Arrow Research search

Author name cluster

Xiao Luo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

42 papers
1 author row

Possible papers

42

AAAI Conference 2026 Conference Paper

CogniTrust: Cognitive Memory-Driven Verifiable Supervision for Robust Hashing

  • Yiyang Gu
  • Bohan Wu
  • Yifang Qin
  • Jiaru Tang
  • Rong-Cheng Tu
  • Zhiping Xiao
  • Taian Guo
  • Junyu Luo

In this paper, we study the problem of robust multi-label hashing, where label noise hinders the learning of a reliable semantic structure from data. Many existing methods rely on heuristic sample selection or consistency-based training, but lack a unified mechanism to validate and refine supervision across structural and semantic levels. Inspired by cognitive theories of human memory, we propose a novel framework called CogniTrust that unifies verifiable supervision with a triadic memory model: a) In episodic memory, feature activations are decomposed into spatial patterns that support the assessment of structural evidence and the estimation of label reliability; b) Semantic memory keeps track of class-level prototypes from structurally attentive regions to estimate the semantic plausibility of labels; c) Reconstructive memory simulates memory recall through interpolation between images using a diffusion-based mixup process, which enriches the training signals for semantically uncertain regions. These components work together, allowing supervision to be refined through the joint consideration of spatial structure and semantic information. Extensive experiments on noisy hashing benchmarks demonstrate that CogniTrust consistently outperforms a range of state-of-the-art baselines. Our results show that cognitive memory mechanisms offer a principled basis for more reliable label denoising and robust hashing.

PDF Details DOI

YNIMG Journal 2026 Journal Article

Dynamic brain network reconfiguration under stress: A multiphase fMRI study

  • Xiao Luo
  • Jiahao Huang
  • Kun Shi
  • Yiqing Ma
  • Yibo Wang
  • Xinli Tang
  • Xiaolin Zhao
  • Xi Ren

Acute stress induces a dynamic reallocation of neural resources across three distinct phases: Pre-stress, Stress, and Post-stress. Despite extensive research on isolated phases, a critical gap remains in understanding how this resource reconfiguration shapes the brain's dynamic characteristics across the entire temporal continuum. To address this gap, we employed Hidden Markov Modeling (HMM) to investigate whole-brain network dynamics continuously across all phases in two independent cohorts using the ScanSTRESS (n = 77, 35 females) and Montreal Imaging Stress Task (n = 48, 24 females). Our results revealed rapid and reversible spatiotemporal reconfigurations of large-scale brain networks, accompanied by elevated cortisol levels in both cohorts. Specifically, a marked spatiotemporal reconfiguration of brain networks was observed from Pre-stress to Stress phases, characterized by overall suppressed activation of the executive control network, alongside enhanced sensory processing, and increased functional coupling among salience, sensory, and executive networks. These changes reversed during the Post-stress phase, with no significant differences between Pre- and Post-stress phases. Critically, we identified robust individual differences: females exhibited higher state switching rates during stress across both cohorts, and a poorer post-stress recovery index (greater deviation from baseline) was associated with higher depression and anxiety scores. Synthesizing these findings, we propose a Tri-Phase Network Reconfiguration Model positing that allostasis is achieved through phase-specific brain state repertoires and directed transitions. This dynamic framework advances our understanding of stress adaptation and offers testable hypotheses for how these processes may be dysregulated in stress-related psychopathology.

Details DOI

AAAI Conference 2025 Conference Paper

Attention Bootstrapping for Multi-Modal Test-Time Adaptation

  • Yusheng Zhao
  • Junyu Luo
  • Xiao Luo
  • Jinsheng Huang
  • Jingyang Yuan
  • Zhiping Xiao
  • Ming Zhang

Test-time adaptation aims to adapt a well-trained model to potential distribution shifts at test time using only unlabeled test data, without access to the original training data. While previous efforts mainly focus on a single modality, test-time distribution shift in the multi-modal setting is more complex and calls for new solutions. This paper tackles the problem of multi-modal test-time adaptation by proposing a novel method named Attention Bootstrapping with Principal Entropy Minimization (ABPEM). We observe that test-time distribution shift causes misalignment across modalities, leading to a large gap between intra-modality discrepancies (measured by self-attention) and inter-modality discrepancies (measured by cross-attention). We name this the attention gap. This attention gap widens with more severe distribution shifts, hindering effective modality fusion. To mitigate this attention gap and encourage better modality fusion, we propose attention bootstrapping that promotes cross-attention with the guidance of self-attention. Moreover, to reduce the gradient noise in the commonly-used entropy minimization, we adopt principal entropy minimization, a refinement of entropy minimization that reduces gradient noise by focusing on the principal parts of entropy, excluding less reliable gradient information. Extensive experiments on the benchmarks validate the effectiveness of the proposed ABPEM in comparison with competing baselines.

PDF Details DOI

TMLR Journal 2025 Journal Article

DELTA: Dual Consistency Delving with Topological Uncertainty for Active Graph Domain Adaptation

  • Pengyun Wang
  • Yadi Cao
  • Chris Russell
  • Yanxin Shen
  • Junyu Luo
  • Ming Zhang
  • Siyu Heng
  • Xiao Luo

Graph domain adaptation has recently enabled knowledge transfer across different graphs. However, without the semantic information on target graphs, the performance on target graphs is still far from satisfactory. To address the issue, we study the problem of active graph domain adaptation, which selects a small quantitative of informative nodes on the target graph for extra annotation. This problem is highly challenging due to the complicated topological relationships and the distribution discrepancy across graphs. In this paper, we propose a novel approach named Dual Consistency Delving with Topological Uncertainty (DELTA) for active graph domain adaptation. Our DELTA consists of an edge-oriented graph subnetwork and a path-oriented graph subnetwork, which can explore topological semantics from complementary perspectives. In particular, our edge-oriented graph subnetwork utilizes the message passing mechanism to learn neighborhood information, while our path-oriented graph subnetwork explores high-order relationships from substructures. To jointly learn from two subnetworks, we roughly select informative candidate nodes with the consideration of consistency across two subnetworks. Then, we aggregate local semantics from its K-hop subgraph based on node degrees for topological uncertainty estimation. To overcome potential distribution shifts, we compare target nodes and their corresponding source nodes for discrepancy scores as an additional component for fine selection. Extensive experiments on benchmark datasets demonstrate that DELTA outperforms various state-of-the-art approaches. The code implementation of DELTA is available at https://github.com/goose315/DELTA.

PDF Details

NeurIPS Conference 2025 Conference Paper

Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models

  • Zitong Shi
  • Frank Wan
  • Haixin Wang
  • Ruoyan Li
  • Zijie Huang
  • Wanjia Zhao
  • Yijia Xiao
  • Xiao Luo

Recent studies reveal that large language models (LLMs) often struggle to resolve conflicting instructions embedded within hierarchical prompts, resulting in decreased compliance with system-level directives and compromising the reliability of safety-critical applications. While earlier approaches attempt to improve instruction hierarchy awareness through prompt engineering or embedding-level modifications, they typically lack structural modeling and either offer limited gains or require extensive fine-tuning. In this work, we introduce $\textbf{FocalLoRA}$, a parameter-efficient and structure-aware framework that strengthens hierarchical instruction adherence by selectively optimizing structurally critical attention heads, referred to as $\textit{focal heads}$, which exhibit heightened sensitivity to instruction conflicts. Experiments across multiple models and a dedicated benchmark demonstrate that FocalLoRA markedly enhances system instruction compliance with minimal tuning cost. For instance, on Llama-8B, fine-tuning only 0. 0188\% of parameters yields a 35. 52\% $\uparrow$ in system instruction compliance.

