Searcharxiv⌕ Search

arXiv subjects

Qun Chen

Publications and source records attributed to Qun Chen.

At least 19 recordsLinked to original sources
arXiv2026

$\xi$-DPO: Direct Preference Optimization via Ratio Reward Margin

Reference-free preference optimization has emerged as an efficient alternative to reinforcement learning from human feedback, with Simple Preference Optimization(SimPO) demonstrating strong performance by eliminating the explicit reference model through a simple objective. However, the joint tuning of the hyperparameters $\beta$ and $\gamma$ in SimPO remains a central challenge. We argue that this difficulty arises because the margin formulation in SimPO is not easily interpretable across datasets with different reward gap structures. To better understand this issue, we conduct a comprehensive analysis of SimPO and find that $\beta$ implicitly controls sample filtering, while the effect of $\gamma$ depends on the reward gap structure of the dataset. Motivated by these observations, we propose $\xi$-DPO: Direct preference optimization via ratio reward margin. We first reformulate the preference objective through an equivalent transformation, changing the optimization target from maximizing the likelihood of reward gaps to minimizing the distance between reward gaps and optimal margins. Then, we redefine the reward in a ratio form between the chosen and rejected, which effectively cancels the effect of $\beta$ and yields a bounded and interpretable margin. This margin is called the ratio reward margin and is denoted by $\xi$. Unlike the margin $\gamma$ in SimPO, $\xi$ explicitly represents the desired relative separation between chosen and rejected responses and can be determined from the initial reward gap distribution, avoiding repeated trial-and-error tuning. ....

cs.LG↗
arXiv2025

Atomistic Machine Learning with Irreducible Cartesian Natural Tensors

Atomistic machine learning is a powerful tool for accurate and efficient investigation of material behavior at the atomic scale. While attempts have been made to construct models directly within Cartesian space, they face challenges in providing a systematic framework based on irreducible representations - a core feature of widely used spherical models. Here we propose Cartesian Natural Tensor Networks to overcome these limitations and thus offer a general, symmetry-preserving framework for atomistic machine learning. We present a theory of irreducible representations using Cartesian natural tensors, comprising their construction, their products, and a systematic scheme to decompose and reconstruct high-rank physical tensors. Leveraging this machinery, we develop equivariant machine learning interatomic potentials for materials and molecular systems with performance on par with leading spherical models. It further captures accurate structure-property relationships for tensorial quantities ranging from low-rank dipole moments to high-rank tensors with complex symmetries, such as the elastic constant tensor.

cond-mat.mtrl-sci↗
arXiv2025

Adaptive Deep Learning for Breast Cancer Subtype Prediction Via Misprediction Risk Analysis

Breast cancer remains a leading cause of cancer-related mortality worldwide. Early detection is critical, yet manual histopathology analysis is complex and subject to inter-observer variability. While deep neural network-based diagnostic systems have advanced binary tasks, they struggle with multiclass subtype prediction due to inter-class similarity, class imbalance, and domain shifts, resulting in frequent mispredictions. This study proposes MultiRisk, an adaptive learning framework that quantifies and mitigates misprediction risk in breast cancer subtype prediction from histopathology images. MultiRisk employs a multiclass misprediction risk analysis model that ranks misprediction likelihood using interpretable features derived from heterogeneous DNN representations, with a dedicated risk model trained to capture multiclass risk patterns. Building on this, we introduce a risk-based adaptive learning strategy that fine-tunes prediction models based on dataset-specific characteristics, effectively reducing misprediction risk and improving adaptability to diverse workloads. The framework is evaluated on multiple histopathological image datasets, achieving AUROCs of 78.1%, 75.6%, and 76.3% for risk analysis. Risk-based adaptive training further improves F1-scores to 61.15%, 65.98%, and 80.53%, demonstrating effectiveness across resolutions and domain shifts. By combining misprediction risk analysis with adaptive fine-tuning, MultiRisk improves predictive accuracy, mitigates errors under limited labeled data, and generalizes across domains, cancer types, and model architectures, supporting reliable clinical decision-making. Code: https://github.com/SheerazNWPU/MultiRisk

cs.CV↗
arXiv2025

Deep Clustering via Gradual Community Detection

Deep clustering is an essential task in modern artificial intelligence, aiming to partition a set of data samples into a given number of homogeneous groups (i.e., clusters). Recent studies have proposed increasingly advanced deep neural networks and training strategies for deep clustering, effectively improving performance. However, deep clustering generally remains challenging due to the inadequacy of supervision signals. Building upon the existing representation learning backbones, this paper proposes a novel clustering strategy of gradual community detection. It initializes clustering by partitioning samples into many pseudo-communities and then gradually expands clusters by community merging. Compared with the existing clustering strategies, community detection factors in the new perspective of cluster network analysis in the clustering process. The new perspective can effectively leverage global structural characteristics to enhance cluster pseudo-label purity, which is critical to the performance of self-supervision. We have implemented the proposed approach based on the popular backbones and evaluated its efficacy on benchmark image datasets. Our extensive experiments have shown that the proposed clustering strategy can effectively improve the SOTA performance. Our ablation study also demonstrates that the new network perspective can effectively improve community pseudo-label purity, resulting in improved self-supervision.

