arXiv subjects

Feng Zhou

Publications and source records attributed to Feng Zhou.

At least 109 records · Page 6Linked to original sources

arXiv2024

TransFeat-TPP: An Interpretable Deep Covariate Temporal Point Processes

The classical temporal point process (TPP) constructs an intensity function by taking the occurrence times into account. Nevertheless, occurrence time may not be the only relevant factor, other contextual data, termed covariates, may also impact the event evolution. Incorporating such covariates into the model is beneficial, while distinguishing their relevance to the event dynamics is of great practical significance. In this work, we propose a Transformer-based covariate temporal point process (TransFeat-TPP) model to improve the interpretability of deep covariate-TPPs while maintaining powerful expressiveness. TransFeat-TPP can effectively model complex relationships between events and covariates, and provide enhanced interpretability by discerning the importance of various covariates. Experimental results on synthetic and real datasets demonstrate improved prediction accuracy and consistently interpretable feature importance when compared to existing deep covariate-TPPs.

cs.LG↗

arXiv2024

Brownian friction dynamics: fluctuations in sliding distance

We have studied the fluctuation (noise) in the position of sliding blocks under constant driving forces on different substrate surfaces. The experimental data are complemented by simulations using a simple spring-block model where the asperity contact regions are modeled by miniblocks connected to the big block by viscoelastic springs. The miniblocks experience forces that fluctuate randomly with the lateral position, simulating the interaction between asperities on the block and the substrate. The theoretical model provides displacement power spectra that agree well with the experimental results.

cond-mat.soft↗

arXiv2024

Interpretable Transformer Hawkes Processes: Unveiling Complex Interactions in Social Networks

Social networks represent complex ecosystems where the interactions between users or groups play a pivotal role in information dissemination, opinion formation, and social interactions. Effectively harnessing event sequence data within social networks to unearth interactions among users or groups has persistently posed a challenging frontier within the realm of point processes. Current deep point process models face inherent limitations within the context of social networks, constraining both their interpretability and expressive power. These models encounter challenges in capturing interactions among users or groups and often rely on parameterized extrapolation methods when modelling intensity over non-event intervals, limiting their capacity to capture intricate intensity patterns, particularly beyond observed events. To address these challenges, this study proposes modifications to Transformer Hawkes processes (THP), leading to the development of interpretable Transformer Hawkes processes (ITHP). ITHP inherits the strengths of THP while aligning with statistical nonlinear Hawkes processes, thereby enhancing its interpretability and providing valuable insights into interactions between users or groups. Additionally, ITHP enhances the flexibility of the intensity function over non-event intervals, making it better suited to capture complex event propagation patterns in social networks. Experimental results, both on synthetic and real data, demonstrate the effectiveness of ITHP in overcoming the identified limitations. Moreover, they highlight ITHP's applicability in the context of exploring the complex impact of users or groups within social networks.

cs.SI↗

arXiv2024

Deep Equilibrium Models are Almost Equivalent to Not-so-deep Explicit Models for High-dimensional Gaussian Mixtures

Deep equilibrium models (DEQs), as a typical implicit neural network, have demonstrated remarkable success on various tasks. There is, however, a lack of theoretical understanding of the connections and differences between implicit DEQs and explicit neural network models. In this paper, leveraging recent advances in random matrix theory (RMT), we perform an in-depth analysis on the eigenspectra of the conjugate kernel (CK) and neural tangent kernel (NTK) matrices for implicit DEQs, when the input data are drawn from a high-dimensional Gaussian mixture. We prove, in this setting, that the spectral behavior of these Implicit-CKs and NTKs depend on the DEQ activation function and initial weight variances, but only via a system of four nonlinear equations. As a direct consequence of this theoretical result, we demonstrate that a shallow explicit network can be carefully designed to produce the same CK or NTK as a given DEQ. Despite derived here for Gaussian mixture data, empirical results show the proposed theory and design principle also apply to popular real-world datasets.

cs.LG↗

arXiv2024

The LCLS-II Photoinjector Laser Infrastructure

This paper presents a comprehensive technical overview of the Linac Coherent Light Source II (LCLS-II) photoinjector laser system, its first and foremost component. The LCLS-II photoinjector laser system serves as an upgrade to the original LCLS at SLAC National Accelerator Laboratory. This advanced laser system generates high-quality laser beams for LCLS-II, contributing to the instrument's unprecedented brightness, precision, and flexibility. Our discussion extends to the various subsystems that comprise the photoinjector, including the photocathode laser, laser heater, and beam transport systems. Lastly, we draw attention to the ongoing research and development infrastructure underway to enhance the functionality and efficiency of the LCLS-II, and similar X-ray free-electron laser facilities around the world, thereby contributing to the future of laser technology and its applications.

