Qing Zhou

Ping Wei, Sheng Li, Xinpeng Zhang et al.

Steganography usually modifies cover media to embed secret data. A new steganographic approach called generative steganography (GS) has emerged recently, in which stego images (images containing secret data) are generated from secret data directly without cover media. However, existing GS schemes are often criticized for their poor performances. In this paper, we propose an advanced generative steganography network (GSN) that can generate realistic stego images without using cover images. We firstly introduce the mutual information mechanism in GS, which helps to achieve high secret extraction accuracy. Our model contains four sub-networks, i.e., an image generator ($G$), a discriminator ($D$), a steganalyzer ($S$), and a data extractor ($E$). $D$ and $S$ act as two adversarial discriminators to ensure the visual quality and security of generated stego images. $E$ is to extract the hidden secret from generated stego images. The generator $G$ is flexibly constructed to synthesize either cover or stego images with different inputs. It facilitates covert communication by concealing the function of generating stego images in a normal generator. A module named secret block is designed to hide secret data in the feature maps during image generation, with which high hiding capacity and image fidelity are achieved. In addition, a novel hierarchical gradient decay (HGD) skill is developed to resist steganalysis detection. Experiments demonstrate the superiority of our work over existing methods.

Yaoteng Zhang, Qing Zhou, Junyu Gao et al.

Remote sensing imagery typically arrives in the form of continuous data streams. Traditional detectors often forget previously learned categories when learning new ones; therefore, research on Remote Sensing Incremental Object Detection (RS-IOD) is of great significance. However, existing methods largely overlook the intra-class scale variations prevalent in remote sensing scenes, which undermines the effectiveness of knowledge transfer and old knowledge preservation. Moreover, RS-IOD also suffers from missing annotations, which cause the model to misclassify old-class instances as background. To address these challenges, we propose a novel framework, STAR-IOD. First, we introduce a Subspace-decoupled Topology Distillation (STD) module to transfer structural knowledge, explicitly aligning inter-class topological relationships and mitigating intra-class representation discrepancies induced by scale shifts. Furthermore, we introduce the Clustering-driven Pseudo-label Generator (CPG), a plug-and-play module that leverages K-Means clustering to dynamically identify class-specific thresholds, thereby guaranteeing an accurate distinction between true positive targets and background noise and alleviating the issue of missing annotations for old classes. We also constructed two Remote Sensing Incremental Object Detection datasets, DIOR-IOD and DOTA-IOD to facilitate research on RS-IOD. Extensive experiments demonstrate that our method outperforms state-of-the-art approaches by 1.7% and 2.1% mAP on DIOR-IOD and DOTA-IOD, respectively, effectively alleviating catastrophic forgetting while preserving strong detection performance on both base and novel classes. The code and dataset are released at: https://github.com/zyt95579/STAR-IOD.

Tao Yang, Qing Zhou, Yanliang Li et al.

Reasoning segmentation increasingly employs reinforcement learning to generate explanatory reasoning chains that guide Multimodal Large Language Models. While these geometric rewards are primarily confined to guiding the final localization, they are incapable of discriminating whether the reasoning process remains anchored on the referred region or strays into irrelevant context. Lacking this discriminative guidance, the model's reasoning often devolves into unfocused and verbose chains that ultimately fail to disambiguate and perceive the target in complex scenes. This suggests a need to complement the RL objective with Discriminative Perception, an ability to actively distinguish a target from its context. To realize this, we propose DPAD to compel the model to generate a descriptive caption of the referred object, which is then used to explicitly discriminate by contrasting the caption's semantic relevance to the referred object against the wider context. By optimizing for this discriminative capability, the model is forced to focus on the unique attributes of the target, leading to a more converged and efficient reasoning chain. The descriptive caption also serves as an interpretability rationale that aligns with the segmentation. Experiments on the benchmarks confirm the validity of our approach, delivering substantial performance gains, with the cIoU on ReasonSeg increasing by 3.09% and the reasoning chain length decreasing by approximately 42%. Code is available at https://github.com/mrazhou/DPAD

Arash A. Amini, Bryon Aragam, Qing Zhou

We study the problem of learning multivariate dependencies in nonparametric and high-dimensional settings. This includes but is not limited to graphical models. Our approach effectively combines several features that are missing from previous work on this problem: We show how the entire dependence structure can be learned nonparametrically while simultaneously evading the curse of dimensionality and relaxing common assumptions such as faithfulness. To this end, we introduce and study the neighbourhood lattice decomposition of a distribution, which is a compact, non-graphical representation of conditional independence (CI) that is valid in the absence of a faithful graphical representation. We show that the neighbourhood lattice decomposition exists in any graphical model and can be computed efficiently, nonparametrically, and consistently in high-dimensions without paying the usual curse of dimensionality. This gives a way to learn all of the independence relations implied by any graphical model, without requiring a priori knowledge of the graph or even the graph type. As a special case, our results provide a general solution to the problem of nonparametric estimation of high-dimensional CI structures over any graphical model.

