arXiv subjects

Yu Lei

Publications and source records attributed to Yu Lei.

At least 73 records · Page 4Linked to original sources

arXiv2024

CIDGMed: Causal Inference-Driven Medication Recommendation with Enhanced Dual-Granularity Learning

Medication recommendation aims to integrate patients' long-term health records to provide accurate and safe medication combinations for specific health states. Existing methods often fail to deeply explore the true causal relationships between diseases/procedures and medications, resulting in biased recommendations. Additionally, in medication representation learning, the relationships between information at different granularities of medications, coarse-grained (medication itself) and fine-grained (molecular level), are not effectively integrated, leading to biases in representation learning. To address these limitations, we propose the Causal Inference-driven Dual-Granularity Medication Recommendation method (CIDGMed). Our approach leverages causal inference to uncover the relationships between diseases/procedures and medications, thereby enhancing the rationality and interpretability of recommendations. By integrating coarse-grained medication effects with fine-grained molecular structure information, CIDGMed provides a comprehensive representation of medications. Additionally, we employ a bias correction model during the prediction phase to further refine recommendations, ensuring both accuracy and safety. Through extensive experiments, CIDGMed significantly outperforms current state-of-the-art models across multiple metrics, achieving a 2.54% increase in accuracy, a 3.65% reduction in side effects, and a 39.42% improvement in time efficiency. Additionally, we demonstrate the rationale of CIDGMed through a case study.

cs.IR↗

arXiv2024

CausalMed: Causality-Based Personalized Medication Recommendation Centered on Patient health state

Medication recommendation systems are developed to recommend suitable medications tailored to specific patient. Previous researches primarily focus on learning medication representations, which have yielded notable advances. However, these methods are limited to capturing personalized patient representations due to the following primary limitations: (i) unable to capture the differences in the impact of diseases/procedures on patients across various patient health states; (ii) fail to model the direct causal relationships between medications and specific health state of patients, resulting in an inability to determine which specific disease each medication is treating. To address these limitations, we propose CausalMed, a patient health state-centric model capable of enhancing the personalization of patient representations. Specifically, CausalMed first captures the causal relationship between diseases/procedures and medications through causal discovery and evaluates their causal effects. Building upon this, CausalMed focuses on analyzing the health state of patients, capturing the dynamic differences of diseases/procedures in different health states of patients, and transforming diseases/procedures into medications on direct causal relationships. Ultimately, CausalMed integrates information from longitudinal visits to recommend medication combinations. Extensive experiments on real-world datasets show that our method learns more personalized patient representation and outperforms state-of-the-art models in accuracy and safety.

cs.AI↗

arXiv2024

A novel measurement method for SiPM external crosstalk probability at low temperature

Silicon photomultipliers (SiPMs) are being considered as potential replacements for conventional photomultiplier tubes (PMTs). However, a significant disadvantage of SiPMs is crosstalk (CT), wherein photons propagate through other pixels, resulting in secondary avalanches. CT can be categorized into internal crosstalk and external crosstalk based on whether the secondary avalanche occurs within the same SiPM or a different one. Numerous methods exist for quantitatively estimating the percentage of internal crosstalk (iCT). However, external crosstalk (eCT) has not been extensively studied. This article presents a novel measurement method for the probability of emitting an external crosstalk photon during a single pixel avalanche, using a setup involving two identical SiPMs facing each other, and without the need for complex optical designs. The entire apparatus is enclosed within a stainless steel chamber, functioning as a light-tight enclosure, and maintained at liquid nitrogen temperature. The experimental setup incorporates two Sensl J-60035 SiPM chips along with two 0.5-inch Hamamatsu Photonics (HPK) VUV4 S13370-6050CN SiPM arrays. The findings show a linear relationship between the probability of emitting an external crosstalk photon and the SiPM overvoltage for both SiPM samples. Surprisingly, this novel measurement method also rovides measurements of the SiPM photon detection efficiency (PDE) for eCT photons at low temperature.

physics.ins-det↗

arXiv2024

PCLMix: Weakly Supervised Medical Image Segmentation via Pixel-Level Contrastive Learning and Dynamic Mix Augmentation

