation in Hundreds of Low-Luminosity Red Giants

Red Giant stars host solar-like oscillations which have mixed character, being sensitive to conditions both in the outer convection zone and deep within the interior. The properties of these modes are sensitive to both core rotation and magnetic fields. While asteroseismic studies of the former have been done on a large scale, studies of the latter are currently limited to tens of stars. We aim to produce the first large catalogue of both magnetic and rotational perturbations. We jointly constrain these parameters by devising an automated method for fitting the power spectra directly. We successfully apply the method to 302 low-luminosity red giants. We find a clear bimodality in core rotation rate. The primary peak is at $δν_{\mathrm{rot}}$ = 0.32 $μ$Hz, and the secondary at $δν_{\mathrm{rot}}$ = 0.47 $μ$Hz. Combining our results with literature values, we find that the percentage of stars rotating much more rapidly than the population average increases with evolutionary state. We measure magnetic splittings of 2$σ$ significance in 23 stars. While the most extreme magnetic splitting values appear in stars with masses > 1.1M$_{\odot}$, implying they formerly hosted a convective core, a small but statistically significant magnetic splitting is measured at lower masses. Asymmetry between the frequencies of a rotationally split multiplet has previously been used to diagnose the presence of a magnetic perturbation. We find that of the stars with a significant detection of magnetic perturbation, 43\% do not show strong asymmetry. We find no strong evidence of correlation between the rotation and magnetic parameters.

astro-ph.SR↗

arXiv2024

Calculable neutrino Dirac mass matrix and one-loop $\bar θ$ in the minimal left-right symmetric model

We revisit the contribution to the strong CP parameter $\bar θ$ from leptonic CP violation at one-loop level in the minimal left-right symmetric model in the case of generalized parity as the left-right symmetry. The Hermitian neutrino Dirac mass matrix $M_D$ can be calculated using the light and heavy neutrino masses and mixings. We propose a parametrization of the right-handed neutrino mixing matrix $V_R$ and construct the heavy neutrino mass that maintains the Hermiticity of $M_D$. We further apply it to evaluate the one-loop $\barθ$, denoted as $\bar θ_{loop}$, as a function of the sterile neutrino masses for explicit examples of $V_R$. By requiring the magnitude of $\bar θ_{loop}\lesssim 10^{-10}$, we derive the upper limits on the sterile neutrino masses, which are within reach of direct searches at the Large Hadron Collider and neutrinoless double beta decay experiments. Furthermore, our parametrization is pertinent for other phenomenological investigations.

hep-ph↗

arXiv2024

GLIMMER: Incorporating Graph and Lexical Features in Unsupervised Multi-Document Summarization

Pre-trained language models are increasingly being used in multi-document summarization tasks. However, these models need large-scale corpora for pre-training and are domain-dependent. Other non-neural unsupervised summarization approaches mostly rely on key sentence extraction, which can lead to information loss. To address these challenges, we propose a lightweight yet effective unsupervised approach called GLIMMER: a Graph and LexIcal features based unsupervised Multi-docuMEnt summaRization approach. It first constructs a sentence graph from the source documents, then automatically identifies semantic clusters by mining low-level features from raw texts, thereby improving intra-cluster correlation and the fluency of generated sentences. Finally, it summarizes clusters into natural sentences. Experiments conducted on Multi-News, Multi-XScience and DUC-2004 demonstrate that our approach outperforms existing unsupervised approaches. Furthermore, it surpasses state-of-the-art pre-trained multi-document summarization models (e.g. PEGASUS and PRIMERA) under zero-shot settings in terms of ROUGE scores. Additionally, human evaluations indicate that summaries generated by GLIMMER achieve high readability and informativeness scores. Our code is available at https://github.com/Oswald1997/GLIMMER.

cs.CL↗

arXiv2024

UICrit: Enhancing Automated Design Evaluation with a UICritique Dataset

Automated UI evaluation can be beneficial for the design process; for example, to compare different UI designs, or conduct automated heuristic evaluation. LLM-based UI evaluation, in particular, holds the promise of generalizability to a wide variety of UI types and evaluation tasks. However, current LLM-based techniques do not yet match the performance of human evaluators. We hypothesize that automatic evaluation can be improved by collecting a targeted UI feedback dataset and then using this dataset to enhance the performance of general-purpose LLMs. We present a targeted dataset of 3,059 design critiques and quality ratings for 983 mobile UIs, collected from seven experienced designers. We carried out an in-depth analysis to characterize the dataset's features. We then applied this dataset to achieve a 55% performance gain in LLM-generated UI feedback via various few-shot and visual prompting techniques. We also discuss future applications of this dataset, including training a reward model for generative UI techniques, and fine-tuning a tool-agnostic multi-modal LLM that automates UI evaluation.