cs.LG↗
arXiv2024

Liouville theorems for ancient solutions to the V-harmonic map heat flows II

When the domain is a complete noncompact Riemannian manifold with nonnegative Bakry--Emery Ricci curvature and the target is a complete Riemannian manifold with sectional curvature bounded above by a positive constant, by carrying out refined gradient estimates, we obtain a better Liouville theorem for ancient solutions to the V-harmonic map heat flows. Furthermore, we can also derive a Liouville theorem for quasi-harmonic maps under an exponential growth condition.

math.DG↗
arXiv2024

Structure-Guided MR-to-CT Synthesis with Spatial and Semantic Alignments for Attenuation Correction of Whole-Body PET/MR Imaging

Deep-learning-based MR-to-CT synthesis can estimate the electron density of tissues, thereby facilitating PET attenuation correction in whole-body PET/MR imaging. However, whole-body MR-to-CT synthesis faces several challenges including the issue of spatial misalignment and the complexity of intensity mapping, primarily due to the variety of tissues and organs throughout the whole body. Here we propose a novel whole-body MR-to-CT synthesis framework, which consists of three novel modules to tackle these challenges: (1) Structure-Guided Synthesis module leverages structure-guided attention gates to enhance synthetic image quality by diminishing unnecessary contours of soft tissues; (2) Spatial Alignment module yields precise registration between paired MR and CT images by taking into account the impacts of tissue volumes and respiratory movements, thus providing well-aligned ground-truth CT images during training; (3) Semantic Alignment module utilizes contrastive learning to constrain organ-related semantic information, thereby ensuring the semantic authenticity of synthetic CT images.We conduct extensive experiments to demonstrate that the proposed whole-body MR-to-CT framework can produce visually plausible and semantically realistic CT images, and validate its utility in PET attenuation correction.

eess.IV↗
arXiv2024

Vector Approximate Survey Propagation

Approximate Message Passing (AMP), originally designed to solve high-dimensional linear inverse problems, has found broad applications in signal processing and statistical inference. Among its key variants, Vector Approximate Message Passing (VAMP) and Generalized Approximate Survey Propagation (GASP) have demonstrated effectiveness even in scenarios where the assumed generative models differ from the true models. However, the maximum a posteriori (MAP) versions of VAMP and GASP have limitations: VAMP is restricted to differentiable priors and likelihoods, while GASP requires the measurement matrix to have independent identically distributed (i.i.d.) elements. To overcome these limitations, this paper introduces a new algorithm, Vector Approximate Survey Propagation (VASP). VASP utilizes survey propagation to handle non-differentiable priors and likelihoods, along with employs vector-form messages to account for correlations in the measurement matrix. Simulations reveal that VASP significantly surpasses VAMP and GASP in estimation accuracy, particularly when the assumed prior is discrete-supported and the measurement matrix is non-i.i.d.. Additionally, the state evolution (SE) of VASP, derived heuristically, accurately reflects the per-iteration mean squared error (MSE). A comparison between the SE and the free energy computed by Takahashi and Kabashima under the one-step replica symmetry breaking (1RSB) ansatz shows that the SE's fixed-point equations align with the free energy's saddle point equations. This suggests that VASP efficiently implements the postulated MAP estimator (which is NP-hard in the worst case) with cubic computational complexity, assuming the 1RSB ansatz is valid.

cs.IT↗
arXiv2024

K-step Vector Approximate Survey Propagation

Approximate Message Passing (AMP), originally developed to address high-dimensional linear inverse problems, has found widespread applications in signal processing and statistical inference. Among its notable variants, Vector Approximate Message Passing (VAMP), Generalized Approximate Survey Propagation (GASP), and Vector Approximate Survey Propagation (VASP) have demonstrated effectiveness even when the assumed generative models differ from the true models. However, many fundamental questions regarding model mismatch remain unanswered. For instance, it is still unclear what level of model mismatch is required for the postulated posterior estimate (PPE) to exhibit a replica symmetry breaking (RSB) structure in the extremum conditions of its free energy, and what order of RSB is necessary. In this paper, we introduce a novel approximate message passing algorithm that incorporates K-step RSB (KRSB) and naturally reduces to VAMP and VASP with specific parameter selections. We refer to this as the K-step VASP (KVASP) algorithm. Simulations show that KVASP significantly outperforms VAMP and GASP in estimation accuracy, particularly when the assumed prior has discrete support and the measurement matrix is non-i.i.d.. Additionally, the state evolution (SE) of KVASP, derived heuristically, accurately tracks the per-iteration mean squared error (MSE). A comparison between the SE and the free energy under the KRSB ansatz reveals that the fixed-point equations of SE align with the saddle-point equations of the free energy. This suggests that, once the KRSB ansatz holds and the SE fixed point is reached, KVASP can accurately compute the PPE in the large system limit (LSL).