In weakly supervised medical image segmentation, the absence of structural priors and the discreteness of class feature distribution present a challenge, i.e., how to accurately propagate supervision signals from local to global regions without excessively spreading them to other irrelevant regions? To address this, we propose a novel weakly supervised medical image segmentation framework named PCLMix, comprising dynamic mix augmentation, pixel-level contrastive learning, and consistency regularization strategies. Specifically, PCLMix is built upon a heterogeneous dual-decoder backbone, addressing the absence of structural priors through a strategy of dynamic mix augmentation during training. To handle the discrete distribution of class features, PCLMix incorporates pixel-level contrastive learning based on prediction uncertainty, effectively enhancing the model's ability to differentiate inter-class pixel differences and intra-class consistency. Furthermore, to reinforce segmentation consistency and robustness, PCLMix employs an auxiliary decoder for dual consistency regularization. In the inference phase, the auxiliary decoder will be dropped and no computation complexity is increased. Extensive experiments on the ACDC dataset demonstrate that PCLMix appropriately propagates local supervision signals to the global scale, further narrowing the gap between weakly supervised and fully supervised segmentation methods. Our code is available at https://github.com/Torpedo2648/PCLMix.

cs.CV↗

arXiv2024

Bayesian Diffusion Models for 3D Shape Reconstruction

We present Bayesian Diffusion Models (BDM), a prediction algorithm that performs effective Bayesian inference by tightly coupling the top-down (prior) information with the bottom-up (data-driven) procedure via joint diffusion processes. We show the effectiveness of BDM on the 3D shape reconstruction task. Compared to prototypical deep learning data-driven approaches trained on paired (supervised) data-labels (e.g. image-point clouds) datasets, our BDM brings in rich prior information from standalone labels (e.g. point clouds) to improve the bottom-up 3D reconstruction. As opposed to the standard Bayesian frameworks where explicit prior and likelihood are required for the inference, BDM performs seamless information fusion via coupled diffusion processes with learned gradient computation networks. The specialty of our BDM lies in its capability to engage the active and effective information exchange and fusion of the top-down and bottom-up processes where each itself is a diffusion process. We demonstrate state-of-the-art results on both synthetic and real-world benchmarks for 3D shape reconstruction.

cs.CV↗

arXiv2024

Knowledge-Aware Multi-Intent Contrastive Learning for Multi-Behavior Recommendation

Multi-behavioral recommendation optimizes user experiences by providing users with more accurate choices based on their diverse behaviors, such as view, add to cart, and purchase. Current studies on multi-behavioral recommendation mainly explore the connections and differences between multi-behaviors from an implicit perspective. Specifically, they directly model those relations using black-box neural networks. In fact, users' interactions with items under different behaviors are driven by distinct intents. For instance, when users view products, they tend to pay greater attention to information such as ratings and brands. However, when it comes to the purchasing phase, users become more price-conscious. To tackle this challenge and data sparsity problem in the multi-behavioral recommendation, we propose a novel model: Knowledge-Aware Multi-Intent Contrastive Learning (KAMCL) model. This model uses relationships in the knowledge graph to construct intents, aiming to mine the connections between users' multi-behaviors from the perspective of intents to achieve more accurate recommendations. KAMCL is equipped with two contrastive learning schemes to alleviate the data scarcity problem and further enhance user representations. Extensive experiments on three real datasets demonstrate the superiority of our model.

cs.IR↗

arXiv2024

High-Discriminative Attribute Feature Learning for Generalized Zero-Shot Learning

