Author name cluster

Wei Zhu

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.

17 papers

2 author rows

EAAI Journal 2025 Journal Article

A communicability-driven expert influence model for large-scale group decision-making based on complex network theory

Fenglan Sun
Yuteng Yi
Wei Zhu
Jürgen Kurths

This paper proposes a novel large-scale group decision-making (LSGDM) framework based on complex network theory. First, by enhancing the clustering efficiency of the Louvain algorithm through complex network theory, this framework enables community classification of a large-scale expert group, thereby reduce the complexity of the expert network and improve decision-making efficiency. Second, a novel communicability-driven expert influence identification model within expert social networks is designed, and a new consensus feedback mechanism is proposed. This approach comprehensively considers both the individual influence of experts and the impact of their interactions to guide consensus-reaching, which can accurately reflect the actual flow of information within the network. Third, by extending the Best–Worst Method and Shannon Entropy Method to the context of fuzzy information, a balance between subjectivity and objectivity is obtained, which can make more accurate and interpretable decision results. The proposed method is validated through a case study on green material selection. Moreover, its superiority is further demonstrated through comparative experiments. The results show that our method demonstrates a 9. 89% reduction in opinion revision costs with accelerated consensus-reaching efficiency.

Details DOI

ECAI Conference 2025 Conference Paper

CorrMoE: Mixture of Experts with De-Stylization Learning for Cross-Scene and Cross-Domain Correspondence Pruning

Peiwen Xia
Tangfei Liao
Wei Zhu
Danhuai Zhao
Jianjun Ke
Kaihao Zhang
Tong Lu 0002
Tao Wang 0052

Establishing reliable correspondences between image pairs is a fundamental task in computer vision, underpinning applications such as 3D reconstruction and visual localization. Although recent methods have made progress in pruning outliers from dense correspondence sets, they often hypothesize consistent visual domains and overlook the challenges posed by diverse scene structures. In this paper, we propose CorrMoE, a novel correspondence pruning framework that enhances robustness under cross-domain and cross-scene variations. To address domain shift, we introduce a De-stylization Dual Branch, performing style mixing on both implicit and explicit graph features to mitigate the adverse influence of domain-specific representations. For scene diversity, we design a Bi-Fusion Mixture of Experts module that adaptively integrates multi-perspective features through linear-complexity attention and dynamic expert routing. Extensive experiments on benchmark datasets demonstrate that CorrMoE achieves superior accuracy and generalization compared to state-of-the-art methods. The code and pre-trained models are available at https: //github. com/peiwenxia/CorrMoE.

Details

NeurIPS Conference 2025 Conference Paper

SYMPHONY: Synergistic Multi-agent Planning with Heterogeneous Language Model Assembly

Wei Zhu
Zhiwen Tang
Kun Yue

Recent advancements have increasingly focused on leveraging large language models (LLMs) to construct autonomous agents for complex problem-solving tasks. However, existing approaches predominantly employ a single-agent framework to generate search branches and estimate rewards during Monte Carlo Tree Search (MCTS) planning. This single-agent paradigm inherently limits exploration capabilities, often resulting in insufficient diversity among generated branches and suboptimal planning performance. To overcome these limitations, we propose $\textbf{SY}$nergistic $\textbf{M}$ulti-agent $\textbf{P}$lanning with $\textbf{H}$eter$\textbf{O}$geneous la$\textbf{N}$gauge model assembl$\textbf{Y}$ ($\textbf{SYMPHONY}$), a novel multi-agent planning framework that integrates a pool of heterogeneous language model-based agents. By leveraging diverse reasoning patterns across agents, SYMPHONY enhances rollout diversity and facilitates more effective exploration. Empirical results across multiple benchmark tasks show that SYMPHONY achieves strong performance even when instantiated with open-source LLMs deployable on consumer-grade hardware. When enhanced with cloud-based LLMs accessible via API, SYMPHONY demonstrates further improvements, outperforming existing state-of-the-art baselines and underscoring the effectiveness of heterogeneous multi-agent coordination in planning tasks.

