Ming Li

• Ph.D
• Professor at Zhejiang Normal University

This paper contributes to a development of randomized methods for neural networks. The proposed learner model is generated incrementally by stochastic configuration (SC) algorithms, termed as Stochastic Configuration Networks (SCNs). In contrast to the existing randomised learning algorithms for single layer feed-forward neural networks (SLFNs), we...

Neural networks have been widely used as predictive models to fit data distribution, and they could be implemented through learning a collection of samples. In many applications, however, the given dataset may contain noisy samples or outliers which may result in a poor learner model in terms of generalization. This paper contributes to a developme...

In this paper we study the convergence rate and inverse theorem for spherical multiscale interpolation in Lp and Sobolev norms. The multiscale interpolation is constructed using a sequence of scaled, compactly supported radial basis functions restricted to the unit sphere . For the interpolation scheme the problem called “native space barrier” is c...

This paper focuses on the multiscale moving least squares approximation scheme on the unit sphere, where the scale depends on the current evaluation points. The scheme is constructed by using a sequence of scaled weight functions, and is a little different from the classical moving least squares approximation on the sphere, which can be obtained by...

Graph anomaly detection (GAD) has attracted increasing interest due to its critical role in diverse real-world applications. Graph neural networks (GNNs) offer a promising avenue for GAD, leveraging their exceptional capacity to model complex graph structures and relationships. However, existing GNN-based models encounter challenges in addressing t...

The out-of-distribution (OOD) detection on graph-structured data is crucial for deploying graph neural networks securely in open-world scenarios. However, existing methods have overlooked the prevalent scenario of multi-label classification in real-world applications. In this work, we investigate the unexplored issue of OOD detection within multi-l...

Graph-based representations are powerful tools for analyzing structured data. In this paper, we propose a novel model to learn Deep Hierarchical Attention-based Kernelized Representations (DHAKR) for graph classification. To this end, we commence by learning an assignment matrix to hierarchically map the substructure invariants into a set of compos...

Hypergraph neural networks (HNNs) have shown promise in handling tasks characterized by high-order correlations, achieving notable success across various applications. However, there has been limited focus on heterophilic hypergraph learning (HHL), in contrast to the increasing attention given to graph neural networks designed for graphs exhibiting...

Hypergraphs provide a flexible framework for modeling high-order (complex) interactions among multiple entities, extending beyond traditional pairwise correlations in graph structures. However, deep hypergraph neural networks (HGNNs) often face the challenge of oversmoothing with increasing depth, similar to issues in graph neural networks (GNNs)....

Graph machine learning has witnessed rapid growth, driving advancements across diverse domains. However, the in-distribution assumption, where training and testing data share the same distribution, often breaks in real-world scenarios, leading to degraded model performance under distribution shifts. This challenge has catalyzed interest in graph ou...

In social networks, the discovery of community structures has received considerable attention as a fundamental problem in various network analysis tasks. However, due to privacy concerns or access restrictions, the network structure is often uncertain , thereby rendering established community detection approaches ineffective without costly network...

In online learning, personalized course recommendations that align with learners' preferences and future needs are essential. Thus, the development of efficient recommender systems is crucial to guide learners to appropriate courses. Graph learning in recommender systems has been extensively studied, yet many models focus on low-frequency informati...

In this work, we develop a family of Aligned Entropic Graph Kernels (AEGK) for graph classification. We commence by performing the Continuous-time Quantum Walk (CTQW) on each graph structure, and compute the Averaged Mixing Matrix (AMM) to describe how the CTQW visits all vertices from a starting vertex. More specifically, we show how this AMM matr...

The cortical surface parcellation provides prior guidance for studying mental disorders and human cognition. Graph neural networks (GNNs) have gained popularity in this task to preserve its spatial structure. However, previous GNNs struggled to effectively exploit the information contained in the complex spatial structure of the cortical surface an...

In this work, we propose two novel quantum walk kernels, namely the Hierarchical Aligned Quantum Jensen-Shannon Kernels (HAQJSK), between un-attributed graph structures. Different from most classical graph kernels, the proposed HAQJSK kernels can incorporate hierarchical aligned structure information between graphs and transform graphs of random si...