Qing Zhou, Junyu Gao, Qi Wang

The rapid growth of dataset scales has been a key driver in advancing deep learning research. However, as dataset scale increases, the training process becomes increasingly inefficient due to the presence of low-value samples, including excessive redundant samples, overly challenging samples, and inefficient easy samples that contribute little to model improvement.To address this challenge, we propose Scale Efficient Training (SeTa) for large datasets, a dynamic sample pruning approach that losslessly reduces training time. To remove low-value samples, SeTa first performs random pruning to eliminate redundant samples, then clusters the remaining samples according to their learning difficulty measured by loss. Building upon this clustering, a sliding window strategy is employed to progressively remove both overly challenging and inefficient easy clusters following an easy-to-hard curriculum.We conduct extensive experiments on large-scale synthetic datasets, including ToCa, SS1M, and ST+MJ, each containing over 3 million samples.SeTa reduces training costs by up to 50\% while maintaining or improving performance, with minimal degradation even at 70\% cost reduction. Furthermore, experiments on various scale real datasets across various backbones (CNNs, Transformers, and Mambas) and diverse tasks (instruction tuning, multi-view stereo, geo-localization, composed image retrieval, referring image segmentation) demonstrate the powerful effectiveness and universality of our approach. Code is available at https://github.com/mrazhou/SeTa.

Qing Zhou, Tao Yang, Junyu Gao et al.

Remote Sensing Image Captioning (RSIC) is a cross-modal field bridging vision and language, aimed at automatically generating natural language descriptions of features and scenes in remote sensing imagery. Despite significant advances in developing sophisticated methods and large-scale datasets for training vision-language models (VLMs), two critical challenges persist: the scarcity of non-English descriptive datasets and the lack of multilingual capability evaluation for models. These limitations fundamentally impede the progress and practical deployment of RSIC, particularly in the era of large VLMs. To address these challenges, this paper presents several significant contributions to the field. First, we introduce and analyze BRSIC (Bilingual Remote Sensing Image Captioning), a comprehensive bilingual dataset that enriches three established English RSIC datasets with Chinese descriptions, encompassing 13,634 images paired with 68,170 bilingual captions. Building upon this foundation, we develop a systematic evaluation framework that addresses the prevalent inconsistency in evaluation protocols, enabling rigorous assessment of model performance through standardized retraining procedures on BRSIC. Furthermore, we present an extensive empirical study of eight state-of-the-art large vision-language models (LVLMs), examining their capabilities across multiple paradigms including zero-shot inference, supervised fine-tuning, and multi-lingual training. This comprehensive evaluation provides crucial insights into the strengths and limitations of current LVLMs in handling multilingual remote sensing tasks. Additionally, our cross-dataset transfer experiments reveal interesting findings. The code and data will be available at https://github.com/mrazhou/BRSIC.

Qing Zhou, Bingxuan Zhao, Tao Yang et al.

Dynamic data pruning accelerates deep learning by selectively omitting less informative samples during training. While per-sample loss is a common importance metric, obtaining it can be challenging or infeasible for complex models or loss functions, often requiring significant implementation effort. This work proposes the Batch Loss Score (BLS), a computationally efficient alternative using an Exponential Moving Average (EMA) of readily available batch losses to assign scores to individual samples. We frame the batch loss, from the perspective of a single sample, as a noisy measurement of its scaled individual loss, with noise originating from stochastic batch composition. It is formally shown that the EMA mechanism functions as a first-order low-pass filter, attenuating high-frequency batch composition noise. This yields a score approximating the smoothed and persistent contribution of the individual sample to the loss, providing a theoretical grounding for BLS as a proxy for sample importance. BLS demonstrates remarkable code integration simplicity (\textbf{three-line injection}) and readily adapts existing per-sample loss-based methods (\textbf{one-line proxy}). Its effectiveness is demonstrated by enhancing two such methods to losslessly prune \textbf{20\%-50\%} of samples across \textit{14 datasets}, \textit{11 tasks} and \textit{18 models}, highlighting its utility and broad applicability, especially for complex scenarios where per-sample loss is difficult to access. Code is available at https://github.com/mrazhou/BLS.

Qing Zhou, Shiyu Zhang, Yuyu Jia et al.

Chain-of-thought (CoT) reasoning has significantly improved the performance of large multimodal models in language-guided segmentation, yet its prohibitive computational cost, stemming from generating verbose rationales, limits real-world applicability. We introduce WISE (Wisdom from Internal Self-Exploration), a novel paradigm for efficient reasoning guided by the principle of \textit{thinking twice -- once for learning, once for speed}. WISE trains a model to generate a structured sequence: a concise rationale, the final answer, and then a detailed explanation. By placing the concise rationale first, our method leverages autoregressive conditioning to enforce that the concise rationale acts as a sufficient summary for generating the detailed explanation. This structure is reinforced by a self-distillation objective that jointly rewards semantic fidelity and conciseness, compelling the model to internalize its detailed reasoning into a compact form. At inference, the detailed explanation is omitted. To address the resulting conditional distribution shift, our inference strategy, WISE-S, employs a simple prompting technique that injects a brevity-focused instruction into the user's query. This final adjustment facilitates the robust activation of the learned concise policy, unlocking the full benefits of our framework. Extensive experiments show that WISE-S achieves state-of-the-art zero-shot performance on the ReasonSeg benchmark with 58.3 cIoU, while reducing the average reasoning length by nearly \textbf{5$\times$} -- from 112 to just 23 tokens. Code is available at \href{https://github.com/mrazhou/WISE}{WISE}.