PDF Details

ECAI Conference 2024 Conference Paper

CorrAdaptor: Adaptive Local Context Learning for Correspondence Pruning

Wei Zhu
Yicheng Liu
Yuping He
Tangfei Liao
Kang Zheng
Xiaoqiu Xu
Tao Wang
Tong Lu

In the fields of computer vision and robotics, accurate pixel-level correspondences are essential for enabling advanced tasks such as structure-from-motion and simultaneous localization and mapping. Recent correspondence pruning methods usually focus on learning local consistency through k-nearest neighbors, which makes it difficult to capture robust context for each correspondence. We propose CorrAdaptor, a novel architecture that introduces a dual-branch structure capable of adaptively adjusting local contexts through both explicit and implicit local graph learning. Specifically, the explicit branch uses KNN-based graphs tailored for initial neighborhood identification, while the implicit branch leverages a learnable matrix to softly assign neighbors and adaptively expand the local context scope, significantly enhancing the model’s robustness and adaptability to complex image variations. Moreover, we design a motion injection module to integrate motion consistency into the network to suppress the impact of outliers and refine local context learning, resulting in substantial performance improvements. The experimental results on extensive correspondence-based tasks indicate that our CorrAdaptor achieves state-of-the-art performance both qualitatively and quantitatively.

Details

ECAI Conference 2023 Conference Paper

Enhancing Document-Level Relation Extraction with Relation-Specific Entity Representation and Evidence Sentence Augmentation

Qizhu Dai
Jiang Zhong
Wei Zhu
Chen Wang 0074
Hong Yin
Qin Lei
Xue Li 0001
Rongzhen Li

Document-level relation extraction (DocRE) is an important task in natural language processing, with applications in knowledge graph construction, question answering, and biomedical text analysis. However, existing approaches to DocRE have limitations in predicting relations between entities using fixed entity representations, which can lead to inaccurate results. In this paper, we propose a novel DocRE model that addresses these limitations by using a relation-specific entity representation method and evidence sentence augmentation. Our model uses evidence sentence augmentation to identify top-k evidence sentences for each relation and a relation-specific entity representation method that aggregates the importance of entity mentions using an attention mechanism. These two components work together to capture the context of each entity mention in relation to the specific relation being predicted and select evidence sentences that support accurate relation identification. Finally, we re-predicts entity relations based on the evidence sentences, called relationship reordering module. This module re-predicts entity relationships based on the predicted set of evidence sentences to form k sets of relationship predictions, and then averages these k+1 sets of results to obtain the final relationship predictions. Experimental results on the DocRED dataset demonstrate that our proposed model achieves an F1 score of 62. 84% and an lgn F1 score of 60. 79%, outperforming state-of-the-art methods.

Details

NeurIPS Conference 2023 Conference Paper

On the Implicit Bias of Linear Equivariant Steerable Networks

Ziyu Chen
Wei Zhu

We study the implicit bias of gradient flow on linear equivariant steerable networks in group-invariant binary classification. Our findings reveal that the parameterized predictor converges in direction to the unique group-invariant classifier with a maximum margin defined by the input group action. Under a unitary assumption on the input representation, we establish the equivalence between steerable networks and data augmentation. Furthermore, we demonstrate the improved margin and generalization bound of steerable networks over their non-invariant counterparts.

PDF Details

EAAI Journal 2023 Journal Article

Reinforcement learning compensated coordination control of multiple mobile manipulators for tight cooperation

Pengjie Xu
Yuanzhe Cui
Yichao Shen
Wei Zhu
Yiheng Zhang
Bingzheng Wang
Qirong Tang

This study presents a coordinated control method based on reinforcement learning for multiple mobile manipulators when strong constraints and close coupling are involved in the tightly cooperative tasks. The reinforcement learning strategy is specifically designed to deal with the unknown vibrations between the mobile manipulators and the common object. Firstly, the problem is converted into a Markov decision process. Next, the grasping forces of the end-effectors are regarded as the parameters to be optimized, and the system states and learning framework are described based on advantage actor–critic algorithm. Thirdly, an agent is trained through interacting with the environment based on a proposed reward policy. To eliminate joint dynamic errors caused by trajectories tracking, an adaptive controller is designed for each mobile manipulator. For the simulations and experiments, two mobile manipulators are employed for transporting a common plate under various conditions. The results demonstrate that the proposed method has better control effects than well-known controllers. This study combines the advantages of both reinforcement learning and model-based method via a coordinated controller designed with the characteristics of tight cooperation.