cs.IT↗
arXiv2024

Supervised Gradual Machine Learning for Aspect Category Detection

Aspect Category Detection (ACD) aims to identify implicit and explicit aspects in a given review sentence. The state-of-the-art approaches for ACD use Deep Neural Networks (DNNs) to address the problem as a multi-label classification task. However, learning category-specific representations heavily rely on the amount of labeled examples, which may not readily available in real-world scenarios. In this paper, we propose a novel approach to tackle the ACD task by combining DNNs with Gradual Machine Learning (GML) in a supervised setting. we aim to leverage the strength of DNN in semantic relation modeling, which can facilitate effective knowledge transfer between labeled and unlabeled instances during the gradual inference of GML. To achieve this, we first analyze the learned latent space of the DNN to model the relations, i.e., similar or opposite, between instances. We then represent these relations as binary features in a factor graph to efficiently convey knowledge. Finally, we conduct a comparative study of our proposed solution on real benchmark datasets and demonstrate that the GML approach, in collaboration with DNNs for feature extraction, consistently outperforms pure DNN solutions.

cs.CL↗
arXiv2023

Few-shot Image Classification based on Gradual Machine Learning

Few-shot image classification aims to accurately classify unlabeled images using only a few labeled samples. The state-of-the-art solutions are built by deep learning, which focuses on designing increasingly complex deep backbones. Unfortunately, the task remains very challenging due to the difficulty of transferring the knowledge learned in training classes to new ones. In this paper, we propose a novel approach based on the non-i.i.d paradigm of gradual machine learning (GML). It begins with only a few labeled observations, and then gradually labels target images in the increasing order of hardness by iterative factor inference in a factor graph. Specifically, our proposed solution extracts indicative feature representations by deep backbones, and then constructs both unary and binary factors based on the extracted features to facilitate gradual learning. The unary factors are constructed based on class center distance in an embedding space, while the binary factors are constructed based on k-nearest neighborhood. We have empirically validated the performance of the proposed approach on benchmark datasets by a comparative study. Our extensive experiments demonstrate that the proposed approach can improve the SOTA performance by 1-5% in terms of accuracy. More notably, it is more robust than the existing deep models in that its performance can consistently improve as the size of query set increases while the performance of deep models remains essentially flat or even becomes worse.

cs.CV↗
arXiv2022

Adaptive Deep Learning for Entity Resolution by Risk Analysis

The state-of-the-art performance on entity resolution (ER) has been achieved by deep learning. However, deep models are usually trained on large quantities of accurately labeled training data, and can not be easily tuned towards a target workload. Unfortunately, in real scenarios, there may not be sufficient labeled training data, and even worse, their distribution is usually more or less different from the target workload even when they come from the same domain. To alleviate the said limitations, this paper proposes a novel risk-based approach to tune a deep model towards a target workload by its particular characteristics. Built on the recent advances on risk analysis for ER, the proposed approach first trains a deep model on labeled training data, and then fine-tunes it by minimizing its estimated misprediction risk on unlabeled target data. Our theoretical analysis shows that risk-based adaptive training can correct the label status of a mispredicted instance with a fairly good chance. We have also empirically validated the efficacy of the proposed approach on real benchmark data by a comparative study. Our extensive experiments show that it can considerably improve the performance of deep models. Furthermore, in the scenario of distribution misalignment, it can similarly outperform the state-of-the-art alternative of transfer learning by considerable margins. Using ER as a test case, we demonstrate that risk-based adaptive training is a promising approach potentially applicable to various challenging classification tasks.

cs.LG↗
arXiv2022

Fundamental limit to the rectification of near-field heat flow: The potential of intrinsic semiconductor films

We derive the fundamental limit to near-field radiative thermal rectification mediated by an intrinsic semiconductor film within the framework of fluctuational electrodynamics. By leveraging the electromagnetic local density of states, we identify ε"_H/ε"_L as an upper bound on the rectification magnitude, where ε"_H and ε"_L are respectively the imaginary parts of the film permittivity at high and low temperatures. This bound is tight and can be approached regardless of whether the film is suspended or supported. For intrinsic silicon the limit can in principle exceed 10^9. Our work highlights the possibility of controlling heat flow as effectively as electric current, and offers guidelines to potentially achieve this goal.