Stephen Smith, Qing Zhou

Learning the structure of causal directed acyclic graphs (DAGs) is useful in many areas of machine learning and artificial intelligence, with wide applications. However, in the high-dimensional setting, it is challenging to obtain good empirical and theoretical results without strong and often restrictive assumptions. Additionally, it is questionable whether all of the variables purported to be included in the network are observable. It is of interest then to restrict consideration to a subset of the variables for relevant and reliable inferences. In fact, researchers in various disciplines can usually select a set of target nodes in the network for causal discovery. This paper develops a new constraint-based method for estimating the local structure around multiple user-specified target nodes, enabling coordination in structure learning between neighborhoods. Our method facilitates causal discovery without learning the entire DAG structure. We establish consistency results for our algorithm with respect to the local neighborhood structure of the target nodes in the true graph. Experimental results on synthetic and real-world data show that our algorithm is more accurate in learning the neighborhood structures with much less computational cost than standard methods that estimate the entire DAG. An R package implementing our methods may be accessed at https://github.com/stephenvsmith/CML.

Dongyang Xu, Yiran Luo, Tianle Lu et al.

Accurate behavior prediction for vehicles is essential but challenging for autonomous driving. Most existing studies show satisfying performance under regular scenarios, but most neglected safety-critical scenarios. In this study, a spatio-temporal dual-encoder network named STDA for safety-critical scenarios was developed. Considering the exceptional capabilities of human drivers in terms of situational awareness and comprehending risks, driver attention was incorporated into STDA to facilitate swift identification of the critical regions, which is expected to improve both performance and interpretability. STDA contains four parts: the driver attention prediction module, which predicts driver attention; the fusion module designed to fuse the features between driver attention and raw images; the temporary encoder module used to enhance the capability to interpret dynamic scenes; and the behavior prediction module to predict the behavior. The experiment data are used to train and validate the model. The results show that STDA improves the G-mean from 0.659 to 0.719 when incorporating driver attention and adopting a temporal encoder module. In addition, extensive experimentation has been conducted to validate that the proposed module exhibits robust generalization capabilities and can be seamlessly integrated into other mainstream models.

Bingxuan Zhao, Qing Zhou, Chuang Yang et al.

Text-to-image generation powered by Diffusion Transformers (DiTs) has made remarkable strides, yet remote sensing (RS) synthesis lags behind due to two barriers: the absence of a domain-specialized DiT prior and the prohibitive cost of training at the large resolutions that RS applications demand. Training-free resolution promotion via Rotary Position Embedding (RoPE) rescaling offers a practical remedy, but every existing method applies a static positional scaling rule throughout the denoising process. This uniform compression is particularly harmful for RS imagery, whose substantially denser medium- and high-frequency energy encodes the fine structures critical for aerial-scene realism, such as vehicles, building contours, and road markings. Addressing both challenges requires a domain-specialized generative prior coupled with a denoising-aware positional adaptation strategy. To this end, we fine-tune FLUX on over 100,000 curated RS images to build a strong domain prior (RS-FLUX), and propose Spectrum-aware Highly-dynamic Adaptation for Resolution Promotion (SHARP), a training-free method that introduces a rational fractional time schedule k_rs(t) into RoPE. SHARP applies strong positional promotion during the early layout-formation stage and progressively relaxes it during detail recovery, aligning extrapolation strength with the frequency-progressive nature of diffusion denoising. Its resolution-agnostic formulation further enables robust multi-scale generation from a single set of hyperparameters. Extensive experiments across six square and rectangular resolutions show that SHARP consistently outperforms all training-free baselines on CLIP Score, Aesthetic Score, and HPSv2, with widening margins at more aggressive extrapolation factors and negligible computational overhead. Code and weights are available at https://github.com/bxuanz/SHARP.

Junjie Chen, Fei Wang, Zhihao Huang et al.

Human conversation involves continuous exchanges of speech and nonverbal cues such as head nods, gaze shifts, and facial expressions that convey attention and emotion. Modeling these bidirectional dynamics in 3D is essential for building expressive avatars and interactive robots. However, existing frameworks often treat talking and listening as independent processes or rely on non-causal full-sequence modeling, hindering temporal coherence across turns. We present TIMAR (Turn-level Interleaved Masked AutoRegression), a causal framework for 3D conversational head generation that models dialogue as interleaved audio-visual contexts. It fuses multimodal information within each turn and applies turn-level causal attention to accumulate conversational history, while a lightweight diffusion head predicts continuous 3D head dynamics that captures both coordination and expressive variability. Experiments on the DualTalk benchmark show that TIMAR reduces Fréchet Distance and MSE by 15-30% on the test set, and achieves similar gains on out-of-distribution data. The source code has been released at https://github.com/CoderChen01/towards-seamless-interaction.

Rusi Chen, Yuanting Yang, Jiezhi Yao et al.

Mitral regurgitation is one of the most prevalent cardiac disorders. Four-dimensional (4D) ultrasound has emerged as the primary imaging modality for assessing dynamic valvular morphology. However, 4D mitral valve (MV) analysis remains challenging due to limited phase annotations, severe motion artifacts, and poor imaging quality. Yet, the absence of inter-phase dependency in existing methods hinders 4D MV analysis. To bridge this gap, we propose a Motion-Topology guided consistency network (MTCNet) for accurate 4D MV ultrasound segmentation in semi-supervised learning (SSL). MTCNet requires only sparse end-diastolic and end-systolic annotations. First, we design a cross-phase motion-guided consistency learning strategy, utilizing a bi-directional attention memory bank to propagate spatio-temporal features. This enables MTCNet to achieve excellent performance both per- and inter-phase. Second, we devise a novel topology-guided correlation regularization that explores physical prior knowledge to maintain anatomically plausible. Therefore, MTCNet can effectively leverage structural correspondence between labeled and unlabeled phases. Extensive evaluations on the first largest 4D MV dataset, with 1408 phases from 160 patients, show that MTCNet performs superior cross-phase consistency compared to other advanced methods (Dice: 87.30%, HD: 1.75mm). Both the code and the dataset are available at https://github.com/crs524/MTCNet.

