arXiv subjects

Chi Xu

Publications and source records attributed to Chi Xu.

At least 37 records · Page 2Linked to original sources

arXiv2024

SALINA: Towards Sustainable Live Sonar Analytics in Wild Ecosystems

Sonar radar captures visual representations of underwater objects and structures using sound wave reflections, making it essential for exploration, mapping, and continuous surveillance in wild ecosystems. Real-time analysis of sonar data is crucial for time-sensitive applications, including environmental anomaly detection and in-season fishery management, where rapid decision-making is needed. However, the lack of both relevant datasets and pre-trained DNN models, coupled with resource limitations in wild environments, hinders the effective deployment and continuous operation of live sonar analytics. We present SALINA, a sustainable live sonar analytics system designed to address these challenges. SALINA enables real-time processing of acoustic sonar data with spatial and temporal adaptations, and features energy-efficient operation through a robust energy management module. Deployed for six months at two inland rivers in British Columbia, Canada, SALINA provided continuous 24/7 underwater monitoring, supporting fishery stewardship and wildlife restoration efforts. Through extensive real-world testing, SALINA demonstrated an up to 9.5% improvement in average precision and a 10.1% increase in tracking metrics. The energy management module successfully handled extreme weather, preventing outages and reducing contingency costs. These results offer valuable insights for long-term deployment of acoustic data systems in the wild.

eess.SP↗

arXiv2024

SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Models

Large Language Models (LLMs) have become increasingly popular, transforming a wide range of applications across various domains. However, the real-world effectiveness of their query cache systems has not been thoroughly investigated. In this work, we for the first time conducted an analysis on real-world human-to-LLM interaction data, identifying key challenges in existing caching solutions for LLM-based chat services. Our findings reveal that current caching methods fail to leverage semantic connections, leading to inefficient cache performance and extra token costs. To address these issues, we propose SCALM, a new cache architecture that emphasizes semantic analysis and identifies significant cache entries and patterns. We also detail the implementations of the corresponding cache storage and eviction strategies. Our evaluations show that SCALM increases cache hit ratios and reduces operational costs for LLMChat services. Compared with other state-of-the-art solutions in GPTCache, SCALM shows, on average, a relative increase of 63% in cache hit ratio and a relative improvement of 77% in tokens savings.

cs.CL↗

arXiv2024

MVMoE: Multi-Task Vehicle Routing Solver with Mixture-of-Experts

Learning to solve vehicle routing problems (VRPs) has garnered much attention. However, most neural solvers are only structured and trained independently on a specific problem, making them less generic and practical. In this paper, we aim to develop a unified neural solver that can cope with a range of VRP variants simultaneously. Specifically, we propose a multi-task vehicle routing solver with mixture-of-experts (MVMoE), which greatly enhances the model capacity without a proportional increase in computation. We further develop a hierarchical gating mechanism for the MVMoE, delivering a good trade-off between empirical performance and computational complexity. Experimentally, our method significantly promotes zero-shot generalization performance on 10 unseen VRP variants, and showcases decent results on the few-shot setting and real-world benchmark instances. We further conduct extensive studies on the effect of MoE configurations in solving VRPs, and observe the superiority of hierarchical gating when facing out-of-distribution data. The source code is available at: https://github.com/RoyalSkye/Routing-MVMoE.

cs.AI↗

arXiv2024

Trustworthy Personalized Bayesian Federated Learning via Posterior Fine-Tune

Performance degradation owing to data heterogeneity and low output interpretability are the most significant challenges faced by federated learning in practical applications. Personalized federated learning diverges from traditional approaches, as it no longer seeks to train a single model, but instead tailors a unique personalized model for each client. However, previous work focused only on personalization from the perspective of neural network parameters and lack of robustness and interpretability. In this work, we establish a novel framework for personalized federated learning, incorporating Bayesian methodology which enhances the algorithm's ability to quantify uncertainty. Furthermore, we introduce normalizing flow to achieve personalization from the parameter posterior perspective and theoretically analyze the impact of normalizing flow on out-of-distribution (OOD) detection for Bayesian neural networks. Finally, we evaluated our approach on heterogeneous datasets, and the experimental results indicate that the new algorithm not only improves accuracy but also outperforms the baseline significantly in OOD detection due to the reliable output of the Bayesian approach.