cond-mat.mes-hall↗
arXiv2021

Giant radiative thermal rectification using an intrinsic semiconductor film

Rectification of heat flow via a thermal diode is not only of fundamental interest, but can also enable a range of novel applications in thermal management and energy conversion. However, despite decades of extensive research, large rectification ratios of practical importance have yet to be demonstrated. Here, we theoretically achieve giant rectification ratios (3 to almost 5 orders of magnitude) by leveraging near-field radiative thermal transport between two parallel planes. Guided by a rational design approach centering on the electromagnetic local density of states (LDOS), we employ a thin film of an intrinsic semiconductor-such as silicon-as one terminal of our radiative thermal diodes, which provides the necessary nonlinearity and a substantial LDOS contrast as the temperature bias is flipped. For the other terminal, we explore two kinds of materials which either serve as a narrowband or a broadband filter, both capable of converting the large LDOS contrast into giant thermal rectification. We further consider representative multilayer configurations in order to block backside radiation and improve mechanical stability. All the diodes perform well over a wide range of film thicknesses, gap sizes, and temperatures. Our work offers an opportunity for realizing thermal diodes with unprecedented rectification ratios.

cond-mat.mes-hall↗
arXiv2021

Radiative thermal diode via hyperbolic metamaterials

Hyperbolic metamaterials (HMMs) support propagating waves with arbitrarily large wavevectors over broad spectral ranges, and are uniquely valuable for engineering radiative thermal transport in the near field. Here, by employing a rational design approach based on the electromagnetic local density of states, we demonstrate the ability of HMMs to substantially rectify radiative heat flow. Our idea is to establish a forward-biased scenario where the two HMM-based terminals of a thermal diode feature overlapped hyperbolic bands which result in a large heat current, and suppress the reverse heat flow by creating spectrally mismatched density of states as the temperature bias is flipped. As an example, we present a few high-performance thermal diodes by pairing HMMs made of polar dielectrics and metal-to-insulator transition (MIT) materials in the form of periodic nanowire arrays, and considering three representative kinds of substrates. Upon optimization, we theoretically achieve a rectification ratio of 324 at a 100 nm gap, which remains greater than 148 for larger gap sizes up to 1 um over a wide temperature range. The maximum rectification represents an almost 1000-fold increase compared to a bulk diode using the same materials, and is twice that of state-of-the-art designs. Our work highlights the potential of HMMs for rectifying radiative heat flow, and may find applications in advanced thermal management and energy conversion systems.

physics.optics↗
arXiv2021

Thin-film radiative thermal diode with large rectification

We propose a mechanism to substantially rectify radiative heat flow by matching thin films of metal-to-insulator transition materials and polar dielectrics in the electromagnetic near field. By leveraging the distinct scaling behaviors of the local density of states with film thickness for metals and insulators, we theoretically achieve rectification ratios over 140-a 10-fold improvement over the state of the art-with nanofilms of vanadium dioxide and cubic boron nitride in the parallel-plane geometry at experimentally feasible gap sizes (~100 nm). Our rational design offers relative ease of fabrication, flexible choice of materials, and robustness against deviations from optimal film thicknesses. We expect this work to facilitate the application of thermal diodes in solid-state thermal circuits and energy conversion devices.

physics.app-ph↗
arXiv2020

Active Deep Learning on Entity Resolution by Risk Sampling

While the state-of-the-art performance on entity resolution (ER) has been achieved by deep learning, its effectiveness depends on large quantities of accurately labeled training data. To alleviate the data labeling burden, Active Learning (AL) presents itself as a feasible solution that focuses on data deemed useful for model training. Building upon the recent advances in risk analysis for ER, which can provide a more refined estimate on label misprediction risk than the simpler classifier outputs, we propose a novel AL approach of risk sampling for ER. Risk sampling leverages misprediction risk estimation for active instance selection. Based on the core-set characterization for AL, we theoretically derive an optimization model which aims to minimize core-set loss with non-uniform Lipschitz continuity. Since the defined weighted K-medoids problem is NP-hard, we then present an efficient heuristic algorithm. Finally, we empirically verify the efficacy of the proposed approach on real data by a comparative study. Our extensive experiments have shown that it outperforms the existing alternatives by considerable margins. Using ER as a test case, we demonstrate that risk sampling is a promising approach potentially applicable to other challenging classification tasks.

cs.LG↗
arXiv2020

Carleman estimates for a stochastic degenerate parabolic equation and applications to null controllability and an inverse random source problem

In this paper, we establish two Carleman estimates for a stochastic degenerate parabolic equation. The first one is for the backward stochastic degenerate parabolic equation with singular weight function. Combining this Carleman estimate and an approximate argument, we prove the null controllability of the forward stochastic degenerate parabolic equation with the gradient term. The second one is for the forward stochastic degenerate parabolic equation with regular weighted function, based on which we obtain the Lipschitz stability for an inverse problem of determining a random source depending only on time in the forward stochastic degenerate parabolic equation.

math.OC↗