Bryon Aragam, Qing Zhou

We develop a penalized likelihood estimation framework to estimate the structure of Gaussian Bayesian networks from observational data. In contrast to recent methods which accelerate the learning problem by restricting the search space, our main contribution is a fast algorithm for score-based structure learning which does not restrict the search space in any way and works on high-dimensional datasets with thousands of variables. Our use of concave regularization, as opposed to the more popular $\ell_0$ (e.g. BIC) penalty, is new. Moreover, we provide theoretical guarantees which generalize existing asymptotic results when the underlying distribution is Gaussian. Most notably, our framework does not require the existence of a so-called faithful DAG representation, and as a result the theory must handle the inherent nonidentifiability of the estimation problem in a novel way. Finally, as a matter of independent interest, we provide a comprehensive comparison of our approach to several standard structure learning methods using open-source packages developed for the R language. Based on these experiments, we show that our algorithm is significantly faster than other competing methods while obtaining higher sensitivity with comparable false discovery rates for high-dimensional data. In particular, the total runtime for our method to generate a solution path of 20 estimates for DAGs with 8000 nodes is around one hour.

Chuang Yang, Bingxuan Zhao, Qing Zhou et al.

The rapid advancement of deep generative models (DGMs) has significantly advanced research in computer vision, providing a cost-effective alternative to acquiring vast quantities of expensive imagery. However, existing methods predominantly focus on synthesizing remote sensing (RS) images aligned with real images in a global layout view, which limits their applicability in RS image object detection (RSIOD) research. To address these challenges, we propose a multi-class and multi-scale object image generator based on DGMs, termed MMO-IG, designed to generate RS images with supervised object labels from global and local aspects simultaneously. Specifically, from the local view, MMO-IG encodes various RS instances using an iso-spacing instance map (ISIM). During the generation process, it decodes each instance region with iso-spacing value in ISIM-corresponding to both background and foreground instances-to produce RS images through the denoising process of diffusion models. Considering the complex interdependencies among MMOs, we construct a spatial-cross dependency knowledge graph (SCDKG). This ensures a realistic and reliable multidirectional distribution among MMOs for region embedding, thereby reducing the discrepancy between source and target domains. Besides, we propose a structured object distribution instruction (SODI) to guide the generation of synthesized RS image content from a global aspect with SCDKG-based ISIM together. Extensive experimental results demonstrate that our MMO-IG exhibits superior generation capabilities for RS images with dense MMO-supervised labels, and RS detectors pre-trained with MMO-IG show excellent performance on real-world datasets.

Yuyu Jia, Qing Zhou, Wei Huang et al.

Few-shot learning aims to generalize the recognizer from seen categories to an entirely novel scenario. With only a few support samples, several advanced methods initially introduce class names as prior knowledge for identifying novel classes. However, obstacles still impede achieving a comprehensive understanding of how to harness the mutual advantages of visual and textual knowledge. In this paper, we propose a coherent Bidirectional Knowledge Permeation strategy called BiKop, which is grounded in a human intuition: A class name description offers a general representation, whereas an image captures the specificity of individuals. BiKop primarily establishes a hierarchical joint general-specific representation through bidirectional knowledge permeation. On the other hand, considering the bias of joint representation towards the base set, we disentangle base-class-relevant semantics during training, thereby alleviating the suppression of potential novel-class-relevant information. Experiments on four challenging benchmarks demonstrate the remarkable superiority of BiKop. Our code will be publicly available.

Zongyin Deng, Qing Zhou, Yuhao Fang et al.

This work presents TV-LoRA, a novel method for low-dose sparse-view CT reconstruction that combines a diffusion generative prior (NCSN++ with SDE modeling) and multi-regularization constraints, including anisotropic TV and nuclear norm (LoRA), within an ADMM framework. To address ill-posedness and texture loss under extremely sparse views, TV-LoRA integrates generative and physical constraints, and utilizes a 2D slice-based strategy with FFT acceleration and tensor-parallel optimization for efficient inference. Experiments on AAPM-2016, CTHD, and LIDC datasets with $N_{\mathrm{view}}=8,4,2$ show that TV-LoRA consistently surpasses benchmarks in SSIM, texture recovery, edge clarity, and artifact suppression, demonstrating strong robustness and generalizability. Ablation studies confirm the complementary effects of LoRA regularization and diffusion priors, while the FFT-PCG module provides a speedup. Overall, Diffusion + TV-LoRA achieves high-fidelity, efficient 3D CT reconstruction and broad clinical applicability in low-dose, sparse-sampling scenarios.

Stella Huang, Qing Zhou

Recent advances have established the identifiability of a directed acyclic graph (DAG) under additive noise models (ANMs), spurring the development of various causal discovery methods. However, most existing methods make restrictive model assumptions, rely heavily on general independence tests, or require substantial computational time. To address these limitations, we propose a sequential procedure to orient undirected edges in a completed partial DAG (CPDAG), representing an equivalence class of DAGs, by leveraging the pairwise additive noise model (PANM) to identify their causal directions. We prove that this procedure can recover the true causal DAG assuming a restricted ANM. Building on this result, we develop a novel constraint-based algorithm for learning causal DAGs under nonlinear ANMs. Given an estimated CPDAG, we develop a ranking procedure that sorts undirected edges by their adherence to the PANM, which defines an evaluation order of the edges. To determine the edge direction, we devise a statistical test that compares the log-likelihood values, evaluated with respect to the competing directions, of a sub-graph comprising just the candidate nodes and their identified parents in the partial DAG. We further establish the structural learning consistency of our algorithm in the large-sample limit. Extensive experiments on synthetic and real-world datasets demonstrate that our method is computationally efficient, robust to model misspecification, and consistently outperforms many existing nonlinear DAG learning methods.