PDF Details

AAAI Conference 2025 Conference Paper

DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval

  • Fan Zhang
  • Changhu Wang
  • Zebang Cheng
  • Xiaojiang Peng
  • Dongjie Wang
  • Yijia Xiao
  • Chong Chen
  • Xian-Sheng Hua

With the burst of big data, 2D-3D cross-modal retrieval has received increasing attention, which aims to retrieve relevant data from one modality given the query from the other modality. In this paper, we study an underexplored yet practical problem of semi-supervised 2D-3D cross-modal retrieval, which could suffer from serious label scarcity in real-world applications. Moreover, the huge heterogeneous gap could deteriorate the process of learning from unlabeled data. In this work, we propose a novel approach named Decoupled Discriminative Learning with Bigraph-aware Alignment (DREAM) for semi-supervised 2D-3D cross-modal retrieval. The core of our DREAM is to decouple the label prediction and reliability measurement processes to reduce overconfident samples in discriminative learning. In particular, we enhance a label prediction module with label propagation from labeled samples and additionally introduce a reliability measurement module to learn the scores of predicted labels. To reduce class-related bias, we compare reliability scores with class-specific adaptive thresholds to identify samples for additional learning. In addition, negative labels are estimated for unselected samples, which guides soft semantic learning to make the best use of all the information. To further minimize the heterogeneous gap, we build a bigraph graph that connects cross-modal similar examples and then conduct learning to cluster with most edges kept for alignment. Extensive experiments on several benchmark datasets validate the superiority of the proposed DREAM.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Dual Prototype-Enhanced Contrastive Framework for Class-Imbalanced Graph Domain Adaptation

  • Xin Ma
  • Yifan Wang
  • Siyu Yi
  • Wei Ju
  • Junyu Luo
  • Yusheng Zhao
  • Xiao Luo
  • Jiancheng Lv

Graph transfer learning, especially in unsupervised domain adaptation, aims to transfer knowledge from a label-abundant source graph to an unlabeled target graph. However, most existing approaches overlook the common issue of label imbalance in the source domain, typically assuming a balanced label distribution that rarely holds in practice. Moreover, they face challenges arising from biased knowledge in the source graph and substantial domain distribution shifts. To remedy the above challenges, we propose a dual-branch prototype-enhanced contrastive framework for class-imbalanced graph domain adaptation in this paper. Specifically, we introduce a dual-branch graph encoder to capture both local and global information, generating class-specific prototypes from a distilled anchor set. Then, a prototype-enhanced contrastive learning framework is introduced. On the one hand, we encourage class alignment between the two branches based on constructed prototypes to alleviate the bias introduced by class imbalance. On the other hand, we infer the pseudo-labels for the target domain and align sample pairs across domains that share similar semantics to reduce domain discrepancies. Experimental results show that our ImGDA outperforms the state-of-the-art methods across multiple datasets and settings. The code is available at: https: //github. com/maxin88scu/ImGDA.

PDF Details

NeurIPS Conference 2025 Conference Paper

Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs

  • Yusheng Zhao
  • Qixin Zhang
  • Xiao Luo
  • Weizhi Zhang
  • Zhiping Xiao
  • Wei Ju
  • Philip S Yu
  • Ming Zhang

Large language models (LLMs) have been used in many zero-shot learning problems, with their strong generalization ability. Recently, adopting LLMs in text-attributed graphs (TAGs) has drawn increasing attention. However, the adoption of LLMs faces two major challenges: limited information on graph structure and unreliable responses. LLMs struggle with text attributes isolated from the graph topology. Worse still, they yield unreliable predictions due to both information insufficiency and the inherent weakness of LLMs (e. g. , hallucination). Towards this end, this paper proposes a novel method named Dynamic Text Bundling Supervision (DENSE) that queries LLMs with bundles of texts to obtain bundle-level labels and uses these labels to supervise graph neural networks. Specifically, we sample a set of bundles, each containing a set of nodes with corresponding texts of close proximity. We then query LLMs with the bundled texts to obtain the label of each bundle. Subsequently, the bundle labels are used to supervise the optimization of graph neural networks, and the bundles are further refined to exclude noisy items. To justify our design, we also provide theoretical analysis of the proposed method. Extensive experiments across ten datasets validate the effectiveness of the proposed method.

PDF Details

NeurIPS Conference 2025 Conference Paper

Flow Field Reconstruction with Sensor Placement Policy Learning

  • Ruoyan Li
  • Frank Wan
  • Zijie Huang
  • Zixiao Liu
  • Haixin Wang
  • Xiao Luo
  • Wei Wang
  • Yizhou Sun

Flow‐field reconstruction from sparse sensor measurements remains a central challenge in modern fluid dynamics, as the need for high‐fidelity data often conflicts with practical limits on sensor deployment. Existing deep learning–based methods have demonstrated promising results, but they typically depend on simplifying assumptions such as two‐dimensional domains, predefined governing equations, synthetic datasets derived from idealized flow physics, and unconstrained sensor placement. In this work, we address these limitations by studying flow reconstruction under realistic conditions and introducing a \emph{directional transport‐aware Graph Neural Network (GNN)} that explicitly encodes both flow directionality and information transport. We further show that conventional sensor placement strategies frequently yield suboptimal configurations. To overcome this, we propose a novel \emph{Two‐Step Constrained PPO} procedure for Proximal Policy Optimization (PPO), which jointly optimizes sensor layouts by incorporating flow variability and accounts for reconstruction model's performance disparity with respect to sensor placement. We conduct comprehensive experiments under realistic assumptions to benchmark the performance of our reconstruction model and sensor placement policy. Together, they achieve significant improvements over existing methods.

PDF Details

NeurIPS Conference 2025 Conference Paper

Fourier Clouds: Fast Bias Correction for Imbalanced Semi-Supervised Learning

  • Jiawei Gu
  • Yidi Wang
  • Qingqiang Sun
  • Xinming Li
  • Xiao Luo
  • Ziyue Qiao

Pseudo-label-based Semi-Supervised Learning (SSL) often suffers from classifier bias, particularly under class imbalance, as inaccurate pseudo-labels tend to exacerbate existing biases towards majority classes. Existing methods, such as \textit{CDMAD}\cite{cdmad}, utilize simplistic reference inputs—typically uniform or blank-colored images—to estimate and correct this bias. However, such simplistic references fundamentally ignore realistic statistical information inherent to real datasets, specifically typical color distributions, texture details, and frequency characteristics. This lack of \emph{statistical representativeness} can lead the model to inaccurately estimate its inherent bias, limiting the effectiveness of bias correction, particularly under severe class imbalance or substantial distribution mismatches between labeled and unlabeled datasets. To overcome these limitations, we introduce the \textbf{FARAD} (Fourier-Adapted Reference for Accurate Debiasing) System. This system utilizes random-phase images, constructed by preserving the amplitude spectrum of real data while randomizing the phase spectrum. This strategy ensures two critical properties: (1) \textbf{Semantic Irrelevance}, as randomizing phase removes any structural or recognizable semantic cues, and (2) \textbf{Statistical Representativeness}, as preserving the amplitude spectrum maintains realistic textures, color distributions, and frequency characteristics. Grounded theoretically in classical Fourier analysis, the FARAD System provides a robust, accurate estimation of per-class biases. Furthermore, computational efficiency is enhanced through optimized real-to-complex (R2C) batched Fast Fourier Transforms (FFTs). Comprehensive experiments demonstrate that our approach, significantly improves minority-class accuracy and overall SSL performance, particularly under challenging imbalance scenarios, compared with existing reference-based bias correction methods.