cs.HC↗

arXiv2024

Production of hidden-heavy and double-heavy hadronic molecules at the $Z$ factory of CEPC

With a clean environment and high collision energy, the Circular Electron Positron Collider (CEPC) would be an excellent facility for heavy flavor physics. Using the Monte Carlo event generator Pythia, we simulate the production of the charmed (bottom) hadron pairs in the electron-positron collisions at the $Z$ factory of CEPC, and the inclusive production rates for typical candidates of the hidden/double-charm and hidden/double-bottom $S$-wave hadronic molecules are estimated at an order-of-magnitude level with the final state interactions after the hadron pair production. The predicted cross sections for the hidden-charm meson-meson molecules $X(3872)$ and $Z_c(3900)$ are at $\rm{pb}$ level, which are about two to three orders of magnitude larger than the production cross sections for the double-charm meson-meson molecules $T_{cc}$ and $T_{cc}^{*}$, as the double-charmed ones require the production of two pairs of $c\bar{c}$ from the $Z$ boson decay. The production cross sections for the hidden-charm pentaquark states $P_{c}$ and $P_{cs}$ as meson-baryon molecules are a few to tens of fb, which are about one magnitude larger than those of the possible hidden-charm baryon-antibaryon and double-charm meson-baryon molecules. In the bottom sector, the production cross sections for the $Z_b$ states as $B^{(*)}\bar{B}^{*}$ molecules are about tens to hundreds of fb, indicating $10^6$ - $10^7$ events from a two-year operation of CEPC, and the expected events from the double-bottom molecules are about 2 - 5 orders of magnitude smaller than the $Z_b$ states. Our results shows great prospects of probing heavy exotic hadrons at CEPC.

hep-ph↗

arXiv2024

TIC441725813: A new bright hybrid sdB pulsator with differential core/envelope rotation

We present the detailed analysis of a new hybrid (p- and g-mode) sdB pulsator, TIC441725813 (TYC 4427-1021-1), discovered and monitored by TESS over 670 days. The TESS light curves available for this star were analysed using prewhitening techniques to extract mode frequencies accurately. The pulsation spectrum is then interpreted through methods that include asymptotic period spacing relationships and rotational multiplets identification. We also exploited a high signal-to-noise ratio (S/N), low-resolution spectrum of TIC441725813 using grids of non-local thermodynamic equilibrium (NLTE) model atmospheres to derive its atmospheric parameters. Interestingly, several frequency multiplets interpreted as rotational splittings of deep-probing g-modes indicate a slow rotation period of at least $85.3 \pm 3.6$ day, while splittings of mostly envelope-probing p-modes suggest a significantly shorter rotation period of $17.9 \pm 0.7$ day, which implies the core (mainly the helium mantle with possibly the deeper partially-mixed helium-burning core that it surrounds) rotates at least ~4.7 times slower than the envelope. The radial velocity curves indicate that TIC441725813 is in a close binary system with a low-luminosity companion, possibly a white dwarf. While elusive in the available TESS photometry, a low-frequency signal that would correspond to a period of $\sim 6.7$ h is found, albeit at low S/N. TIC441725813 is a particularly interesting sdB star whose envelope rotates faster than the core. We hypothesise that this might be caused by the effects of tidal interaction with a companion, although in the present case, the presence of such a companion will have to be further investigated. This analysis paves the way toward a more detailed seismic probing of TIC441725813 using optimisation techniques, which will be presented in a second paper.

astro-ph.SR↗

arXiv2024

Nuclear matrix elements of neutrinoless double-beta decay in covariant density functional theory with different mechanisms

Nuclear matrix elements (NMEs) for neutrinoless double-beta ($0νββ$) decay in candidate nuclei play a crucial role in interpreting results from current experiments and in designing future ones. Accurate NME values serve as important nuclear inputs for constraining parameters in new physics, such as neutrino mass and the Wilson coefficients of lepton-number-violating (LNV) operators. In this study, we present a comprehensive calculation of NMEs for $0νββ$ decay in $^{76}$Ge, $^{82}$Se, $^{100}$Mo, $^{130}$Te, and $^{136}$Xe, using nuclear wave functions obtained from multi-reference covariant density functional theory (MR-CDFT). We employ three types of transition potentials at the leading order in chiral effective field theory. Our results, along with recent data, are utilized to constrain the coefficients of LNV operators. The results demonstrate that the combined NMEs based on the Feynman diagrams at the hadronic scale for the nonstandard mechanisms lead to uncertainty by different nuclear models comparable to that for the standard mechanism. The use of NMEs from various nuclear models does not dramatically change the parameter space intervals for the coefficients, although MR-CDFT yields the most stringent constraint. Furthermore, our NMEs can also be used to perform a more comprehensive analysis with multiple isotopes.