Bingxu Wang, Min Ge, Kunzhi Cai et al.

Postoperative delirium (POD), a severe neuropsychiatric complication affecting nearly 50% of high-risk surgical patients, is defined as an acute disorder of attention and cognition, It remains significantly underdiagnosed in the intensive care units (ICUs) due to subjective monitoring methods. Early and accurate diagnosis of POD is critical and achievable. Here, we propose a POD prediction framework comprising a Transformer representation model followed by traditional machine learning algorithms. Our approaches utilizes multi-modal physiological data, including amplitude-integrated electroencephalography (aEEG), vital signs, electrocardiographic monitor data as well as hemodynamic parameters. We curated the first multi-modal POD dataset encompassing two patient types and evaluated the various Transformer architectures for representation learning. Empirical results indicate a consistent improvements of sensitivity and Youden index in patient TYPE I using Transformer representations, particularly our fusion adaptation of Pathformer. By enabling effective delirium diagnosis from postoperative day 1 to 3, our extensive experimental findings emphasize the potential of multi-modal physiological data and highlight the necessity of representation learning via multi-modal Transformer architecture in clinical diagnosis.

Yijia Zhao, Qing Zhou

The causal bandit problem aims to sequentially learn the intervention that maximizes the expectation of a reward variable within a system governed by a causal graph. Most existing approaches assume prior knowledge of the graph structure, or impose unrealistically restrictive conditions on the graph. In this paper, we assume a Gaussian linear directed acyclic graph (DAG) over arms and the reward variable, and study the causal bandit problem when the graph structure is unknown. We identify backdoor adjustment sets for each arm using sequentially generated experimental and observational data during the decision process, which allows us to estimate causal effects and construct upper confidence bounds. By integrating estimates from both data sources, we develop a novel bandit algorithm, based on modified upper confidence bounds, to sequentially determine the optimal intervention. We establish both case-dependent and case-independent upper bounds on the cumulative regret for our algorithm, which improve upon the bounds of the standard multi-armed bandit algorithms. Our empirical study demonstrates its advantage over existing methods with respect to cumulative regret and computation time.

Alex Chen, Qing Zhou

The assumption of independence between observations (units) in a dataset is prevalent across various methodologies for learning causal graphical models. However, this assumption often finds itself in conflict with real-world data, posing challenges to accurate structure learning. We propose a decorrelation-based approach for causal graph learning on dependent binary data, where the local conditional distribution is defined by a latent utility model with dependent errors across units. We develop a pairwise maximum likelihood method to estimate the covariance matrix for the dependence among the units. Then, leveraging the estimated covariance matrix, we develop an EM-like iterative algorithm to generate and decorrelate samples of the latent utility variables, which serve as decorrelated data. Any standard causal discovery method can be applied on the decorrelated data to learn the underlying causal graph. We demonstrate that the proposed decorrelation approach significantly improves the accuracy in causal graph learning, through numerical experiments on both synthetic and real-world datasets.

Zhongao Sun, Jiameng Li, Yuhan Wang et al.

Brain tumor segmentation remains a significant challenge, particularly in the context of multi-modal magnetic resonance imaging (MRI) where missing modality images are common in clinical settings, leading to reduced segmentation accuracy. To address this issue, we propose a novel strategy, which is called masked predicted pre-training, enabling robust feature learning from incomplete modality data. Additionally, in the fine-tuning phase, we utilize a knowledge distillation technique to align features between complete and missing modality data, simultaneously enhancing model robustness. Notably, we leverage the Holder pseudo-divergence instead of the KLD for distillation loss, offering improve mathematical interpretability and properties. Extensive experiments on the BRATS2018 and BRATS2020 datasets demonstrate significant performance enhancements compared to existing state-of-the-art methods.

Ping Wei, Qing Zhou, Zichi Wang et al.

Generative steganography (GS) is an emerging technique that generates stego images directly from secret data. Various GS methods based on GANs or Flow have been developed recently. However, existing GAN-based GS methods cannot completely recover the hidden secret data due to the lack of network invertibility, while Flow-based methods produce poor image quality due to the stringent reversibility restriction in each module. To address this issue, we propose a novel GS scheme called "Generative Steganography Diffusion" (GSD) by devising an invertible diffusion model named "StegoDiffusion". It not only generates realistic stego images but also allows for 100\% recovery of the hidden secret data. The proposed StegoDiffusion model leverages a non-Markov chain with a fast sampling technique to achieve efficient stego image generation. By constructing an ordinary differential equation (ODE) based on the transition probability of the generation process in StegoDiffusion, secret data and stego images can be converted to each other through the approximate solver of ODE -- Euler iteration formula, enabling the use of irreversible but more expressive network structures to achieve model invertibility. Our proposed GSD has the advantages of both reversibility and high performance, significantly outperforming existing GS methods in all metrics.