PDF Details

TMLR Journal 2025 Journal Article

Graph Fourier Neural ODEs: Modeling Spatial-temporal Multi-scales in Molecular Dynamics

  • Fang Sun
  • Zijie Huang
  • Haixin Wang
  • Huacong Tang
  • Xiao Luo
  • Wei Wang
  • Yizhou Sun

Accurately predicting long-horizon molecular dynamics (MD) trajectories remains a significant challenge, as existing deep learning methods often struggle to retain fidelity over extended simulations. We hypothesize that one key factor limiting accuracy is the difficulty of capturing interactions that span distinct spatial and temporal scales—ranging from high-frequency local vibrations to low-frequency global conformational changes. To address these limitations, we propose **Graph Fourier Neural ODEs (GF-NODE)**, integrating a graph Fourier transform for spatial frequency decomposition with a Neural ODE framework for continuous-time evolution. Specifically, GF-NODE first decomposes molecular configurations into multiple spatial frequency modes using the graph Laplacian, then evolves the frequency components in time via a learnable Neural ODE module that captures both local and global dynamics, and finally reconstructs the updated molecular geometry through an inverse graph Fourier transform. By explicitly modeling high- and low-frequency phenomena in this unified pipeline, GF-NODE more effectively captures long-range correlations and local fluctuations alike. We provide theoretical insight through heat equation analysis on a simplified diffusion model, demonstrating how graph Laplacian eigenvalues can determine temporal dynamics scales, and crucially validate this correspondence through comprehensive empirical analysis on real molecular dynamics trajectories showing quantitative spatial-temporal correlations across diverse molecular systems. Experimental results on challenging MD benchmarks, including MD17 and alanine dipeptide, demonstrate that GF-NODE achieves state-of-the-art accuracy while preserving essential geometrical features over extended simulations. These findings highlight the promise of bridging spectral decomposition with continuous-time modeling to improve the robustness and predictive power of MD simulations. Our implementation is publicly available at https://github.com/FrancoTSolis/GF-NODE-code.

PDF Details

AIJ Journal 2025 Journal Article

MATE: Masked optimal transport with dynamic selection for partial label graph learning

  • Yiyang Gu
  • Binqi Chen
  • Zihao Chen
  • Ziyue Qiao
  • Xiao Luo
  • Junyu Luo
  • Zhiping Xiao
  • Wei Ju

This paper investigates the problem of partial label graph learning, in which every graph is associated with a set of candidate labels. Previous methods for weakly supervised graph classification often provide pseudo-labels for graph samples that could be overconfident and biased towards the dominant classes, thus resulting in substantial error accumulation. In this paper, we introduce a new framework named Masked Optimal Transport with Dynamic Selection (MATE) for partial label graph learning, which improves the quality of graph assignments from the perspectives of class balancing and uncertainty mining. In particular, our MATE masks probabilities out of candidate sets and then adopts optimal transport to optimize the assignments without class biases. This design is based on the assumption that the true label distribution is class-balanced or nearly balanced, which is common in various training datasets and real-world scenarios. To further reduce potential noise, we propose a novel scoring metric termed partial energy discrepancy (PED) to evaluate the uncertainty of assignments, and then introduce a dynamic selection strategy that modifies the sample-specific thresholds via momentum updating. Finally, these samples are divided into three levels, i. e. , confident, less-confident, and unconfident and each group is trained separately in our collaborative optimization framework. Extensive experiments on various benchmarks demonstrate the superiority of our MATE compared to various state-of-the-art baselines.

Details DOI

IJCAI Conference 2025 Conference Paper

NeuBM: Mitigating Model Bias in Graph Neural Networks Through Neutral Input Calibration

  • Jiawei Gu
  • Ziyue Qiao
  • Xiao Luo

Graph Neural Networks (GNNs) have shown remarkable performance across various domains, yet they often struggle with model bias, particularly in the presence of class imbalance. This bias can lead to suboptimal performance and unfair predictions, especially for underrepresented classes. We introduce NeuBM (Neutral Bias Mitigation), a novel approach to mitigate model bias in GNNs through neutral input calibration. NeuBM leverages a dynamically updated neutral graph to estimate and correct the inherent biases of the model. By subtracting the logits obtained from the neutral graph from those of the input graph, NeuBM effectively recalibrates the model's predictions, reducing bias across different classes. Our method integrates seamlessly into existing GNN architectures and training procedures, requiring minimal computational overhead. Extensive experiments on multiple benchmark datasets demonstrate that NeuBM significantly improves the balanced accuracy and recall of minority classes, while maintaining strong overall performance. The effectiveness of NeuBM is particularly pronounced in scenarios with severe class imbalance and limited labeled data, where traditional methods often struggle. We provide theoretical insights into how NeuBM achieves bias mitigation, relating it to the concept of representation balancing. Our analysis reveals that NeuBM not only adjusts the final predictions but also influences the learning of balanced feature representations throughout the network.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy Supervision

  • Yiyang Gu
  • Bohan Wu
  • Qinghua Ran
  • Rong-Cheng Tu
  • Xiao Luo
  • Zhiping Xiao
  • Wei Ju
  • Dacheng Tao

This paper studies the problem of learning hash codes from noisy supervision, which is a practical yet challenging task. This problem is important in extensive real-world applications such as image retrieval and cross-modal retrieval. However, most of the existing methods focus on label denoising to address this problem, but ignore the geometric structure of the hash space, which is critical for learning stable hash codes. Towards this end, this paper proposes a novel framework named Semantic Geometry Shaping (SEGA) that explicitly refines the semantic geometry of hash space. Specifically, we first learn dynamic class prototypes as semantic anchors and cluster hash embeddings around these prototypes to keep structural stability. We then leverage both the energy of predicted distributions and structure-based divergence to estimate the uncertainty of instances and calibrate the supervision in a soft manner. Moreover, we introduce structure-aware interpolation to improve the class boundaries. To verify the effectiveness of our design, we give the theoretical analysis for the proposed framework. Experiments on a range of widely-used retrieval datasets justify the superiority of our SEGA over extensive strong baselines under noisy supervision.

PDF Details

NeurIPS Conference 2025 Conference Paper

SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding

  • Zhao Jin
  • Rong-Cheng Tu
  • Jingyi Liao
  • Wenhao Sun
  • Xiao Luo
  • Shunyu Liu
  • Dacheng Tao

3D Visual Grounding (3DVG) aims to localize target objects within a 3D scene based on natural language queries. To alleviate the reliance on costly 3D training data, recent studies have explored zero-shot 3DVG by leveraging the extensive knowledge and powerful reasoning capabilities of pre-trained LLMs and VLMs. However, existing paradigms tend to emphasize either spatial (3D-based) or semantic (2D-based) understanding, limiting their effectiveness in complex real-world applications. In this work, we introduce SPAZER — a VLM-driven agent that combines both modalities in a progressive reasoning framework. It first holistically analyzes the scene and produces a 3D rendering from the optimal viewpoint. Based on this, anchor-guided candidate screening is conducted to perform a coarse-level localization of potential objects. Furthermore, leveraging retrieved relevant 2D camera images, 3D-2D joint decision-making is efficiently performed to determine the best-matching object. By bridging spatial and semantic reasoning neural streams, SPAZER achieves robust zero-shot grounding without training on 3D-labeled data. Extensive experiments on ScanRefer and Nr3D benchmarks demonstrate that SPAZER significantly outperforms previous state-of-the-art zero-shot methods, achieving notable gains of $\mathbf{9. 0\}$% and $\mathbf{10. 9\}$% in accuracy.

PDF Details

AAAI Conference 2025 Conference Paper

TRACI: A Data-centric Approach for Multi-Domain Generalization on Graphs

  • Yusheng Zhao
  • Changhu Wang
  • Xiao Luo
  • Junyu Luo
  • Wei Ju
  • Zhiping Xiao
  • Ming Zhang

Graph neural networks (GNNs) have gained superior performance in graph-based prediction tasks with a variety of applications such as social analysis and drug discovery. Despite the remarkable progress, their performance often degrades on test graphs with distribution shifts. Existing domain adaptation methods rely on unlabeled test graphs during optimization, limiting their applicability to graphs in the wild. Towards this end, this paper studies the problem of multi-domain generalization on graphs, which utilizes multiple source graphs to learn a GNN with high performance on unseen target graphs. We propose a new approach named Topological Adversarial Learning with Prototypical Mixup (TRACI) to solve the problem. The fundamental principle behind our TRACI is to produce virtual adversarial and mixed graph samples from a data-centric view. In particular, TRACI enhances GNN generalization by employing a gradient-ascent strategy that considers both label prediction entropy and graph topology to craft challenging adversarial samples. Additionally, it generates domain-agnostic node representations by characterizing class-graph pair prototypes through latent distributions and applying multi-sample prototypical Mixup for distribution alignment across graphs. We further provide theoretical analysis showing that TRACI reduces the model's excess risk. Extensive experiments on various benchmark datasets demonstrate that TRACI outperforms state-of-the-art baselines, validating its effectiveness.