cs.LG↗

arXiv2023

Disordered hyperuniformity signals functioning and resilience of self-organized vegetation patterns

In harsh environments, organisms may self-organize into spatially patterned systems in various ways. So far, studies of ecosystem spatial self-organization have primarily focused on apparent orders reflected by regular patterns. However, self-organized ecosystems may also have cryptic orders that can be unveiled only through certain quantitative analyses. Here we show that disordered hyperuniformity as a striking class of hidden orders can exist in spatially self-organized vegetation landscapes. By analyzing the high-resolution remotely sensed images across the American drylands, we demonstrate that it is not uncommon to find disordered hyperuniform vegetation states characterized by suppressed density fluctuations at long range. Such long-range hyperuniformity has been documented in a wide range of microscopic systems. Our finding contributes to expanding this domain to accommodate natural landscape ecological systems. We use theoretical modeling to propose that disordered hyperuniform vegetation patterning can arise from three generalized mechanisms prevalent in dryland ecosystems, including (1) critical absorbing states driven by an ecological legacy effect, (2) scale-dependent feedbacks driven by plant-plant facilitation and competition, and (3) density-dependent aggregation driven by plant-sediment feedbacks. Our modeling results also show that disordered hyperuniform patterns can help ecosystems cope with arid conditions with enhanced functioning of soil moisture acquisition. However, this advantage may come at the cost of slower recovery of ecosystem structure upon perturbations. Our work highlights that disordered hyperuniformity as a distinguishable but underexplored ecosystem self-organization state merits systematic studies to better understand its underlying mechanisms, functioning, and resilience.

q-bio.PE↗

arXiv2023

A global product of fine-scale urban building height based on spaceborne lidar

Characterizing urban environments with broad coverages and high precision is more important than ever for achieving the UN's Sustainable Development Goals (SDGs) as half of the world's populations are living in cities. Urban building height as a fundamental 3D urban structural feature has far-reaching applications. However, so far, producing readily available datasets of recent urban building heights with fine spatial resolutions and global coverages remains a challenging task. Here, we provide an up-to-date global product of urban building heights based on a fine grid size of 150 m around 2020 by combining the spaceborne lidar instrument of GEDI and multi-sourced data including remotely sensed images (i.e., Landsat-8, Sentinel-2, and Sentinel-1) and topographic data. Our results revealed that the estimated method of building height samples based on the GEDI data was effective with 0.78 of Pearson's r and 3.67 m of RMSE in comparison to the reference data. The mapping product also demonstrated good performance as indicated by its strong correlation with the reference data (i.e., Pearson's r = 0.71, RMSE = 4.60 m). Compared with the currently existing products, our global urban building height map holds the ability to provide a higher spatial resolution (i.e., 150 m) with a great level of inherent details about the spatial heterogeneity and flexibility of updating using the GEDI samples as inputs. This work will boost future urban studies across many fields including climate, environmental, ecological, and social sciences.

cs.LG↗

arXiv2023

Machine-Learning-Assisted and Real-Time-Feedback-Controlled Growth of InAs/GaAs Quantum Dots

Self-assembled InAs/GaAs quantum dots (QDs) have properties highly valuable for developing various optoelectronic devices such as QD lasers and single photon sources. The applications strongly rely on the density and quality of these dots, which has motivated studies of the growth process control to realize high-quality epi-wafers and devices. Establishing the process parameters in molecular beam epitaxy (MBE) for a specific density of QDs is a multidimensional optimization challenge, usually addressed through time-consuming and iterative trial-and-error. Here, we report a real-time feedback control method to realize the growth of QDs with arbitrary density, which is fully automated and intelligent. We developed a machine learning (ML) model named 3D ResNet 50 trained using reflection high-energy electron diffraction (RHEED) videos as input instead of static images and providing real-time feedback on surface morphologies for process control. As a result, we demonstrated that ML from previous growth could predict the post-growth density of QDs, by successfully tuning the QD densities in near-real time from 1.5E10 cm-2 down to 3.8E8 cm-2 or up to 1.4E11 cm-2. Compared to traditional methods, our approach, with in situ tuning capabilities and excellent reliability, can dramatically expedite the material optimization process and improve the reproducibility of MBE, constituting significant progress for thin film growth techniques. The concepts and methodologies proved feasible in this work are promising to be applied to a variety of material growth processes, which will revolutionize semiconductor manufacturing for optoelectronic and microelectronic industries.