Gabriel Ruiz, Oscar Hernan Madrid Padilla, Qing Zhou

Causal discovery, the learning of causality in a data mining scenario, has been of strong scientific and theoretical interest as a starting point to identify "what causes what?" Contingent on assumptions and a proper learning algorithm, it is sometimes possible to identify and accurately estimate a causal directed acyclic graph (DAG), as opposed to a Markov equivalence class of graphs that gives ambiguity of causal directions. The focus of this paper is in highlighting the identifiability and estimation of DAGs with general error distributions through a general sequential sorting procedure that orders variables one at a time, starting at root nodes, followed by children of the root nodes, and so on until completion. We demonstrate a novel application of this general approach to estimate the topological ordering of a DAG. At each step of the procedure, only simple likelihood ratio scores are calculated on regression residuals to decide the next node to append to the current partial ordering. The computational complexity of our algorithm on a p-node problem is O(pd), where d is the maximum neighborhood size. Under mild assumptions, the population version of our procedure provably identifies a true ordering of the underlying DAG. We provide extensive numerical evidence to demonstrate that this sequential procedure scales to possibly thousands of nodes and works well for high-dimensional data. We accompany these numerical experiments with an application to a single-cell gene expression dataset.

Qiaoling Ye, Arash A. Amini, Qing Zhou

We consider the task of learning causal structures from data stored on multiple machines, and propose a novel structure learning method called distributed annealing on regularized likelihood score (DARLS) to solve this problem. We model causal structures by a directed acyclic graph that is parameterized with generalized linear models, so that our method is applicable to various types of data. To obtain a high-scoring causal graph, DARLS simulates an annealing process to search over the space of topological sorts, where the optimal graphical structure compatible with a sort is found by a distributed optimization method. This distributed optimization relies on multiple rounds of communication between local and central machines to estimate the optimal structure. We establish its convergence to a global optimizer of the overall score that is computed on all data across local machines. To the best of our knowledge, DARLS is the first distributed method for learning causal graphs with such theoretical guarantees. Through extensive simulation studies, DARLS has shown competing performance against existing methods on distributed data, and achieved comparable structure learning accuracy and test-data likelihood with competing methods applied to pooled data across all local machines. In a real-world application for modeling protein-DNA binding networks with distributed ChIP-Sequencing data, DARLS also exhibits higher predictive power than other methods, demonstrating a great advantage in estimating causal networks from distributed data.

Jireh Huang, Qing Zhou

We develop a novel hybrid method for Bayesian network structure learning called partitioned hybrid greedy search (pHGS), composed of three distinct yet compatible new algorithms: Partitioned PC (pPC) accelerates skeleton learning via a divide-and-conquer strategy, $p$-value adjacency thresholding (PATH) effectively accomplishes parameter tuning with a single execution, and hybrid greedy initialization (HGI) maximally utilizes constraint-based information to obtain a high-scoring and well-performing initial graph for greedy search. We establish structure learning consistency of our algorithms in the large-sample limit, and empirically validate our methods individually and collectively through extensive numerical comparisons. The combined merits of pPC and PATH achieve significant computational reductions compared to the PC algorithm without sacrificing the accuracy of estimated structures, and our generally applicable HGI strategy reliably improves the estimation structural accuracy of popular hybrid algorithms with negligible additional computational expense. Our empirical results demonstrate the superior empirical performance of pHGS against many state-of-the-art structure learning algorithms.

Bingling Wang, Qing Zhou

Discovery of causal relationships from observational data is an important problem in many areas. Several recent results have established the identifiability of causal DAGs with non-Gaussian and/or nonlinear structural equation models (SEMs). In this paper, we focus on nonlinear SEMs defined by non-invertible functions, which exist in many data domains, and propose a novel test for non-invertible bivariate causal models. We further develop a method to incorporate this test in structure learning of DAGs that contain both linear and nonlinear causal relations. By extensive numerical comparisons, we show that our algorithms outperform existing DAG learning methods in identifying causal graphical structures. We illustrate the practical application of our method in learning causal networks for combinatorial binding of transcription factors from ChIP-Seq data.

Arash A. Amini, Bryon Aragam, Qing Zhou

Knowing when a graphical model is perfect to a distribution is essential in order to relate separation in the graph to conditional independence in the distribution, and this is particularly important when performing inference from data. When the model is perfect, there is a one-to-one correspondence between conditional independence statements in the distribution and separation statements in the graph. Previous work has shown that almost all models based on linear directed acyclic graphs as well as Gaussian chain graphs are perfect, the latter of which subsumes Gaussian graphical models (i.e., the undirected Gaussian models) as a special case. However, the complexity of chain graph models leads to a proof of this result which is indirect and mired by the complications of parameterizing this general class. In this paper, we directly approach the problem of perfectness for the Gaussian graphical models, and provide a new proof, via a more transparent parametrization, that almost all such models are perfect. Our approach is based on, and substantially extends, a construction of Lněnička and Matúš showing the existence of a perfect Gaussian distribution for any graph.

Hangjian Li, Oscar Hernan Madrid Padilla, Qing Zhou

Structural learning of directed acyclic graphs (DAGs) or Bayesian networks has been studied extensively under the assumption that data are independent. We propose a new Gaussian DAG model for dependent data which assumes the observations are correlated according to an undirected network. Under this model, we develop a method to estimate the DAG structure given a topological ordering of the nodes. The proposed method jointly estimates the Bayesian network and the correlations among observations by optimizing a scoring function based on penalized likelihood. We show that under some mild conditions, the proposed method produces consistent estimators after one iteration. Extensive numerical experiments also demonstrate that by jointly estimating the DAG structure and the sample correlation, our method achieves much higher accuracy in structure learning. When the node ordering is unknown, through experiments on synthetic and real data, we show that our algorithm can be used to estimate the correlations between samples, with which we can de-correlate the dependent data to significantly improve the performance of classical DAG learning methods.