Zero-shot learning(ZSL) aims to recognize new classes without prior exposure to their samples, relying on semantic knowledge from observed classes. However, current attention-based models may overlook the transferability of visual features and the distinctiveness of attribute localization when learning regional features in images. Additionally, they often overlook shared attributes among different objects. Highly discriminative attribute features are crucial for identifying and distinguishing unseen classes. To address these issues, we propose an innovative approach called High-Discriminative Attribute Feature Learning for Generalized Zero-Shot Learning (HDAFL). HDAFL optimizes visual features by learning attribute features to obtain discriminative visual embeddings. Specifically, HDAFL utilizes multiple convolutional kernels to automatically learn discriminative regions highly correlated with attributes in images, eliminating irrelevant interference in image features. Furthermore, we introduce a Transformer-based attribute discrimination encoder to enhance the discriminative capability among attributes. Simultaneously, the method employs contrastive loss to alleviate dataset biases and enhance the transferability of visual features, facilitating better semantic transfer between seen and unseen classes. Experimental results demonstrate the effectiveness of HDAFL across three widely used datasets.

cs.CV↗

arXiv2024

HDR Imaging for Dynamic Scenes with Events

High dynamic range imaging (HDRI) for real-world dynamic scenes is challenging because moving objects may lead to hybrid degradation of low dynamic range and motion blur. Existing event-based approaches only focus on a separate task, while cascading HDRI and motion deblurring would lead to sub-optimal solutions, and unavailable ground-truth sharp HDR images aggravate the predicament. To address these challenges, we propose an Event-based HDRI framework within a Self-supervised learning paradigm, i.e., Self-EHDRI, which generalizes HDRI performance in real-world dynamic scenarios. Specifically, a self-supervised learning strategy is carried out by learning cross-domain conversions from blurry LDR images to sharp LDR images, which enables sharp HDR images to be accessible in the intermediate process even though ground-truth sharp HDR images are missing. Then, we formulate the event-based HDRI and motion deblurring model and conduct a unified network to recover the intermediate sharp HDR results, where both the high dynamic range and high temporal resolution of events are leveraged simultaneously for compensation. We construct large-scale synthetic and real-world datasets to evaluate the effectiveness of our method. Comprehensive experiments demonstrate that the proposed Self-EHDRI outperforms state-of-the-art approaches by a large margin. The codes, datasets, and results are available at https://lxp-whu.github.io/Self-EHDRI.

cs.CV↗

arXiv2024

Bayesian Exploration of Pre-trained Models for Low-shot Image Classification

Low-shot image classification is a fundamental task in computer vision, and the emergence of large-scale vision-language models such as CLIP has greatly advanced the forefront of research in this field. However, most existing CLIP-based methods lack the flexibility to effectively incorporate other pre-trained models that encompass knowledge distinct from CLIP. To bridge the gap, this work proposes a simple and effective probabilistic model ensemble framework based on Gaussian processes, which have previously demonstrated remarkable efficacy in processing small data. We achieve the integration of prior knowledge by specifying the mean function with CLIP and the kernel function with an ensemble of deep kernels built upon various pre-trained models. By regressing the classification label directly, our framework enables analytical inference, straightforward uncertainty quantification, and principled hyper-parameter tuning. Through extensive experiments on standard benchmarks, we demonstrate that our method consistently outperforms competitive ensemble baselines regarding predictive performance. Additionally, we assess the robustness of our method and the quality of the yielded uncertainty estimates on out-of-distribution datasets. We also illustrate that our method, despite relying on label regression, still enjoys superior model calibration compared to most deterministic baselines.

cs.CV↗

arXiv2024

COPR: Continual Learning Human Preference through Optimal Policy Regularization

The technique of Reinforcement Learning from Human Feedback (RLHF) is a commonly employed method to improve pre-trained Language Models (LM), enhancing their ability to conform to human preferences. Nevertheless, the current RLHF-based LMs necessitate full retraining each time novel queries or feedback are introduced, which becomes a challenging task because human preferences can vary between different domains or tasks. Retraining LMs poses practical difficulties in many real-world situations due to the significant time and computational resources required, along with concerns related to data privacy. To address this limitation, we propose a new method called Continual Optimal Policy Regularization (COPR), in which we compute the distribution of optimal policy bypassing the partition function and then regularize the current policy based on the historically optimal distribution to mitigate Catastrophic Forgetting (CF). COPR involves a single learning phase and doesn't necessitate complex reinforcement learning. Importantly, it shares the capability with RLHF to learn from unlabeled data by maintaining a scoring module, similar to reward model, making it flexible for continually learning without human feedback. Our experimental results show that COPR outperforms strong Continuous Learning (CL) baselines when it comes to consistently aligning with human preferences on incremental tasks and domains.