physics.acc-ph↗

arXiv2024

Towards Context-Aware Modeling of Situation Awareness in Conditionally Automated Driving

Maintaining adequate situation awareness (SA) is crucial for the safe operation of conditionally automated vehicles (AVs), which requires drivers to regain control during takeover (TOR) events. This study developed a predictive model for real-time assessment of driver SA using multimodal data (e.g., galvanic skin response, heart rate and eye tracking data, and driver characteristics) collected in a simulated driving environment. Sixty-seven participants experienced automated driving scenarios with TORs, with conditions varying in risk perception and the presence of automation errors. A LightGBM (Light Gradient Boosting Machine) model trained on the top 12 predictors identified by SHAP (SHapley Additive exPlanations) achieved promising performance with RMSE=0.89, MAE=0.71, and Corr=0.78. These findings have implications towards context-aware modeling of SA in conditionally automated driving, paving the way for safer and more seamless driver-AV interactions.

cs.HC↗

arXiv2024

IFDID: Information Filter upon Diversity-Improved Decoding for Diversity-Faithfulness Tradeoff in NLG

Some Natural Language Generation (NLG) tasks require both faithfulness and diversity. The decoding strategy is intensively related to the quality of the generated text. Strategies such as beam search, greedy search, etc., perform with low diversity and high repetition. On the other hand, guided decoding, the solution towards diversity, may generate unfaithful expressions. To this end, this paper presents Information Filter upon Diversity-Improved Decoding (IFDID) to obtain the tradeoff between diversity and faithfulness. IFDID is a two-stage decoding strategy leveraging the proposed Enhance-Filter framework, which achieves the tradeoff by increasing the probabilities of some typical tokens being selected and subsequently filtering them by their information amount. To verify the effectiveness, we compare our method with other baselines on related CommonGEN, RocStories and AdGen benchmarks, which cover Chinese and English datasets. Our numerical experimental results and human evaluation outcomes verify the effectiveness of the proposed approach, as our approach achieves a 1.24 higher ROUGE score describing faithfulness as well as higher diversity represented by 62.5% higher upon Dist-2 than traditional approaches, demonstrating that IFDID is a novel SOTA decoding strategy for the tradeoff between diversity and faithfulness.

cs.CL↗

arXiv2024

Accelerating Convergence in Bayesian Few-Shot Classification

Bayesian few-shot classification has been a focal point in the field of few-shot learning. This paper seamlessly integrates mirror descent-based variational inference into Gaussian process-based few-shot classification, addressing the challenge of non-conjugate inference. By leveraging non-Euclidean geometry, mirror descent achieves accelerated convergence by providing the steepest descent direction along the corresponding manifold. It also exhibits the parameterization invariance property concerning the variational distribution. Experimental results demonstrate competitive classification accuracy, improved uncertainty quantification, and faster convergence compared to baseline models. Additionally, we investigate the impact of hyperparameters and components. Code is publicly available at https://github.com/keanson/MD-BSFC.

cs.LG↗

arXiv2024

An Evidential-enhanced Tri-Branch Consistency Learning Method for Semi-supervised Medical Image Segmentation

Semi-supervised segmentation presents a promising approach for large-scale medical image analysis, effectively reducing annotation burdens while achieving comparable performance. This methodology holds substantial potential for streamlining the segmentation process and enhancing its feasibility within clinical settings for translational investigations. While cross-supervised training, based on distinct co-training sub-networks, has become a prevalent paradigm for this task, addressing critical issues such as predication disagreement and label-noise suppression requires further attention and progress in cross-supervised training. In this paper, we introduce an Evidential Tri-Branch Consistency learning framework (ETC-Net) for semi-supervised medical image segmentation. ETC-Net employs three branches: an evidential conservative branch, an evidential progressive branch, and an evidential fusion branch. The first two branches exhibit complementary characteristics, allowing them to address prediction diversity and enhance training stability. We also integrate uncertainty estimation from the evidential learning into cross-supervised training, mitigating the negative impact of erroneous supervision signals. Additionally, the evidential fusion branch capitalizes on the complementary attributes of the first two branches and leverages an evidence-based Dempster-Shafer fusion strategy, supervised by more reliable and accurate pseudo-labels of unlabeled data. Extensive experiments conducted on LA, Pancreas-CT, and ACDC datasets demonstrate that ETC-Net surpasses other state-of-the-art methods for semi-supervised segmentation. The code will be made available in the near future at https://github.com/Medsemiseg.

cs.CV↗

arXiv2024

Strong interactions between integrated microresonators and alkali atomic vapors: towards single-atom, single-photon operation