cond-mat.mes-hall↗

arXiv2023

Global Inequality in Cooling from Urban Green Spaces and its Climate Change Adaptation Potential

Heat extremes are projected to severely impact humanity and with increasing geographic disparities. Global South countries are more exposed to heat extremes and have reduced adaptation capacity. One documented source of such adaptation inequality is a lack of resources to cool down indoor temperatures. Less is known about the capacity to ameliorate outdoor heat stress. Here, we assess global inequality in green infrastructure, on which urban residents critically rely to ameliorate lethal heat stress outdoors. We use satellite-derived indicators of land surface temperature and urban green space area to quantify the daytime cooling capacity of urban green spaces in the hottest months across ~500 cities with population size over 1 million per city globally. Our results show a striking contrast with an about two-fold lower cooling capacity in Global South cities compared to the Global North (2.1 degrees Celsius vs. 3.8 degrees Celsius). A similar gap occurs for the cooling adaptation benefits received by an average urban resident (Global South 1.9 degrees Celsius vs. North 3.6 degrees Celsius), i.e., accounting for relative spatial distributions of people and urban green spaces. This cooling adaptation inequality is attributed to the discrepancies in urban green space quantity and quality between Global North and South cities, jointly shaped by natural and socioeconomic factors. Our analyses suggest vast potential for enhancing outdoor cooling adaptation while reducing its global inequality through expanding and optimizing urban green infrastructure.

stat.AP↗

arXiv2023

Self-Supervised Depth Estimation in Laparoscopic Image using 3D Geometric Consistency

Depth estimation is a crucial step for image-guided intervention in robotic surgery and laparoscopic imaging system. Since per-pixel depth ground truth is difficult to acquire for laparoscopic image data, it is rarely possible to apply supervised depth estimation to surgical applications. As an alternative, self-supervised methods have been introduced to train depth estimators using only synchronized stereo image pairs. However, most recent work focused on the left-right consistency in 2D and ignored valuable inherent 3D information on the object in real world coordinates, meaning that the left-right 3D geometric structural consistency is not fully utilized. To overcome this limitation, we present M3Depth, a self-supervised depth estimator to leverage 3D geometric structural information hidden in stereo pairs while keeping monocular inference. The method also removes the influence of border regions unseen in at least one of the stereo images via masking, to enhance the correspondences between left and right images in overlapping areas. Intensive experiments show that our method outperforms previous self-supervised approaches on both a public dataset and a newly acquired dataset by a large margin, indicating a good generalization across different samples and laparoscopes. Code and data are available at https://github.com/br0202/M3Depth.

cs.CV↗

arXiv2023

Consistent optical and electrical determination of carrier concentrations for the accurate modeling of the transport properties of n-type Ge

A consistent methodology is presented to extract carrier concentrations in n-type Ge from measurements of the infrared dielectric function and the Hall effect. In the case of the optical measurements, usually carried out using spectroscopic ellipsometry, the carrier concentration is affected by the doping dependence of the conductivity effective mass, which is computed using a model of the electronic density of states that accounts for non-parabolicity and is fit to electronic structure calculations. Carrier concentrations obtained from Hall measurements require a knowledge of the Hall factor, which is arbitrarily set equal to unit in most practical applications. We have calculated the Hall factor for n-Ge using a model that accounts for scattering with phonons and with ionized impurities. We show that determinations of the carrier concentration n using our computed effective mass and Hall factor virtually eliminates any systematic discrepancy between the two types of measurement. We then use these results to compute majority carrier mobilities from measured resistivity values, to compare with measurements of minority carrier mobilities, and to fit empirical expressions to the doping dependence of the mobilities that can be used to model Ge devices.

cond-mat.mtrl-sci↗

arXiv2023

COMET: Convolutional Dimension Interaction for Collaborative Filtering

Representation learning-based recommendation models play a dominant role among recommendation techniques. However, most of the existing methods assume both historical interactions and embedding dimensions are independent of each other, and thus regrettably ignore the high-order interaction information among historical interactions and embedding dimensions. In this paper, we propose a novel representation learning-based model called COMET (COnvolutional diMEnsion inTeraction), which simultaneously models the high-order interaction patterns among historical interactions and embedding dimensions. To be specific, COMET stacks the embeddings of historical interactions horizontally at first, which results in two "embedding maps". In this way, internal interactions and dimensional interactions can be exploited by convolutional neural networks (CNN) with kernels of different sizes simultaneously. A fully-connected multi-layer perceptron (MLP) is then applied to obtain two interaction vectors. Lastly, the representations of users and items are enriched by the learnt interaction vectors, which can further be used to produce the final prediction. Extensive experiments and ablation studies on various public implicit feedback datasets clearly demonstrate the effectiveness and rationality of our proposed method.