PDF Details DOI

YNIMG Journal 2024 Journal Article

Development and validation of a perivascular space segmentation method in multi-center datasets

  • Peiyu Huang
  • Lingyun Liu
  • Yao Zhang
  • Siyan Zhong
  • Peng Liu
  • Hui Hong
  • Shuyue Wang
  • Linyun Xie

BACKGROUND: Perivascular spaces (PVS) visible on magnetic resonance imaging (MRI) are significant markers associated with various neurological diseases. Although quantitative analysis of PVS may enhance sensitivity and improve consistency across studies, the field lacks a universally validated method for analyzing images from multi-center studies. METHODS: We annotated PVS on multi-center 3D T1-weighted (T1w) images acquired using scanners from three major vendors (Siemens, General Electric, and Philips). A neural network, mcPVS-Net (multi-center PVS segmentation network), was trained using data from 40 subjects and then tested in a separate cohort of 15 subjects. We assessed segmentation accuracy against ground truth masks tailored for each scanner vendor. Additionally, we evaluated the agreement between segmented PVS volumes and visual scores for each scanner. We also explored correlations between PVS volumes and various clinical factors such as age, hypertension, and white matter hyperintensities (WMH) in a larger sample of 1020 subjects. Furthermore, mcPVS-Net was applied to a new dataset comprising both T1w and T2-weighted (T2w) images from a United Imaging scanner to investigate if PVS volumes could discriminate between subjects with differing visual scores. We also compared the mcPVS-Net with a previously published method that segments PVS from T1 images. RESULTS: In the test dataset, mcPVS-Net achieved a mean DICE coefficient of 0.80, with an average Precision of 0.81 and Recall of 0.79, indicating good specificity and sensitivity. The segmented PVS volumes were significantly associated with visual scores in both the basal ganglia (r = 0.541, p < 0.001) and white matter regions (r = 0.706, p < 0.001), and PVS volumes were significantly different among subjects with varying visual scores. Segmentation performance was consistent across different scanner vendors. PVS volumes exhibited significant associations with age, hypertension, and WMH. In the United Imaging scanner dataset, PVS volumes showed good associations with PVS visual scores evaluated on either T1w or T2w images. Compared to a previously published method, mcPVS-Net showed a higher accuracy and improved PVS segmentation in the basal ganglia region. CONCLUSION: The mcPVS-Net demonstrated good accuracy for segmenting PVS from 3D T1w images. It may serve as a useful tool for future PVS research.

Details DOI

NeurIPS Conference 2024 Conference Paper

EGODE: An Event-attended Graph ODE Framework for Modeling Rigid Dynamics

  • Jingyang Yuan
  • Gongbo Sun
  • Zhiping Xiao
  • Hang Zhou
  • Xiao Luo
  • Junyu Luo
  • Yusheng Zhao
  • Wei Ju

This paper studies the problem of rigid dynamics modeling, which has a wide range of applications in robotics, graphics, and mechanical design. The problem is partly solved by graph neural network (GNN) simulators. However, these approaches cannot effectively handle the relationship between intrinsic continuity and instantaneous changes in rigid dynamics. Moreover, they usually neglect hierarchical structures across mesh nodes and objects in systems. In this paper, we propose a novel approach named Event-attend Graph ODE (EGODE) for effective rigid dynamics modeling. In particular, we describe the rigid system using both mesh node representations and object representations. To model continuous dynamics across hierarchical structures, we use a coupled graph ODE framework for the evolution of both types of representations over a long period. In addition, to capture instantaneous changes during the collision, we introduce an event module, which can effectively estimate the occurrence of the collision and update the states of both mesh node and object representations during evolution. Extensive experiments on a range of benchmark datasets validate the superiority of the proposed EGODE compared to various state-of-the-art baselines. The source code can be found at https: //github. com/yuanjypku/EGODE.

PDF Details DOI

YNIMG Journal 2024 Journal Article

Higher intracranial arterial pulsatility is associated with presumed imaging markers of the glymphatic system: An explorative study

  • Linyun Xie
  • Yao Zhang
  • Hui Hong
  • Shan Xu
  • Lei Cui
  • Shuyue Wang
  • Jixuan Li
  • Lingyun Liu

BACKGROUND: Arterial pulsation has been suggested as a key driver of paravascular cerebrospinal fluid flow, which is the foundation of glymphatic clearance. However, whether intracranial arterial pulsatility is associated with glymphatic markers in humans has not yet been studied. METHODS: , and the presumed glymphatic markers, controlling for related covariates. RESULTS: in the ICA C2 (β, -0.239, p, 0.041) and C7 segments (β, -0.238, p, 0.037). CONCLUSIONS: Intracranial arterial pulsatility was associated with presumed neuroimaging markers of the glymphatic system, but the results were not consistent across different markers. Further studies are warranted to confirm these findings.

Details DOI

AAAI Conference 2024 Conference Paper

LION: Implicit Vision Prompt Tuning

  • Haixin Wang
  • Jianlong Chang
  • Yihang Zhai
  • Xiao Luo
  • Jinan Sun
  • Zhouchen Lin
  • Qi Tian

Despite recent promising performances across a range of vision tasks, vision Transformers still have an issue of high computational costs. Recently, vision prompt learning has provided an economical solution to this problem without fine-tuning the whole large-scale model. However, the efficiency and effectiveness of existing models are still far from satisfactory due to the parameter cost of extensive prompt blocks and tricky prompt framework designs. In this paper, we propose a light-weight prompt framework named impLicit vIsion prOmpt tuNing (LION), which is motivated by deep implicit models with stable low memory costs for various complex tasks. In particular, we merely insect two equilibrium implicit layers in two ends of the pre-trained backbone with parameters frozen. Moreover, according to the lottery hypothesis, we further prune the parameters to relieve the computation burden in implicit layers. Various experiments have validated that our LION obtains promising performances on a wide range of datasets. Most importantly, LION reduces up to 11.5 % of training parameter numbers while obtaining higher performance than the state-of-the-art VPT, especially under challenging scenes. Furthermore, we find that our proposed LION has an excellent generalization performance, making it an easy way to boost transfer learning in the future.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling

  • Zijie Huang
  • Wanjia Zhao
  • Jingdong Gao
  • Ziniu Hu
  • Xiao Luo
  • Yadi Cao
  • Yuanzhou Chen
  • Yizhou Sun

Learning complex physical dynamics purely from data is challenging due to the intrinsic properties of systems to be satisfied. Incorporating physics-informed priors, such as in Hamiltonian Neural Networks (HNNs), achieves high-precision modeling for energy-conservative systems. However, real-world systems often deviate from strict energy conservation and follow different physical priors. To address this, we present a framework that achieves high-precision modeling for a wide range of dynamical systems from the numerical aspect, by enforcing Time-Reversal Symmetry (TRS) via a novel regularization term. It helps preserve energies for conservative systems while serving as a strong inductive bias for non-conservative, reversible systems. While TRS is a domain-specific physical prior, we present the first theoretical proof that TRS loss can universally improve modeling accuracy by minimizing higher-order Taylor terms in ODE integration, which is numerically beneficial to various systems regardless of their properties, even for irreversible systems. By integrating the TRS loss within neural ordinary differential equation models, the proposed model TREAT demonstrates superior performance on diverse physical systems. It achieves a significant 11. 5% MSE improvement in a challenging chaotic triple-pendulum scenario, underscoring TREAT’s broad applicability and effectiveness.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