cs.LG↗

arXiv2024

Multi-Convergence-Angle Ptychography with Simultaneous Strong Contrast and High Resolution

Advances in bioimaging methods and hardware facilities have revolutionised the determination of numerous biological structures at atomic or near-atomic resolution. Among these developments, electron ptychography has recently attracted considerable attention because of its superior resolution, remarkable sensitivity to light elements, and high electron dose efficiency. Here, we introduce an innovative approach called multi-convergence-angle (MCA) ptychography, which can simultaneously enhance both contrast and resolution with continuous information transfer across a wide spectrum of spatial frequency. Our work provides feasibility of future applications of MCA-ptychography in providing high-quality two-dimensional images as input to three-dimensional reconstruction methods, thereby facilitating more accurate determination of biological structures.

physics.optics↗

arXiv2024

Dark matter measurements combining stellar and HI kinematics: 30% $1-σ$ outliers with low dark matter content at $5R_\mathrm{e}$

We construct the Schwarzschild dynamical models for 11 early-type galaxies with the SAURON and Mitchell stellar IFUs out to $2-4 R_\mathrm{e}$, and construct dynamical models with combined stellar and HI kinematics for a subsample of 4 galaxies with HI velocity fields out to $10 R_\mathrm{e}$ obtained from the Westerbork Synthesis Radio Telescope, thus robustly obtaining the dark matter content out to large radii for these galaxies. Adopting a generalised-NFW dark matter profile, we measure an NFW-like density cusp in the dark matter inner slopes for all sample galaxies, with a mean value of $1.00\pm0.04$ (rms scatter $0.15$). The mean dark matter fraction for the sample is $0.2$ within $1 R_\mathrm{e}$, and increases to $0.4$ at $2 R_\mathrm{e}$, and $0.6$ at $5 R_\mathrm{e}$. The dark matter fractions within $1 R_\mathrm{e}$ of these galaxies are systematically lower than the predictions of both the TNG-100 and EAGLE simulations. For the dark matter fractions within $2 R_\mathrm{e}$ and $5 R_\mathrm{e}$, 40% and 70% galaxies are $1-σ$ consistent with either the TNG-100 or the EAGLE predictions, while the remaining 60% and 30% galaxies lie below the $1-σ$ region. Combined with 36 galaxies with dark matter fractions measured out to $5 R_\mathrm{e}$ in the literature, about 10% of these 47 galaxies lie below the $3-σ$ region of the TNG-100 or EAGLE predictions.

astro-ph.GA↗

arXiv2023

Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles

Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs). However, a notable challenge in RLHF is overoptimization, where beyond a certain threshold, the pursuit of higher rewards leads to a decline in human preferences. In this paper, we observe the weakness of KL regularization which is commonly employed in existing RLHF methods to address overoptimization. To mitigate this limitation, we scrutinize the RLHF objective in the offline dataset and propose uncertainty-penalized RLHF (UP-RLHF), which incorporates uncertainty regularization during RL-finetuning. To enhance the uncertainty quantification abilities for reward models, we first propose a diverse low-rank adaptation (LoRA) ensemble by maximizing the nuclear norm of LoRA matrix concatenations. Then we optimize policy models utilizing penalized rewards, determined by both rewards and uncertainties provided by the diverse reward LoRA ensembles. Our experimental results, based on two real human preference datasets, showcase the effectiveness of diverse reward LoRA ensembles in quantifying reward uncertainty. Additionally, uncertainty regularization in UP-RLHF proves to be pivotal in mitigating overoptimization, thereby contributing to the overall performance.