cs.IR↗

arXiv2023

Attention over Self-attention:Intention-aware Re-ranking with Dynamic Transformer Encoders for Recommendation

Re-ranking models refine item recommendation lists generated by the prior global ranking model, which have demonstrated their effectiveness in improving the recommendation quality. However, most existing re-ranking solutions only learn from implicit feedback with a shared prediction model, which regrettably ignore inter-item relationships under diverse user intentions. In this paper, we propose a novel Intention-aware Re-ranking Model with Dynamic Transformer Encoder (RAISE), aiming to perform user-specific prediction for each individual user based on her intentions. Specifically, we first propose to mine latent user intentions from text reviews with an intention discovering module (IDM). By differentiating the importance of review information with a co-attention network, the latent user intention can be explicitly modeled for each user-item pair. We then introduce a dynamic transformer encoder (DTE) to capture user-specific inter-item relationships among item candidates by seamlessly accommodating the learned latent user intentions via IDM. As such, one can not only achieve more personalized recommendations but also obtain corresponding explanations by constructing RAISE upon existing recommendation engines. Empirical study on four public datasets shows the superiority of our proposed RAISE, with up to 13.95%, 9.60%, and 13.03% relative improvements evaluated by Precision@5, MAP@5, and NDCG@5 respectively.

cs.IR↗

arXiv2023

Regularising disparity estimation via multi task learning with structured light reconstruction

3D reconstruction is a useful tool for surgical planning and guidance. However, the lack of available medical data stunts research and development in this field, as supervised deep learning methods for accurate disparity estimation rely heavily on large datasets containing ground truth information. Alternative approaches to supervision have been explored, such as self-supervision, which can reduce or remove entirely the need for ground truth. However, no proposed alternatives have demonstrated performance capabilities close to what would be expected from a supervised setup. This work aims to alleviate this issue. In this paper, we investigate the learning of structured light projections to enhance the development of direct disparity estimation networks. We show for the first time that it is possible to accurately learn the projection of structured light on a scene, implicitly learning disparity. Secondly, we \textcolor{black}{explore the use of a multi task learning (MTL) framework for the joint training of structured light and disparity. We present results which show that MTL with structured light improves disparity training; without increasing the number of model parameters. Our MTL setup outperformed the single task learning (STL) network in every validation test. Notably, in the medical generalisation test, the STL error was 1.4 times worse than that of the best MTL performance. The benefit of using MTL is emphasised when the training data is limited.} A dataset containing stereoscopic images, disparity maps and structured light projections on medical phantoms and ex vivo tissue was created for evaluation together with virtual scenes. This dataset will be made publicly available in the future.

cs.CV↗

arXiv2022

Asymptotic behavior of a three-dimensional haptotactic cross-diffusion system modeling oncolytic virotherapy

This paper deals with an initial-boundary value problem for a doubly haptotactic cross-diffusion system arising from the oncolytic virotherapy \begin{equation*} \left\{ \begin{array}{lll} u_t=Δu-\nabla \cdot(u\nabla v)+μu(1-u)-uz,\\ v_t=-(u+w)v,\\ w_t=Δw-\nabla \cdot(w\nabla v)-w+uz,\\ z_t=D_zΔz-z-uz+βw, \end{array} \right. \end{equation*} in a smoothly bounded domain $Ω\subset \mathbb{R}^3$ with $β>0$,~$μ>0$ and $D_z>0$. Based on a self-map argument, it is shown that under the assumption $β\max \{1,\|u_0\|_{L^{\infty}(Ω)}\}< 1+ (1+\frac1{\min_{x\in Ω}u_0(x)})^{-1}$, this problem possesses a uniquely determined global classical solution $(u,v,w,z)$ for certain type of small data $(u_0,v_0,w_0,z_0)$. Moreover, $(u,v,w,z)$ is globally bounded and exponentially stabilizes towards its spatially homogeneous equilibrium %constant equilibrium $(1,0,0,0)$ as $t\rightarrow \infty$.