PURE: Prompt Evolution with Graph ODE for Out-of-distribution Fluid Dynamics Modeling

  • Hao Wu
  • Changhu Wang
  • Fan Xu
  • Jinbao Xue
  • Chong Chen
  • Xian-Sheng Hua
  • Xiao Luo

This work studies the problem of out-of-distribution fluid dynamics modeling. Previous works usually design effective neural operators to learn from mesh-based data structures. However, in real-world applications, they would suffer from distribution shifts from the variance of system parameters and temporal evolution of the dynamical system. In this paper, we propose a novel approach named \underline{P}rompt Evol\underline{u}tion with G\underline{r}aph OD\underline{E} (\method{}) for out-of-distribution fluid dynamics modeling. The core of our \method{} is to learn time-evolving prompts using a graph ODE to adapt spatio-temporal forecasting models to different scenarios. In particular, our \method{} first learns from historical observations and system parameters in the frequency domain to explore multi-view context information, which could effectively initialize prompt embeddings. More importantly, we incorporate the interpolation of observation sequences into a graph ODE, which can capture the temporal evolution of prompt embeddings for model adaptation. These time-evolving prompt embeddings are then incorporated into basic forecasting models to overcome temporal distribution shifts. We also minimize the mutual information between prompt embeddings and observation embeddings to enhance the robustness of our model to different distributions. Extensive experiments on various benchmark datasets validate the superiority of the proposed \method{} in comparison to various baselines.

PDF Details DOI

IJCAI Conference 2024 Conference Paper

Rank and Align: Towards Effective Source-free Graph Domain Adaptation

  • Junyu Luo
  • Zhiping Xiao
  • Yifan Wang
  • Xiao Luo
  • Jingyang Yuan
  • Wei Ju
  • Langechuan Liu
  • Ming Zhang

Graph neural networks (GNNs) have achieved impressive performance in graph domain adaptation. However, extensive source graphs could be unavailable in real-world scenarios due to privacy and storage concerns. To this end, we investigate an underexplored yet practical problem of source-free graph domain adaptation, which transfers knowledge from source models instead of source graphs to a target domain. To solve this problem, we introduce a novel GNN-based approach called Rank and Align (RNA), which ranks graph similarities with spectral seriation for robust semantics learning, and aligns inharmonic graphs with harmonic graphs which close to the source domain for subgraph extraction. In particular, to overcome label scarcity, we employ the spectral seriation algorithm to infer the robust pairwise rankings, which can guide semantic learning using a similarity learning objective. To depict distribution shifts, we utilize spectral clustering and the silhouette coefficient to detect harmonic graphs, which the source model can easily classify. To reduce potential domain discrepancy, we extract domain-invariant subgraphs from inharmonic graphs by an adversarial edge sampling process, which guides the invariant learning of GNNs. Extensive experiments on several benchmark datasets demonstrate the effectiveness of our proposed RNA.

PDF Details DOI

NeurIPS Conference 2024 Conference Paper

Semi-supervised Knowledge Transfer Across Multi-omic Single-cell Data

  • Fan Zhang
  • Tianyu Liu
  • Zihao Chen
  • Xiaojiang Peng
  • Chong Chen
  • Xian-Sheng Hua
  • Xiao Luo
  • Hongyu Zhao

Knowledge transfer between multi-omic single-cell data aims to effectively transfer cell types from scRNA-seq data to unannotated scATAC-seq data. Several approaches aim to reduce the heterogeneity of multi-omic data while maintaining the discriminability of cell types with extensive annotated data. However, in reality, the cost of collecting both a large amount of labeled scRNA-seq data and scATAC-seq data is expensive. Therefore, this paper explores a practical yet underexplored problem of knowledge transfer across multi-omic single-cell data under cell type scarcity. To address this problem, we propose a semi-supervised knowledge transfer framework named Dual label scArcity elimiNation with Cross-omic multi-samplE Mixup (DANCE). To overcome the label scarcity in scRNA-seq data, we generate pseudo-labels based on optimal transport and merge them into the labeled scRNA-seq data. Moreover, we adopt a divide-and-conquer strategy which divides the scATAC-seq data into source-like and target-specific data. For source-like samples, we employ consistency regularization with random perturbations while for target-specific samples, we select a few candidate labels and progressively eliminate incorrect cell types from the label set for additional supervision. Next, we generate virtual scRNA-seq samples with multi-sample Mixup based on the class-wise similarity to reduce cell heterogeneity. Extensive experiments on many benchmark datasets suggest the superiority of our DANCE over a series of state-of-the-art methods.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

CARE: Modeling Interacting Dynamics Under Temporal Environmental Variation

  • Xiao Luo
  • Haixin Wang
  • Zijie Huang
  • Huiyu Jiang
  • Abhijeet Gangan
  • Song Jiang
  • Yizhou Sun

Modeling interacting dynamical systems, such as fluid dynamics and intermolecular interactions, is a fundamental research problem for understanding and simulating complex real-world systems. Many of these systems can be naturally represented by dynamic graphs, and graph neural network-based approaches have been proposed and shown promising performance. However, most of these approaches assume the underlying dynamics does not change over time, which is unfortunately untrue. For example, a molecular dynamics can be affected by the environment temperature over the time. In this paper, we take an attempt to provide a probabilistic view for time-varying dynamics and propose a model Context-attended Graph ODE (CARE) for modeling time-varying interacting dynamical systems. In our CARE, we explicitly use a context variable to model time-varying environment and construct an encoder to initialize the context variable from historical trajectories. Furthermore, we employ a neural ODE model to depict the dynamic evolution of the context variable inferred from system states. This context variable is incorporated into a coupled ODE to simultaneously drive the evolution of systems. Comprehensive experiments on four datasets demonstrate the effectiveness of our proposed CARE compared with several state-of-the-art approaches.

PDF Details

AAAI Conference 2023 Conference Paper

GLCC: A General Framework for Graph-Level Clustering

  • Wei Ju
  • Yiyang Gu
  • Binqi Chen
  • Gongbo Sun
  • Yifang Qin
  • Xingyuming Liu
  • Xiao Luo
  • Ming Zhang

This paper studies the problem of graph-level clustering, which is a novel yet challenging task. This problem is critical in a variety of real-world applications such as protein clustering and genome analysis in bioinformatics. Recent years have witnessed the success of deep clustering coupled with graph neural networks (GNNs). However, existing methods focus on clustering among nodes given a single graph, while exploring clustering on multiple graphs is still under-explored. In this paper, we propose a general graph-level clustering framework named Graph-Level Contrastive Clustering (GLCC) given multiple graphs. Specifically, GLCC first constructs an adaptive affinity graph to explore instance- and cluster-level contrastive learning (CL). Instance-level CL leverages graph Laplacian based contrastive loss to learn clustering-friendly representations while cluster-level CL captures discriminative cluster representations incorporating neighbor information of each sample. Moreover, we utilize neighbor-aware pseudo-labels to reward the optimization of representation learning. The two steps can be alternatively trained to collaborate and benefit each other. Experiments on a range of well-known datasets demonstrate the superiority of our proposed GLCC over competitive baselines.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

IDEA: An Invariant Perspective for Efficient Domain Adaptive Image Retrieval

  • Haixin Wang
  • Hao Wu
  • Jinan Sun
  • Shikun Zhang
  • Chong Chen
  • Xian-Sheng Hua
  • Xiao Luo

In this paper, we investigate the problem of unsupervised domain adaptive hashing, which leverage knowledge from a label-rich source domain to expedite learning to hash on a label-scarce target domain. Although numerous existing approaches attempt to incorporate transfer learning techniques into deep hashing frameworks, they often neglect the essential invariance for adequate alignment between these two domains. Worse yet, these methods fail to distinguish between causal and non-causal effects embedded in images, rendering cross-domain retrieval ineffective. To address these challenges, we propose an Invariance-acquired Domain AdaptivE HAshing (IDEA) model. Our IDEA first decomposes each image into a causal feature representing label information, and a non-causal feature indicating domain information. Subsequently, we generate discriminative hash codes using causal features with consistency learning on both source and target domains. More importantly, we employ a generative model for synthetic samples to simulate the intervention of various non-causal effects, ultimately minimizing their impact on hash codes for domain invariance. Comprehensive experiments conducted on benchmark datasets validate the superior performance of our IDEA compared to a variety of competitive baselines.