Qiaoling Ye, Arash A. Amini, Qing Zhou

Bayesian networks are a class of popular graphical models that encode causal and conditional independence relations among variables by directed acyclic graphs (DAGs). We propose a novel structure learning method, annealing on regularized Cholesky score (ARCS), to search over topological sorts, or permutations of nodes, for a high-scoring Bayesian network. Our scoring function is derived from regularizing Gaussian DAG likelihood, and its optimization gives an alternative formulation of the sparse Cholesky factorization problem from a statistical viewpoint, which is of independent interest. We combine global simulated annealing over permutations with a fast proximal gradient algorithm, operating on triangular matrices of edge coefficients, to compute the score of any permutation. Combined, the two approaches allow us to quickly and effectively search over the space of DAGs without the need to verify the acyclicity constraint or to enumerate possible parent sets given a candidate topological sort. The annealing aspect of the optimization is able to consistently improve the accuracy of DAGs learned by local search algorithms. In addition, we develop several techniques to facilitate the structure learning, including pre-annealing data-driven tuning parameter selection and post-annealing constraint-based structure refinement. Through extensive numerical comparisons, we show that ARCS achieves substantial improvements over existing methods, demonstrating its great potential to learn Bayesian networks from both observational and experimental data.

Jiaying Gu, Qing Zhou

Structure learning of Bayesian networks has always been a challenging problem. Nowadays, massive-size networks with thousands or more of nodes but fewer samples frequently appear in many areas. We develop a divide-and-conquer framework, called partition-estimation-fusion (PEF), for structure learning of such big networks. The proposed method first partitions nodes into clusters, then learns a subgraph on each cluster of nodes, and finally fuses all learned subgraphs into one Bayesian network. The PEF method is designed in a flexible way so that any structure learning method may be used in the second step to learn a subgraph structure as either a DAG or a CPDAG. In the clustering step, we adapt the hierarchical clustering method to automatically choose a proper number of clusters. In the fusion step, we propose a novel hybrid method that sequentially add edges between subgraphs. Extensive numerical experiments demonstrate the competitive performance of our PEF method, in terms of both speed and accuracy compared to existing methods. Our method can improve the accuracy of structure learning by 20% or more, while reducing running time up to two orders-of-magnitude.

Qing Zhou, Songfeng Lu, Zhigang Zhang et al.

In this paper, we propose a quantum version of the differential cryptanalysis which offers a quadratic speedup over the existing classical one and show the quantum circuit implementing it. The quantum differential cryptanalysis is based on the quantum minimum/maximum-finding algorithm, where the values to be compared and filtered are obtained by calling the quantum counting algorithm. Any cipher which is vulnerable to the classical differential cryptanalysis based on counting procedures can be cracked more quickly under this quantum differential attack.

Qing Zhou, Songfeng Lu

We propose a homomorphic search protocol based on quantum homomorphic encryption, in which a client Alice with limited quantum ability can give her encrypted data to a powerful but untrusted quantum server and let the server search for her without decryption. By outsourcing the interactive key-update process to a trusted key center, Alice only needs to prepare and encrypt her original data and to decrypt the ciphered search result in linear time. Besides, we also present a compact and perfectly secure quantum homomorphic evaluation protocol for Cliford circuits, where the decryption key can be calculated by Alice with polynomial overhead with respect to the key length.

Arash A. Amini, Bryon Aragam, Qing Zhou

Neighborhood regression has been a successful approach in graphical and structural equation modeling, with applications to learning undirected and directed graphical models. We extend these ideas by defining and studying an algebraic structure called the neighborhood lattice based on a generalized notion of neighborhood regression. We show that this algebraic structure has the potential to provide an economic encoding of all conditional independence statements in a Gaussian distribution (or conditional uncorrelatedness in general), even in the cases where no graphical model exists that could "perfectly" encode all such statements. We study the computational complexity of computing these structures and show that under a sparsity assumption, they can be computed in polynomial time, even in the absence of the assumption of perfectness to a graph. On the other hand, assuming perfectness, we show how these neighborhood lattices may be "graphically" computed using the separation properties of the so-called partial correlation graph. We also draw connections with directed acyclic graphical models and Bayesian networks. We derive these results using an abstract generalization of partial uncorrelatedness, called partial orthogonality, which allows us to use algebraic properties of projection operators on Hilbert spaces to significantly simplify and extend existing ideas and arguments. Consequently, our results apply to a wide range of random objects and data structures, such as random vectors, data matrices, and functions.

Bryon Aragam, Jiaying Gu, Qing Zhou

Learning graphical models from data is an important problem with wide applications, ranging from genomics to the social sciences. Nowadays datasets often have upwards of thousands---sometimes tens or hundreds of thousands---of variables and far fewer samples. To meet this challenge, we have developed a new R package called sparsebn for learning the structure of large, sparse graphical models with a focus on Bayesian networks. While there are many existing software packages for this task, this package focuses on the unique setting of learning large networks from high-dimensional data, possibly with interventions. As such, the methods provided place a premium on scalability and consistency in a high-dimensional setting. Furthermore, in the presence of interventions, the methods implemented here achieve the goal of learning a causal network from data. Additionally, the sparsebn package is fully compatible with existing software packages for network analysis.