Details DOI

YNIMG Journal 2022 Journal Article

Cortical layer-specific differences in stimulus selectivity revealed with high-field fMRI and single-vessel resolution optical imaging of the primary visual cortex

Shinho Cho
Arani Roy
Chao J. Liu
Djaudat Idiyatullin
Wei Zhu
Yi Zhang
Xiao-Hong Zhu
Phillip O'Herron

The mammalian neocortex exhibits a stereotypical laminar organization, with feedforward inputs arriving primarily into layer 4, local computations shaping response selectivity in layers 2/3, and outputs to other brain areas emanating via layers 2/3, 5 and 6. It cannot be assumed a priori that these signatures of laminar differences in neuronal circuitry are reflected in hemodynamic signals that form the basis of functional magnetic resonance imaging (fMRI). Indeed, optical imaging of single-vessel functional responses has highlighted the potential limits of using vascular signals as surrogates for mapping the selectivity of neural responses. Therefore, before fMRI can be employed as an effective tool for studying critical aspects of laminar processing, validation with single-vessel resolution is needed. The primary visual cortex (V1) in cats, with its precise neuronal functional micro-architecture, offers an ideal model system to examine laminar differences in stimulus selectivity across imaging modalities. Here we used cerebral blood volume weighted (wCBV) fMRI to examine if layer-specific orientation-selective responses could be detected in cat V1. We found orientation preference maps organized tangential to the cortical surface that typically extended across depth in a columnar fashion. We then examined arterial dilation and blood velocity responses to identical visual stimuli by using two- and three- photon optical imaging at single-vessel resolution-which provides a measure of the hemodynamic signals with the highest spatial resolution. Both fMRI and optical imaging revealed a consistent laminar response pattern in which orientation selectivity in cortical layer 4 was significantly lower compared to layer 2/3. This systematic change in selectivity across cortical layers has a clear underpinning in neural circuitry, particularly when comparing layer 4 to other cortical layers.

Details DOI

TMLR Journal 2022 Journal Article

Deformation Robust Roto-Scale-Translation Equivariant CNNs

Liyao Gao
Guang Lin
Wei Zhu

Incorporating group symmetry directly into the learning process has proved to be an effective guideline for model design. By producing features that are guaranteed to transform covariantly to the group actions on the inputs, group-equivariant convolutional neural networks (G-CNNs) achieve significantly improved generalization performance in learning tasks with intrinsic symmetry. General theory and practical implementation of G-CNNs have been studied for planar images under either rotation or scaling transformation, but only individually. We present, in this paper, a roto-scale-translation equivariant CNN ($\mathcal{RST}$-CNN), that is guaranteed to achieve equivariance jointly over these three groups via coupled group convolutions. Moreover, as symmetry transformations in reality are rarely perfect and typically subject to input deformation, we provide a stability analysis of the equivariance of representation to input distortion, which motivates the truncated expansion of the convolutional filters under (pre-fixed) low-frequency spatial modes. The resulting model provably achieves deformation-robust $\mathcal{RST}$ equivariance, i.e., the $\mathcal{RST}$ symmetry is still "approximately” preserved when the transformation is "contaminated” by a nuisance data deformation, a property that is especially important for out-of-distribution generalization. Numerical experiments on MNIST, Fashion-MNIST, and STL-10 demonstrate that the proposed model yields remarkable gains over prior arts, especially in the small data regime where both rotation and scaling variations are present within the data.

PDF Details

JMLR Journal 2022 Journal Article

Scaling-Translation-Equivariant Networks with Decomposed Convolutional Filters

Wei Zhu
Qiang Qiu
Robert Calderbank
Guillermo Sapiro
Xiuyuan Cheng

Encoding the scale information explicitly into the representation learned by a convolutional neural network (CNN) is beneficial for many computer vision tasks especially when dealing with multiscale inputs. We study, in this paper, a scaling-translation-equivariant ($\mathcal{ST}$-equivariant) CNN with joint convolutions across the space and the scaling group, which is shown to be both sufficient and necessary to achieve equivariance for the regular representation of the scaling-translation group $\mathcal{ST}$. To reduce the model complexity and computational burden, we decompose the convolutional filters under two pre-fixed separable bases and truncate the expansion to low-frequency components. A further benefit of the truncated filter expansion is the improved deformation robustness of the equivariant representation, a property which is theoretically analyzed and empirically verified. Numerical experiments demonstrate that the proposed scaling-translation-equivariant network with decomposed convolutional filters (ScDCFNet) achieves significantly improved performance in multiscale image classification and better interpretability than regular CNNs at a reduced model size. [abs] [ pdf ][ bib ] &copy JMLR 2022. ( edit, beta )