Cavity quantum electrodynamics (cQED), the interaction of a two-level system with a high quality factor (Q) cavity, is a foundational building block in different architectures for quantum computation, communication, and metrology. The strong interaction between the atom and the cavity enables single photon operation which is required for quantum gates and sources. Cold atoms, quantum dots, and color centers in crystals are amongst the systems that have shown single photon operations, but they require significant physical infrastructure. Atomic vapors, on the other hand, require limited experimental infrastructure and are hence much easier to deploy outside a laboratory, but they produce an ensemble of moving atoms that results in short interaction times involving multiple atoms, which can hamper quantum operations. A solution to this issue can be found in nanophotonic cavities, where light-matter interaction is enhanced and the volume of operation is small, so that fast single-atom, single-photon operations are enabled. In this work, we study the interaction of an atomically-clad microring resonator (ACMRR) with different-sized ensembles of Rb atoms. We demonstrate strong coupling between an ensemble of ~50 atoms interacting with a high-quality factor (Q > 4 x 10^5) ACMRR, yielding a many-atom cooperativity C ~ 5.5. We continue to observe signatures of atom-photon interaction for a few (< 3) atoms, for which we observe saturation at the level of one intracavity photon. Further development of our platform, which includes integrated thermo-optic heaters to enable cavity tuning and stabilization, should enable the observation of interactions between single photons and single atoms.

quant-ph↗

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

Enhancing Phrase Representation by Information Bottleneck Guided Text Diffusion Process for Keyphrase Extraction

Keyphrase extraction (KPE) is an important task in Natural Language Processing for many scenarios, which aims to extract keyphrases that are present in a given document. Many existing supervised methods treat KPE as sequential labeling, span-level classification, or generative tasks. However, these methods lack the ability to utilize keyphrase information, which may result in biased results. In this study, we propose Diff-KPE, which leverages the supervised Variational Information Bottleneck (VIB) to guide the text diffusion process for generating enhanced keyphrase representations. Diff-KPE first generates the desired keyphrase embeddings conditioned on the entire document and then injects the generated keyphrase embeddings into each phrase representation. A ranking network and VIB are then optimized together with rank loss and classification loss, respectively. This design of Diff-KPE allows us to rank each candidate phrase by utilizing both the information of keyphrases and the document. Experiments show that Diff-KPE outperforms existing KPE methods on a large open domain keyphrase extraction benchmark, OpenKP, and a scientific domain dataset, KP20K.

cs.CL↗

arXiv2024

Bias Mitigation in Fine-tuning Pre-trained Models for Enhanced Fairness and Efficiency

Fine-tuning pre-trained models is a widely employed technique in numerous real-world applications. However, fine-tuning these models on new tasks can lead to unfair outcomes. This is due to the absence of generalization guarantees for fairness properties, regardless of whether the original pre-trained model was developed with fairness considerations. To tackle this issue, we introduce an efficient and robust fine-tuning framework specifically designed to mitigate biases in new tasks. Our empirical analysis shows that the parameters in the pre-trained model that affect predictions for different demographic groups are different, so based on this observation, we employ a transfer learning strategy that neutralizes the importance of these influential weights, determined using Fisher information across demographic groups. Additionally, we integrate this weight importance neutralization strategy with a matrix factorization technique, which provides a low-rank approximation of the weight matrix using fewer parameters, reducing the computational demands. Experiments on multiple pre-trained models and new tasks demonstrate the effectiveness of our method.

cs.LG↗

arXiv2024

Large Anomalous Hall Effect at Room Temperature in a Fermi-Level-Tuned Kagome Antiferromagnet

The recent discoveries of surperisingly large anomalous Hall effect in chiral antiderromagnets have triggered extensive research efforts in various fields, ranging from topological condensed-matter physics to antiferromagnetic spintronics, and energy harvesting technology. However, such AHE-hosting antiferromagnetic materials are rare in nature. Herein, we demonstrate that Mn2.4Ga, a Fermi-level-tuned kagome antiferromagnet, has a large anomalous Hall conductivity of about 150 Ω-1cm-1 at room temperature that surpasses the usual high values (i.e.,20-50 Ω-1cm-1) observed so far in two outstanding kagome antiferromagnets, Mn3Sn and Mn3Ge. The spin triangular structure of Mn2.4Ga guarantees a nonzero Berry curvature while generates only a weak net moment in the kagome plane.Moreover, the anomalous Hall conductivity exhibits a sign reversal with the rotation of a small magnetic field, which can be ascribed to the field-controlled chirality of the spin triangular structure. Our theoretical calculation indicate that the large AHE in Mn2.4Ga originates from a significantly enhanced Berry curvature associated wiht the tuning of the Fermi level close to the Weyl points. These properties, together with the ability to manipulate moment orientations using a moderate external magnetic field, make Mn2.4Ga extremely exciting for future antiferromagnetic spintronics.