nucl-th↗

arXiv2024

Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation

Recent works have demonstrated that using reinforcement learning (RL) with multiple quality rewards can improve the quality of generated images in text-to-image (T2I) generation. However, manually adjusting reward weights poses challenges and may cause over-optimization in certain metrics. To solve this, we propose Parrot, which addresses the issue through multi-objective optimization and introduces an effective multi-reward optimization strategy to approximate Pareto optimal. Utilizing batch-wise Pareto optimal selection, Parrot automatically identifies the optimal trade-off among different rewards. We use the novel multi-reward optimization algorithm to jointly optimize the T2I model and a prompt expansion network, resulting in significant improvement of image quality and also allow to control the trade-off of different rewards using a reward related prompt during inference. Furthermore, we introduce original prompt-centered guidance at inference time, ensuring fidelity to user input after prompt expansion. Extensive experiments and a user study validate the superiority of Parrot over several baselines across various quality criteria, including aesthetics, human preference, text-image alignment, and image sentiment.

cs.CV↗

arXiv2024

Electronic Correlation and Pseudogap-like Behavior of High-Temperature Superconductor La3Ni2O7

High-temperature superconductivity (HTSC) remains one of the most challenging and fascinating mysteries in condensed matter physics. Recently, superconductivity with transition temperature exceeding liquid-nitrogen temperature is discovered in La3Ni2O7 at high pressure, which provides a new platform to explore the unconventional HTSC. In this work, using high-resolution angle-resolved photoemission spectroscopy and ab-initio calculation, we systematically investigate the electronic structures of La3Ni2O7 at ambient pressure. Our experiments are in nice agreement with ab-initio calculations after considering an orbital-dependent band renormalization effect. The strong electron correlation effect pushes a flat band of d_(z^2 ) orbital component below the Fermi level (EF), which is predicted to locate right at EF under high pressure. Moreover, the d_(x^2-y^2 ) band shows a pseudogap-like behavior with suppressed spectral weight and diminished quasiparticle peak near EF. Our findings provide important insights into the electronic structure of La3Ni2O7, which will shed light on the understanding of the unconventional superconductivity in nickelates.

cond-mat.supr-con↗

arXiv2024

Charmless decays of the spin-2 partner of $X(3872)$

The Belle collaboration recently reported a promising candidate for the spin-2 $D^*\bar{D}^*$ partner of the $X(3872)$, called the $X_2$ for short, having a mass of $(4014.3 \pm 4.0 \pm 1.5)~\mathrm{MeV}$ and a width of $(4 \pm 11 \pm 6)~\mathrm{MeV} $. In present work, we assume the $X_2$ as a pure molecule of the $D^*\bar{D}^*$ under three cases, i.e., pure neutral components ($θ= 0$), isospin singlet ($θ= π/4$) and neutral components dominant ($θ= π/6$), where $θ$ is a phase angle describing the proportion of neutral and charged constituents. Using an effective Lagrangian approach, we calculated the partial widths of $X_2\to VV$ and $X_2 \to PP$ ($V$ and $P$ stand for light vector and pseudoscalar mesons, respectively). The predicted decay widths of $X_2 \to VV$ can reach a few hundreds of $\mathrm{keV}$, while the decay widths of $X_2 \to PP$ are about several tens of $\mathrm{keV}$. In addition, the effects from the proportion of neutral and charged constituent on the decay widths of $X_2\to VV$ and $PP$ are also investigated. We hope that the present calculations will be checked experimentally in the future.

hep-ph↗

arXiv2024

Channel Modeling Aided Dataset Generation for AI-Enabled CSI Feedback: Advances, Challenges, and Solutions

The AI-enabled autoencoder has demonstrated great potential in channel state information (CSI) feedback in frequency division duplex (FDD) multiple input multiple output (MIMO) systems. However, this method completely changes the existing feedback strategies, making it impractical to deploy in recent years. To address this issue, this paper proposes a channel modeling aided data augmentation method based on a limited number of field channel data. Specifically, the user equipment (UE) extracts the primary stochastic parameters of the field channel data and transmits them to the base station (BS). The BS then updates the typical TR 38.901 model parameters with the extracted parameters. In this way, the updated channel model is used to generate the dataset. This strategy comprehensively considers the dataset collection, model generalization, model monitoring, and so on. Simulations verify that our proposed strategy can significantly improve performance compared to the benchmarks.

eess.SP↗