math.AP↗

arXiv2022

Direct Modulation of Electrically Pumped Coupled Microring Lasers

We demonstrate how the presence of gain-loss contrast between two coupled identical resonators can be used as a new degree of freedom to enhance the modulation frequency response of laser diodes. An electrically pumped microring laser system with a bending radius of 50 μm is fabricated on an InAlGaAs/InP MQW p-i-n structure. The room temperature continuous wave (CW) laser threshold current of the device is 27 mA. By adjusting the ratio between the injection current levels in the two coupled microrings, our experimental results clearly show a bandwidth improvement by up to 1.63 times the fundamental resonant frequency of the individual device. This matches well with our rate equation simulation model.

physics.optics↗

arXiv2021

Asymptotic behavior of a doubly haptotactic cross-diffusion model for oncolytic virotherapy

This paper considers a model for oncolytic virotherapy given by the doubly haptotactic cross-diffusion system \begin{equation*} \left\{\begin{array}{ll} u_t=D_uΔu-ξ_u\nabla\cdot(u\nabla v)+μ_u u(1-u)-ρuz, v_t=- (α_u u+α_w w)v,\\ w_t=D_wΔw-ξ_w\nabla\cdot(w\nabla v)- w+ρuz,\\ z_t=D_zΔz-δ_z z- ρuz+βw, \end{array}\right. \end{equation*} with positive parameters $D_u,D_w,D_z,ξ_u,ξ_w,δ_z,ρ$, $α_u,α_w,μ_u,β$. When posed under no-flux boundary conditions in a smoothly bounded domain $Ω\subset {\mathbb{R}}^2$, and along with initial conditions involving suitably regular data, the global existence of classical solution to this system was asserted in Tao and Winkler (2020). Based on the suitable quasi-Lyapunov functional, it is shown that when the virus replication rate $β<1$, the global classical solution $(u,v,w,z)$ is uniformly bounded and exponentially stabilizes to the constant equilibrium $(1, 0, 0, 0)$ in the topology $(L^\infty(Ω))^4 $ as $t\rightarrow \infty$.

math.AP↗

arXiv2021

GLIMG: Global and Local Item Graphs for Top-N Recommender Systems

Graph-based recommendation models work well for top-N recommender systems due to their capability to capture the potential relationships between entities. However, most of the existing methods only construct a single global item graph shared by all the users and regrettably ignore the diverse tastes between different user groups. Inspired by the success of local models for recommendation, this paper provides the first attempt to investigate multiple local item graphs along with a global item graph for graph-based recommendation models. We argue that recommendation on global and local graphs outperforms that on a single global graph or multiple local graphs. Specifically, we propose a novel graph-based recommendation model named GLIMG (Global and Local IteM Graphs), which simultaneously captures both the global and local user tastes. By integrating the global and local graphs into an adapted semi-supervised learning model, users' preferences on items are propagated globally and locally. Extensive experimental results on real-world datasets show that our proposed method consistently outperforms the state-of-the art counterparts on the top-N recommendation task.

cs.IR↗

arXiv2021

Asymptotic behavior of a quasilinear Keller--Segel system with signal-suppressed motility

This paper is concerned with the density-suppressed motility model: $u_{t}=Δ(\displaystyle\frac{u^m}{v^α}) +βuf(w), v_{t}=DΔv-v+u, w_{t}=Δw-uf(w)$ in a smoothly bounded convex domain $Ω\subset {\mathbb{R}}^2$, where $m>1$, $α>0, β>0$ and $D>0$ are parameters, the response function $f$ satisfies $f\in C^1([0,\infty)), f(0)=0, f(w)>0$ in $(0,\infty)$. This system describes the density-suppressed motility of Eeshcrichia coli cells in process of spatio-temporal pattern formation via so-called self-trapping mechanisms. Based on the duality argument, it is shown that for suitable large $D$ the problem admits at least one global weak solution $(u,v,w)$ which will asymptotically converge to the spatially uniform equilibrium $(\overline{u_0}+β\overline{w_0},\overline{u_0}+β\overline{w_0},0)$ with $\overline{u_0}=\frac1{|Ω|}\int_Ωu(x,0)dx $ and $\overline{w_0}=\frac1{|Ω|}\int_Ωw(x,0)dx $ in $L^\infty(Ω)$.

math.AP↗