PDF Details

NeurIPS Conference 2023 Conference Paper

Parameter-efficient Tuning of Large-scale Multimodal Foundation Model

  • Haixin Wang
  • Xinlong Yang
  • Jianlong Chang
  • Dian Jin
  • Jinan Sun
  • Shikun Zhang
  • Xiao Luo
  • Qi Tian

Driven by the progress of large-scale pre-training, parameter-efficient transfer learning has gained immense popularity across different subfields of Artificial Intelligence. The core is to adapt the model to downstream tasks with only a small set of parameters. Recently, researchers have leveraged such proven techniques in multimodal tasks and achieve promising results. However, two critical issues remain unresolved: how to further reduce the complexity with lightweight design and how to boost alignment between modalities under extremely low parameters. In this paper, we propose A gracefUl pRompt framewOrk for cRoss-modal trAnsfer (AURORA) to overcome these challenges. Considering the redundancy in existing architectures, we first utilize the mode approximation to generate 0. 1M trainable parameters to implement the multimodal parameter-efficient tuning, which explores the low intrinsic dimension with only 0. 04% parameters of the pre-trained model. Then, for better modality alignment, we propose the Informative Context Enhancement and Gated Query Transformation module under extremely few parameters scenes. A thorough evaluation on six cross-modal benchmarks shows that it not only outperforms the state-of-the-art but even outperforms the full fine-tuning approach. Our code is available at: https: //github. com/WillDreamer/Aurora.

PDF Details

TMLR Journal 2023 Journal Article

RIGNN: A Rationale Perspective for Semi-supervised Open-world Graph Classification

  • Xiao Luo
  • Yusheng Zhao
  • Zhengyang Mao
  • Yifang Qin
  • Wei Ju
  • Ming Zhang
  • Yizhou Sun

Graph classification has gained growing attention in the graph machine learning community and a variety of semi-supervised methods have been developed to reduce the high cost of annotation. They usually combine graph neural networks (GNNs) and extensive semi-supervised techniques such as knowledge distillation. However, they adhere to the close-set assumption that unlabeled graphs all belong to known classes, limiting their applications in the real world. This paper goes further, investigating a practical problem of semi-supervised open-world graph classification where these unlabeled graph data could come from unseen classes. A novel approach named Rationale-Informed GNN (RIGNN) is proposed, which takes a rationale view to detect components containing the most information related to the label space and classify unlabeled graphs into a known class or an unseen class. In particular, RIGNN contains a relational detector and a feature extractor to produce effective rationale features, which maximize the mutual information with label information and exhibit sufficient disentanglement with non-rationale elements. Furthermore, we construct a graph-of-graph based on geometrical relationships, which gives instructions on enhancing rationale representations. In virtue of effective rationale representations, we can provide accurate and balanced predictions for unlabeled graphs. An extension is also made to accomplish effective open-set graph classification. We verify our proposed methods on four benchmark datasets in various settings and experimental results reveal the effectiveness of our proposed RIGNN compared with state-of-the-art methods.

PDF Details

IJCAI Conference 2023 Conference Paper

Semi-supervised Domain Adaptation in Graph Transfer Learning

  • Ziyue Qiao
  • Xiao Luo
  • Meng Xiao
  • Hao Dong
  • Yuanchun Zhou
  • Hui Xiong

As a specific case of graph transfer learning, unsupervised domain adaptation on graphs aims for knowledge transfer from label-rich source graphs to unlabeled target graphs. However, graphs with topology and attributes usually have considerable cross-domain disparity and there are numerous real-world scenarios where merely a subset of nodes are labeled in the source graph. This imposes critical challenges on graph transfer learning due to serious domain shifts and label scarcity. To address these challenges, we propose a method named Semi-supervised Graph Domain Adaptation (SGDA). To deal with the domain shift, we add adaptive shift parameters to each of the source nodes, which are trained in an adversarial manner to align the cross-domain distributions of node embedding. Thus, the node classifier trained on labeled source nodes can be transferred to the target nodes. Moreover, to address the label scarcity, we propose pseudo-labeling on unlabeled nodes, which improves classification on the target graph via measuring the posterior influence of nodes based on their relative position to the class centroids. Finally, extensive experiments on a range of publicly accessible datasets validate the effectiveness of our proposed SGDA in different experimental settings.

PDF Details DOI

TMLR Journal 2023 Journal Article

Zero-shot Node Classification with Graph Contrastive Embedding Network

  • Wei Ju
  • Yifang Qin
  • Siyu Yi
  • Zhengyang Mao
  • Kangjie Zheng
  • Luchen Liu
  • Xiao Luo
  • Ming Zhang

This paper studies zero-shot node classification, which aims to predict new classes (i.e., unseen classes) of nodes in a graph. This problem is challenging yet promising in a variety of real-world applications such as social analysis and bioinformatics. The key of zero-shot node classification is to enable the knowledge transfer of nodes from training classes to unseen classes. However, existing methods typically ignore the dependencies between nodes and classes, and fail to be organically integrated in a united way. In this paper, we present a novel framework called the Graph Contrastive Embedding Network (GraphCEN) for zero-shot node classification. Specifically, GraphCEN first constructs an affinity graph to model the relations between the classes. Then the node- and class-level contrastive learning (CL) are proposed to jointly learn node embeddings and class assignments in an end-to-end manner. The two-level CL can be optimized to mutually enhance each other. Extensive experiments indicate that our GraphCEN significantly outperforms the state-of-the-art approaches on multiple challenging benchmark datasets.

PDF Details

JBHI Journal 2022 Journal Article

A Deep Language Model for Symptom Extraction From Clinical Text and its Application to Extract COVID-19 Symptoms From Social Media

  • Xiao Luo
  • Priyanka Gandhi
  • Susan Storey
  • Kun Huang

Patients experience various symptoms when they haveeither acute or chronic diseases or undergo some treatments for diseases. Symptoms are often indicators of the severity of the disease and the need for hospitalization. Symptoms are often described in free text written as clinical notes in the Electronic Health Records (EHR) and are not integrated with other clinical factors for disease prediction and healthcare outcome management. In this research, we propose a novel deep language model to extract patient-reported symptoms from clinical text. The deep language model integrates syntactic and semantic analysis for symptom extraction and identifies the actual symptoms reported by patients and conditional or negation symptoms. The deep language model can extract both complex and straightforward symptom expressions. We used a real-world clinical notes dataset to evaluate our model and demonstrated that our model achieves superior performance compared to three other state-of-the-art symptom extraction models. We extensively analyzed our model to illustrate its effectiveness by examining each component’s contribution to the model. Finally, we applied our model on a COVID-19 tweets data set to extract COVID-19 symptoms. The results show that our model can identify all the symptoms suggested by the Center for Disease Control (CDC) ahead of their timeline and many rare symptoms.