cs.LG↗

arXiv2023

Study on the radon adsorption capability of low-background activated carbon

Radon is a significant background source in rare event detection experiments. Activated Carbon (AC) adsorption is widely used for effective radon removal. The selection of AC considers its adsorption capacity and radioactive background. In this study, using self-developed devices, we screened and identified a new kind of low-background AC from Qingdao Inaf Technology Company that has very high Radon adsorption capacity. By adjusting the average pore size to 2.3 nm, this AC demonstrates a radon adsorption capacity of 2.6 or 4.7 times higher than Saratech or Carboact activated carbon under the same conditions.

hep-ex↗

arXiv2023

Charge equilibration of Laser-accelerated Carbon Ions in Foam Target

The charge equilibration of laser-accelerated carbon ion beams in 2 mg/cm3 foam target was investigated experimentally. The ions were generated through target normal sheath acceleration mechanism in laser-foil interaction scheme. This allows to get the equilibrium charge state in wide energy range near Bragg peak within a single shot. By using foam, the charge equilibration measurement in density regime between gas and solid state was firstly reached out experimentally. It was found that the theoretical predictions with tabulated cross section data for gas target greatly underestimated the charge states. The experimental data are in close agreement with both semi-empirical formula as well as rate equation predictions based on ion-solid interactions. The important role of target density effects that increase the ionization probability and decrease the electron capture probability through frequent multi-collisions in foam are demonstrated. The double electron processes are shown to have little influence on the average charge states. The findings are essential for high energy density physics research where the foams are widely used, and have impacts on a broad range of applications in medical, biological and material fields. The method also provides a new approach to investigate the interaction mechanism of swift heavy ions in matter by taking advantage of the laser-accelerated short-pulse wide-energy range ions.

physics.atom-ph↗

arXiv2023

FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly

While text-3D editing has made significant strides in leveraging score distillation sampling, emerging approaches still fall short in delivering separable, precise and consistent outcomes that are vital to content creation. In response, we introduce FocalDreamer, a framework that merges base shape with editable parts according to text prompts for fine-grained editing within desired regions. Specifically, equipped with geometry union and dual-path rendering, FocalDreamer assembles independent 3D parts into a complete object, tailored for convenient instance reuse and part-wise control. We propose geometric focal loss and style consistency regularization, which encourage focal fusion and congruent overall appearance. Furthermore, FocalDreamer generates high-fidelity geometry and PBR textures which are compatible with widely-used graphics engines. Extensive experiments have highlighted the superior editing capabilities of FocalDreamer in both quantitative and qualitative evaluations.

cs.CV↗

arXiv2023

Proton-Boron Fusion Yield Increased by Orders of Magnitude with Foam Targets

A novel intense beam-driven scheme for high yield of the tri-alpha reaction 11B(p,α)2α was investigated. We used a foam target made of cellulose triacetate (TAC, C_9H_{16}O_8) doped with boron. It was then heated volumetrically by soft X-ray radiation from a laser heated hohlraum and turned into a homogenous, and long living plasma. We employed a picosecond laser pulse to generate a high-intensity energetic proton beam via the well-known Target Normal Sheath Acceleration (TNSA) mechanism. We observed up to 10^{10}/sr α particles per laser shot. This constitutes presently the highest yield value normalized to the laser energy on target. The measured fusion yield per proton exceeds the classical expectation of beam-target reactions by up to four orders of magnitude under high proton intensities. This enhancement is attributed to the strong electric fields and nonequilibrium thermonuclear fusion reactions as a result of the new method. Our approach shows opportunities to pursue ignition of aneutronic fusion.

physics.plasm-ph↗

arXiv2023

Transport of intense ion beams in plasmas: collimation and energy-loss reduction

We compare the transport properties of a well-characterized hydrogen plasma for low and high current ion beams. The energy-loss of low current beams can be well understood, within the framework of current stopping power models. However, for high current proton beams, significant energy-loss reduction and collimation is observed in the experiment. We have developed a new particle-in-cell code, which includes both collective electromagnetic effects and collisional interactions. Our simulations indicate that resistive magnetic fields, induced by the transport of an intense proton beam, act to collimate the proton beam and simultaneously deplete the local plasma density along the beam path. This in turn causes the energy-loss reduction detected in the experiment.

physics.plasm-ph↗