cond-mat.mtrl-sci↗

arXiv2024

Besov Regularity of Weak solutions to a Class of Nonlinear Elliptic Equations

In this article, we study a Besov regularity estimate of weak solutions to a class of nonlinear elliptic equations in divergence form. The main purpose is to establish Calderon-Zygmund type estimate in Besov spaces with more general assumptions on coefficients, non-homogeneous term and integrable index. By involving the Sharp maximal function, we establish an oscillation estimate of weak solutions in Orlicz-Sobolev spaces. By deriving a higher integrability estimate of weak solutions, we obtain the desired regularity estimate which expands the Calderon-Zygmund theory for nonlinear elliptic equations.

math.AP↗

arXiv2024

Advancing on-chip Kerr optical parametric oscillation towards coherent applications covering the green gap

Optical parametric oscillation (OPO) in Kerr microresonators can efficiently transfer near-infrared laser light into the visible spectrum. To date, however, chromatic dispersion has mostly limited output wavelengths to >560 nm, and robust access to the whole green light spectrum has not been demonstrated. In fact, wavelengths between 532 nm and 633 nm, commonly referred to as the "green gap", are especially challenging to produce with conventional laser gain. Hence, there is motivation to extend the Kerr OPO wavelength range and develop reliable device designs. Here, we experimentally show how to robustly access the entire green gap with Kerr OPO in silicon nitride microrings pumped near 780 nm. Our microring geometries are optimized for green-gap emission; in particular, we introduce a dispersion engineering technique, based on partially undercutting the microring, which not only expands wavelength access but also proves robust to variations in resonator dimensions, in particular, the microring width. Using just two devices, we generate >100 wavelengths evenly distributed throughout the green gap, as predicted by our dispersion simulations. Moreover, we establish the usefulness of Kerr OPO to coherent applications by demonstrating continuous frequency tuning (>50 GHz) and narrow optical linewidths (<1 MHz). Our work represents an important step in the quest to bring nonlinear nanophotonics and its advantages to the visible spectrum.

physics.optics↗

arXiv2023

Lifting by Image -- Leveraging Image Cues for Accurate 3D Human Pose Estimation

The "lifting from 2D pose" method has been the dominant approach to 3D Human Pose Estimation (3DHPE) due to the powerful visual analysis ability of 2D pose estimators. Widely known, there exists a depth ambiguity problem when estimating solely from 2D pose, where one 2D pose can be mapped to multiple 3D poses. Intuitively, the rich semantic and texture information in images can contribute to a more accurate "lifting" procedure. Yet, existing research encounters two primary challenges. Firstly, the distribution of image data in 3D motion capture datasets is too narrow because of the laboratorial environment, which leads to poor generalization ability of methods trained with image information. Secondly, effective strategies for leveraging image information are lacking. In this paper, we give new insight into the cause of poor generalization problems and the effectiveness of image features. Based on that, we propose an advanced framework. Specifically, the framework consists of two stages. First, we enable the keypoints to query and select the beneficial features from all image patches. To reduce the keypoints attention to inconsequential background features, we design a novel Pose-guided Transformer Layer, which adaptively limits the updates to unimportant image patches. Then, through a designed Adaptive Feature Selection Module, we prune less significant image patches from the feature map. In the second stage, we allow the keypoints to further emphasize the retained critical image features. This progressive learning approach prevents further training on insignificant image features. Experimental results show that our model achieves state-of-the-art performance on both the Human3.6M dataset and the MPI-INF-3DHP dataset.

cs.CV↗

arXiv2023

Mitigating Label Bias in Machine Learning: Fairness through Confident Learning

Discrimination can occur when the underlying unbiased labels are overwritten by an agent with potential bias, resulting in biased datasets that unfairly harm specific groups and cause classifiers to inherit these biases. In this paper, we demonstrate that despite only having access to the biased labels, it is possible to eliminate bias by filtering the fairest instances within the framework of confident learning. In the context of confident learning, low self-confidence usually indicates potential label errors; however, this is not always the case. Instances, particularly those from underrepresented groups, might exhibit low confidence scores for reasons other than labeling errors. To address this limitation, our approach employs truncation of the confidence score and extends the confidence interval of the probabilistic threshold. Additionally, we incorporate with co-teaching paradigm for providing a more robust and reliable selection of fair instances and effectively mitigating the adverse effects of biased labels. Through extensive experimentation and evaluation of various datasets, we demonstrate the efficacy of our approach in promoting fairness and reducing the impact of label bias in machine learning models.

cs.LG↗