PDF Details

TIST Journal 2021 Journal Article

Route Optimization via Environment-Aware Deep Network and Reinforcement Learning

Pengzhan Guo
Keli Xiao
Zeyang Ye
Wei Zhu

Vehicle mobility optimization in urban areas is a long-standing problem in smart city and spatial data analysis. Given the complex urban scenario and unpredictable social events, our work focuses on developing a mobile sequential recommendation system to maximize the profitability of vehicle service providers (e.g., taxi drivers). In particular, we treat the dynamic route optimization problem as a long-term sequential decision-making task. A reinforcement-learning framework is proposed to tackle this problem, by integrating a self-check mechanism and a deep neural network for customer pick-up point monitoring. To account for unexpected situations (e.g., the COVID-19 outbreak), our method is designed to be capable of handling related environment changes with a self-adaptive parameter determination mechanism. Based on the yellow taxi data in New York City and vicinity before and after the COVID-19 outbreak, we have conducted comprehensive experiments to evaluate the effectiveness of our method. The results show consistently excellent performance, from hourly to weekly measures, to support the superiority of our method over the state-of-the-art methods (i.e., with more than 98% improvement in terms of the profitability for taxi drivers).

Details DOI

NeurIPS Conference 2018 Conference Paper

Deep Neural Nets with Interpolating Function as Output Activation

Bao Wang
xiyang luo
Zhen Li
Wei Zhu
Zuoqiang Shi
Stanley Osher

We replace the output layer of deep neural nets, typically the softmax function, by a novel interpolating function. And we propose end-to-end training and testing algorithms for this new architecture. Compared to classical neural nets with softmax function as output activation, the surrogate with interpolating function as output activation combines advantages of both deep and manifold learning. The new framework demonstrates the following major advantages: First, it is better applicable to the case with insufficient training data. Second, it significantly improves the generalization accuracy on a wide variety of networks. The algorithm is implemented in PyTorch, and the code is available at https: //github. com/ BaoWangMath/DNN-DataDependentActivation.

PDF Details

AAAI Conference 2017 Conference Paper

Unsupervised Large Graph Embedding

Feiping Nie
Wei Zhu
Xuelong Li

There are many successful spectral based unsupervised dimensionality reduction methods, including Laplacian Eigenmap (LE), Locality Preserving Projection (LPP), Spectral Regression (SR), etc. LPP and SR are two different linear spectral based methods, however, we discover that LPP and SR are equivalent, if the symmetric similarity matrix is doubly stochastic, Positive Semi-Deﬁnite (PSD) and with rank p, where p is the reduced dimension. The discovery promotes us to seek low-rank and doubly stochastic similarity matrix, we then propose an unsupervised linear dimensionality reduction method, called Unsupervised Large Graph Embedding (ULGE). ULGE starts with similar idea as LPP, it adopts an efﬁcient approach to construct similarity matrix and then performs spectral analysis efﬁciently, the computational complexity can reduce to O(ndm), which is a signiﬁcant improvement compared to conventional spectral based methods which need O(n2 d) at least, where n, d and m are the number of samples, dimensions and anchors, respectively. Extensive experiments on several public available data sets demonstrate the efﬁciency and effectiveness of the proposed method.

PDF Details

AAAI Conference 2016 Conference Paper

Unsupervised Feature Selection with Structured Graph Optimization

Feiping Nie
Wei Zhu
Xuelong Li

Since amounts of unlabelled and high-dimensional data needed to be processed, unsupervised feature selection has become an important and challenging problem in machine learning. Conventional embedded unsupervised methods always need to construct the similarity matrix, which makes the selected features highly depend on the learned structure. However real world data always contain lots of noise samples and features that make the similarity matrix obtained by original data can’t be fully relied. We propose an unsupervised feature selection approach which performs feature selection and local structure learning simultaneously, the similarity matrix thus can be determined adaptively. Moreover, we constrain the similarity matrix to make it contain more accurate information of data structure, thus the proposed approach can select more valuable features. An efﬁcient and simple algorithm is derived to optimize the problem. Experiments on various benchmark data sets, including handwritten digit data, face image data and biomedical data, validate the effectiveness of the proposed approach.

PDF Details

YNIMG Journal 2004 Journal Article