Details DOI

YNIMG Journal 2022 Journal Article

Altered brain iron depositions from aging to Parkinson's disease and Alzheimer's disease: A quantitative susceptibility mapping study

  • Xiaojun Guan
  • Tao Guo
  • Cheng Zhou
  • Jingjing Wu
  • Qingze Zeng
  • Kaicheng Li
  • Xiao Luo
  • Xueqin Bai

Brain iron deposition is a promising marker for human brain health, providing insightful information for understanding aging as well as neurodegenerations, e. g. , Parkinson's disease (PD) and Alzheimer's disease (AD). To comprehensively evaluate brain iron deposition along with aging, PD-related neurodegeneration, from prodromal PD (pPD) to clinical PD (cPD), and AD-related neurodegeneration, from mild cognitive impairment (MCI) to AD, a total of 726 participants from July 2013 to December 2020, including 100 young adults, 189 old adults, 184 pPD, 171 cPD, 31 MCI and 51 AD patients, were included. Quantitative susceptibility mapping data were acquired and used to quantify regional magnetic susceptibility, and the resulting spatial standard deviations were recorded. A general linear model was applied to perform the inter-group comparison. As a result, relative to young adults, old adults showed significantly higher iron deposition with higher spatial variation in all of the subcortical nuclei (p < 0. 01). pPD showed a high spatial variation of iron distribution in the subcortical nuclei except for substantia nigra (SN); and iron deposition in SN and red nucleus (RN) were progressively increased from pPD to cPD (p < 0. 01). AD showed significantly higher iron deposition in caudate and putamen with higher spatial variation compared with old adults, pPD and cPD (p < 0. 01), and significant iron deposition in SN compared with old adults (p < 0. 01). Also, linear regression models had significances in predicting motor score in pPD and cPD (Rmean = 0. 443, Ppermutation = 0. 001) and cognition score in MCI and AD (Rmean = 0. 243, Ppermutation = 0. 037). In conclusion, progressive iron deposition in the SN and RN may characterize PD-related neurodegeneration, namely aging to cPD through pPD. On the other hand, extreme iron deposition in the caudate and putamen may characterize AD-related neurodegeneration.

Details DOI

NeurIPS Conference 2022 Conference Paper

Expediting Large-Scale Vision Transformer for Dense Prediction without Fine-tuning

  • Weicong Liang
  • Yuhui Yuan
  • Henghui Ding
  • Xiao Luo
  • Weihong Lin
  • Ding Jia
  • Zheng Zhang
  • Chao Zhang

Vision transformers have recently achieved competitive results across various vision tasks but still suffer from heavy computation costs when processing a large number of tokens. Many advanced approaches have been developed to reduce the total number of tokens in the large-scale vision transformers, especially for image classification tasks. Typically, they select a small group of essential tokens according to their relevance with the [\texttt{class}] token, then fine-tune the weights of the vision transformer. Such fine-tuning is less practical for dense prediction due to the much heavier computation and GPU memory cost than image classification. In this paper, we focus on a more challenging problem, \ie, accelerating large-scale vision transformers for dense prediction without any additional re-training or fine-tuning. In response to the fact that high-resolution representations are necessary for dense prediction, we present two non-parametric operators, a \emph{token clustering layer} to decrease the number of tokens and a \emph{token reconstruction layer} to increase the number of tokens. The following steps are performed to achieve this: (i) we use the token clustering layer to cluster the neighboring tokens together, resulting in low-resolution representations that maintain the spatial structures; (ii) we apply the following transformer layers only to these low-resolution representations or clustered tokens; and (iii) we use the token reconstruction layer to re-create the high-resolution representations from the refined low-resolution representations. The results obtained by our method are promising on five dense prediction tasks including object detection, semantic segmentation, panoptic segmentation, instance segmentation, and depth estimation. Accordingly, our method accelerates $40\%\uparrow$ FPS and saves $30\%\downarrow$ GFLOPs of ``Segmenter+ViT-L/$16$'' while maintaining $99. 5\%$ of the performance on ADE$20$K without fine-tuning the official weights.

PDF Details

IJCAI Conference 2022 Conference Paper

Improved Deep Unsupervised Hashing with Fine-grained Semantic Similarity Mining for Multi-Label Image Retrieval

  • Zeyu Ma
  • Xiao Luo
  • Yingjie Chen
  • Mixiao Hou
  • Jinxing Li
  • Minghua Deng
  • Guangming Lu

In this paper, we study deep unsupervised hashing, a critical problem for approximate nearest neighbor research. Most recent methods solve this problem by semantic similarity reconstruction for guiding hashing network learning or contrastive learning of hash codes. However, in multi-label scenarios, these methods usually either generate an inaccurate similarity matrix without reflection of similarity ranking or suffer from the violation of the underlying assumption in contrastive learning, resulting in limited retrieval performance. To tackle this issue, we propose a novel method termed HAMAN, which explores semantics from a fine-grained view to enhance the ability of multi-label image retrieval. In particular, we reconstruct the pairwise similarity structure by matching fine-grained patch features generated by the pre-trained neural network, serving as reliable guidance for similarity preserving of hash codes. Moreover, a novel conditional contrastive learning on hash codes is proposed to adopt self-supervised learning in multi-label scenarios. According to extensive experiments on three multi-label datasets, the proposed method outperforms a broad range of state-of-the-art methods.

PDF Details DOI

YNICL Journal 2022 Journal Article

Increased functional connectivity between nucleus basalis of Meynert and amygdala in cognitively intact elderly along the Alzheimer’s continuum

  • Qingze Zeng
  • Tiantian Qiu
  • Kaicheng Li
  • Xiao Luo
  • Shuyue Wang
  • Xiaopei Xu
  • Xiaocao Liu
  • Luwei Hong

BACKGROUND: A growing body of research reported the degeneration of the basal forebrain (BF) cholinergic system in the early course of Alzheimer's disease (AD). However, functional changes of the BF in asymptomatic individuals along the Alzheimer's continuum remain unclear. METHODS: A total of 229 cognitively intact participants were included from the Alzheimer's Disease Neuroimaging Initiative dataset and further divided into four groups based on the "A/T" profile using amyloid and tau positron emission tomography (PET). All A-T+ subjects were excluded. One hundred and seventy-three subjects along the Alzheimer's continuum (A-T-, A+ T-, A+ T+) were used for further study. The seed-based functional connectivity (FC) maps of the BF subregions (Ch1-3 and Ch4 [nucleus basalis of Meynert, NBM]) with whole-brain voxels were constructed. Analyses of covariance to detect the between-group differences and to further investigated the relations between FC values and AD biomarkers or cognition. RESULTS: We found increased FC between right Ch4 and bilateral amygdala among three groups, and the FC value could well distinguish between the A-T- group and the Alzheimer's continuum groups. Furthermore, increased FC between the Ch4 and amygdala was associated with higher pathological burden reflected by amyloid and tau PET in the entire population as well as better logistic memory function in A + T+ group. CONCLUSION: Our study demonstrated the NBM functional connectivity increased in cognitively normal elderly along the Alzheimer's continuum, which indicated a potential compensatory mechanism to counteract pathological changes in AD and maintain intact cognitive function.

Details DOI

YNICL Journal 2022 Journal Article

Reduced coupling between the global blood-oxygen-level-dependent signal and cerebrospinal fluid inflow is associated with the severity of small vessel disease

  • Yao Zhang
  • Ruiting Zhang
  • Shuyue Wang
  • Hui Hong
  • Yeerfan Jiaerken
  • Kaicheng Li
  • Qingze Zeng
  • Xiao Luo

BACKGROUND: Small vessel disease (SVD) is highly prevalent in the elderly and associated with an increased risk of dementia and stroke. SVD may have disturbed cerebrospinal fluid (CSF) flow, which can compromise waste clearance and accelerate disease progression. METHODS: We retrospectively included 146 SVD patients from a prospectively collected dataset, with one- or two-year follow-up data in 61 patients. The coupling strength between the global blood-oxygen-level-dependent (gBOLD) signal and CSF inflow was used to reflect CSF dynamics. We performed regression analyses to investigate the association between the gBOLD-CSF coupling index and the severity of SVD and vascular risk factors. Longitudinal analysis was carried out to investigate causal relationships. RESULTS: Patients with severe SVD had significantly decreased gBOLD-CSF coupling (β = -0.180, p = 0.032). Dilation of perivascular spaces in the basal ganglia area (β = -0.172, p = 0.033) and diabetes (β = -0.204, p = 0.014) were associated with reduced gBOLD-CSF coupling. In longitudinal analyses, diabetes was associated with faster decline in gBOLD-CSF coupling (β = 0.20, p = 0.039), while perivascular space (PVS) dilation in the centrum semiovale showed a opposite relationship (β = -0.20, p = 0.041). The gBOLD-CSF coupling could not predict SVD progression. CONCLUSION: Altered CSF flow is associated with the severity of SVD.