Bryon Aragam, Arash A. Amini, Qing Zhou

We study a family of regularized score-based estimators for learning the structure of a directed acyclic graph (DAG) for a multivariate normal distribution from high-dimensional data with $p\gg n$. Our main results establish support recovery guarantees and deviation bounds for a family of penalized least-squares estimators under concave regularization without assuming prior knowledge of a variable ordering. These results apply to a variety of practical situations that allow for arbitrary nondegenerate covariance structures as well as many popular regularizers including the MCP, SCAD, $\ell_{0}$ and $\ell_{1}$. The proof relies on interpreting a DAG as a recursive linear structural equation model, which reduces the estimation problem to a series of neighbourhood regressions. We provide a novel statistical analysis of these neighbourhood problems, establishing uniform control over the superexponential family of neighbourhoods associated with a Gaussian distribution. We then apply these results to study the statistical properties of score-based DAG estimators, learning causal DAGs, and inferring conditional independence relations via graphical models. Our results yield---for the first time---finite-sample guarantees for structure learning of Gaussian DAGs in high-dimensions via score-based estimation.

Yuliya Marchetti, Qing Zhou

We develop an iterative subsampling approach to improve the computational efficiency of our previous work on solution path clustering (SPC). The SPC method achieves clustering by concave regularization on the pairwise distances between cluster centers. This clustering method has the important capability to recognize noise and to provide a short path of clustering solutions; however, it is not sufficiently fast for big datasets. Thus, we propose a method that iterates between clustering a small subsample of the full data and sequentially assigning the other data points to attain orders of magnitude of computational savings. The new method preserves the ability to isolate noise, includes a solution selection mechanism that ultimately provides one clustering solution with an estimated number of clusters, and is shown to be able to extract small tight clusters from noisy data. The method's relatively minor losses in accuracy are demonstrated through simulation studies, and its ability to handle large datasets is illustrated through applications to gene expression datasets. An R package, SPClustering, for the SPC method with iterative subsampling is available at http://www.stat.ucla.edu/~zhou/Software.html.

Yuliya Marchetti, Qing Zhou

Fast accumulation of large amounts of complex data has created a need for more sophisticated statistical methodologies to discover interesting patterns and better extract information from these data. The large scale of the data often results in challenging high-dimensional estimation problems where only a minority of the data shows specific grouping patterns. To address these emerging challenges, we develop a new clustering methodology that introduces the idea of a regularization path into unsupervised learning. A regularization path for a clustering problem is created by varying the degree of sparsity constraint that is imposed on the differences between objects via the minimax concave penalty with adaptive tuning parameters. Instead of providing a single solution represented by a cluster assignment for each object, the method produces a short sequence of solutions that determines not only the cluster assignment but also a corresponding number of clusters for each solution. The optimization of the penalized loss function is carried out through an MM algorithm with block coordinate descent. The advantages of this clustering algorithm compared to other existing methods are as follows: it does not require the input of the number of clusters; it is capable of simultaneously separating irrelevant or noisy observations that show no grouping pattern, which can greatly improve data interpretation; it is a general methodology that can be applied to many clustering problems. We test this method on various simulated datasets and on gene expression data, where it shows better or competitive performance compared against several clustering methods.

Jiaying Gu, Fei Fu, Qing Zhou

Bayesian networks, with structure given by a directed acyclic graph (DAG), are a popular class of graphical models. However, learning Bayesian networks from discrete or categorical data is particularly challenging, due to the large parameter space and the difficulty in searching for a sparse structure. In this article, we develop a maximum penalized likelihood method to tackle this problem. Instead of the commonly used multinomial distribution, we model the conditional distribution of a node given its parents by multi-logit regression, in which an edge is parameterized by a set of coefficient vectors with dummy variables encoding the levels of a node. To obtain a sparse DAG, a group norm penalty is employed, and a blockwise coordinate descent algorithm is developed to maximize the penalized likelihood subject to the acyclicity constraint of a DAG. When interventional data are available, our method constructs a causal network, in which a directed edge represents a causal relation. We apply our method to various simulated and real data sets. The results show that our method is very competitive, compared to many existing methods, in DAG estimation from both interventional and high-dimensional observational data.

Qing Zhou

Regularized linear regression under the $\ell_1$ penalty, such as the Lasso, has been shown to be effective in variable selection and sparse modeling. The sampling distribution of an $\ell_1$-penalized estimator $\hatβ$ is hard to determine as the estimator is defined by an optimization problem that in general can only be solved numerically and many of its components may be exactly zero. Let $S$ be the subgradient of the $\ell_1$ norm of the coefficient vector $β$ evaluated at $\hatβ$. We find that the joint sampling distribution of $\hatβ$ and $S$, together called an augmented estimator, is much more tractable and has a closed-form density under a normal error distribution in both low-dimensional ($p\leq n$) and high-dimensional ($p>n$) settings. Given $β$ and the error variance $σ^2$, one may employ standard Monte Carlo methods, such as Markov chain Monte Carlo and importance sampling, to draw samples from the distribution of the augmented estimator and calculate expectations with respect to the sampling distribution of $\hatβ$. We develop a few concrete Monte Carlo algorithms and demonstrate with numerical examples that our approach may offer huge advantages and great flexibility in studying sampling distributions in $\ell_1$-penalized linear regression. We also establish nonasymptotic bounds on the difference between the true sampling distribution of $\hatβ$ and its estimator obtained by plugging in estimated parameters, which justifies the validity of Monte Carlo simulation from an estimated sampling distribution even when $p\gg n\to \infty$.