Details DOI

IJCAI Conference 2022 Conference Paper

TGNN: A Joint Semi-supervised Framework for Graph-level Classification

  • Wei Ju
  • Xiao Luo
  • Meng Qu
  • Yifan Wang
  • Chong Chen
  • Minghua Deng
  • Xian-Sheng Hua
  • Ming Zhang

This paper studies semi-supervised graph classification, a crucial task with a wide range of applications in social network analysis and bioinformatics. Recent works typically adopt graph neural networks to learn graph-level representations for classification, failing to explicitly leverage features derived from graph topology (e. g. , paths). Moreover, when labeled data is scarce, these methods are far from satisfactory due to their insufficient topology exploration of unlabeled data. We address the challenge by proposing a novel semi-supervised framework called Twin Graph Neural Network (TGNN). To explore graph structural information from complementary views, our TGNN has a message passing module and a graph kernel module. To fully utilize unlabeled data, for each module, we calculate the similarity of each unlabeled graph to other labeled graphs in the memory bank and our consistency loss encourages consistency between two similarity distributions in different embedding spaces. The two twin modules collaborate with each other by exchanging instance similarity knowledge to fully explore the structure information of both labeled and unlabeled data. We evaluate our TGNN on various public datasets and show that it achieves strong performance.

PDF Details DOI

JBHI Journal 2021 Journal Article

A Computational Framework to Analyze the Associations Between Symptoms and Cancer Patient Attributes Post Chemotherapy Using EHR Data

  • Xiao Luo
  • Priyanka Gandhi
  • Susan Storey
  • Zuoyi Zhang
  • Zhi Han
  • Kun Huang

Patients with cancer, such as breast and colorectal cancer, often experience different symptoms post-chemotherapy. The symptoms could be fatigue, gastrointestinal (nausea, vomiting, lack of appetite), psychoneurological symptoms (depressive symptoms, anxiety), or other types. Previous research focused on understanding the symptoms using survey data. In this research, we propose to utilize the data within the Electronic Health Record (EHR). A computational framework is developed to use a natural language processing (NLP) pipeline to extract the clinician-documented symptoms from clinical notes. Then, a patient clustering method is based on the symptom severity levels to group the patient in clusters. The association rule mining is used to analyze the associations between symptoms and patient attributes (smoking history, number of comorbidities, diabetes status, age at diagnosis) in the patient clusters. The results show that the various symptom types and severity levels have different associations between breast and colorectal cancers and different timeframes post-chemotherapy. The results also show that patients with breast or colorectal cancers, who smoke and have severe fatigue, likely have severe gastrointestinal symptoms six months after the chemotherapy. Our framework can be generalized to analyze symptoms or symptom clusters of other chronic diseases where symptom management is critical.

Details DOI

IJCAI Conference 2021 Conference Paper

CIMON: Towards High-quality Hash Codes

  • Xiao Luo
  • Daqing Wu
  • Zeyu Ma
  • Chong Chen
  • Minghua Deng
  • Jinwen Ma
  • Zhongming Jin
  • Jianqiang Huang

Recently, hashing is widely used in approximate nearest neighbor search for its storage and computational efficiency. Most of the unsupervised hashing methods learn to map images into semantic similarity-preserving hash codes by constructing local semantic similarity structure from the pre-trained model as the guiding information, i. e. , treating each point pair similar if their distance is small in feature space. However, due to the inefficient representation ability of the pre-trained model, many false positives and negatives in local semantic similarity will be introduced and lead to error propagation during the hash code learning. Moreover, few of the methods consider the robustness of models, which will cause instability of hash codes to disturbance. In this paper, we propose a new method named Comprehensive sImilarity Mining and cOnsistency learNing (CIMON). First, we use global refinement and similarity statistical distribution to obtain reliable and smooth guidance. Second, both semantic and contrastive consistency learning are introduced to derive both disturb-invariant and discriminative hash codes. Extensive experiments on several benchmark datasets show that the proposed method outperforms a wide range of state-of-the-art methods in both retrieval performance and robustness.

PDF Details DOI

YNICL Journal 2020 Journal Article

Increased thalamic volume and decreased thalamo-precuneus functional connectivity are associated with smoking relapse

  • Chao Wang
  • Shuyue Wang
  • Zhujing Shen
  • Wei Qian
  • Yeerfan Jiaerken
  • Xiao Luo
  • Kaicheng Li
  • Qingze Zeng

The thalamus, with the highest density of nicotinic acetylcholine receptor (nAChR) in the brain, plays a central role in thalamo-cortical circuits that are implicated in nicotine addiction. However, little is known about whether the thalamo-cortical circuits are potentially predictive of smoking relapse. In the current study, a total of 125 participants (84 treatment-seeking male smokers and 41 age-matched male nonsmokers) were recruited. Structural and functional magnetic resonance images (MRI) were acquired from all participants. After a 12-week smoking cessation treatment with varenicline, the smokers were then divided into relapsers (n = 54) and nonrelapsers (n = 30). Then, we compared thalamic volume and seed-based thalamo-cortical resting state functional connectivity (rsFC) prior to the cessation treatment among relapsers, nonrelapsers and nonsmokers to investigate the associations between thalamic structure/function and smoking relapse. Increased thalamic volume was detected in smokers relative to nonsmokers, and in relapsers relative to nonrelapsers, especially on the left side. Moreover, decreased left thalamo-precuneus rsFC was detected in relapsers relative to nonrelapsers. Additionally, a logistic regression analysis showed that the thalamic volume and thalamo-precuneus rsFC predicted smoking relapse with an accuracy of 75.7%. These novel findings indicate that increased thalamic volume and decreased thalamo-precuneus rsFC are associated with smoking relapse, and these thalamic measures may be used to predict treatment efficacy of nicotine addiction and serve as a potential biomarker for personalized medicine.

Details DOI

YNICL Journal 2019 Journal Article

Gray matter structural covariance networks changes along the Alzheimer's disease continuum

  • Kaicheng Li
  • Xiao Luo
  • Qingze Zeng
  • Peiyu Huang
  • Zhujing Shen
  • Xiaojun Xu
  • Jingjing Xu
  • Chao Wang

Alzheimer's disease (AD) has a long neuropathological accumulation phase before the onset of dementia. Such AD neuropathological deposition between neurons impairs the synaptic communication, resulting in networks disorganization. Our study aimed to explore the evolution patterns of gray matter structural covariance networks (SCNs) along AD continuum. Based on the AT(N) (i. e. , Amyloid/Tau/Neurodegeneration) pathological classification system, we classified subjects into four groups using cerebrospinal fluid amyloid-beta1–42 (A) and phosphorylated tau protein181 (T). We identified 101 subjects with normal AD biomarkers (A-T-), 40 subjects with Alzheimer's pathologic change (A + T−), 101 subjects with biological AD (A + T+) and 91 AD with dementia (demented subjects with A + T+). We used four regions of interest to anchor default mode network (DMN, medial temporal subsystem and midline core subsystem), salience network (SN) and executive control network (ECN). Finally, we used a multi-regression model-based linear-interaction analysis to assess the SCN changes. Along the disease progression, DMN and SN showed increased structural association at the early stage while decreased structural association at the late stage. Moreover, ECN showed progressively increased structural association as AD neuropathological profiles progress. In conclusion, this study found the dynamic trajectory of SCNs changes along the AD continuum and support the network disconnection hypothesis underlying AD neuropathological progression. Further, SCN may potentially serve as an effective AD biomarker.

Details DOI
v2026.09.13