Deep learning ( DL ) based knowledge tracing ( KT ) models have challenges for uninterpretable prediction and parameter representation in educational applications, though they achieved remarkable outcomes in predicting the exercise performance of students. This paper proposes a novel knowledge tracing model of high precision and interpretability...

Augmented reality (AR) has been regarded as a useful tool in writing education, with the goal of enhancing students’ learning. However, questions still exist about the consistency of student motivation and their writing performance when participating in educational activities driven by AR. This study focused on AR-based writing courses, employing k...

Graph convolutional networks (GCNs) have emerged as powerful models for graph learning tasks, exhibiting promising performance in various domains. While their empirical success is evident, there is a growing need to understand their essential ability from a theoretical perspective. Existing theoretical research has primarily focused on the analysis...

Graph Auto-Encoders (GAEs) are powerful tools for graph representation learning. In this paper, we develop a novel Hierarchical Cluster-based GAE (HC-GAE), that can learn effective structural characteristics for graph data analysis. To this end, during the encoding process, we commence by utilizing the hard node assignment to decompose a sample gra...

Message passing (MP) is crucial for effective graph neural networks (GNNs). Most local message-passing schemes have been shown to underperform on heterophily graphs due to the perturbation of updated representations caused by local redundant heterophily information. However, our experiment findings indicate that the distribution of heterophily info...

In this paper, we explore the approximation theory of functions defined on graphs. Our study builds upon the approximation results derived from the $K$-functional. We establish a theoretical framework to assess the lower bounds of approximation for target functions using Graph Convolutional Networks (GCNs) and examine the over-smoothing phenomenon...

Graph Auto-Encoders (GAEs) are powerful tools for graph representation learning. In this paper, we develop a novel Hierarchical Cluster-based GAE (HC-GAE), that can learn effective structural characteristics for graph data analysis. To this end, during the encoding process, we commence by utilizing the hard node assignment to decompose a sample gra...

Spectral Graph Neural Networks (GNNs), alternatively known as graph filters, have gained increasing prevalence for heterophily graphs. Optimal graph filters rely on Laplacian eigendecomposition for Fourier transform. In an attempt to avert prohibitive computations, numerous polynomial filters have been proposed. However, polynomials in the majority...

Graph Neural Networks (GNNs) are powerful tools for graph classification. One important operation for GNNs is the downsampling or pooling that can learn effective embeddings from the node representations. In this paper, we propose a new hierarchical pooling operation, namely the Edge-Node Attention-based Differentiable Pooling (ENADPool), for GNNs...

In the field of educational data mining, accurately predicting student performance is vital for developing effective educational strategies. However, existing methods often fall short in capturing the complex relationships between students, focusing mainly on individual attributes. This paper introduces a pioneering framelet-based dual hypergraph n...

Graph Neural Network (GNN) has attracted considerable research interest in various graph data modeling tasks. Most GNNs require efficient and sufficient label information during training phase. However, in open environments, the performance of existing GNNs sharply decrease according to the data (structure, attribute and label) missing and noising....

Deep neural networks for graphs (DNNGs) represent an emerging field that studies how the deep learning method can be generalized to graph-structured data. Since graphs are a powerful and flexible tool to represent complex information in the form of patterns and their relationships, ranging from molecules to protein-to-protein interaction networks,...

The nature of heterophilous graphs is significantly different from that of homophilous graphs, which causes difficulties in early graph neural network (GNN) models and suggests aggregations beyond the one-hop neighborhood. In this article, we develop a new way to implement multiscale extraction via constructing Haar-type graph framelets with desire...

Visual tracking is a vitally important task in computer vision, which is widely used in intelligent surveillance and traffic control, etc. Currently, real-time multiple object tracking methods are still not mature in practical applications and still need to be further refined to enhance their performance especially in complex and crowded environmen...

Face detection is a fundamental task in computer vision, yet remains challenging in educational settings due to the presence of objects of various sizes. Subpar detection can significantly impede subsequent tasks' performance. To address this, we present a novel framework, Small Object Detection Super Resolution (SODSR), inspired by super resolutio...

Cortical surface parcellation aims to segment the surface into anatomically and functionally significant regions, which are crucial for diagnosing and treating numerous neurological diseases. However, existing methods generally ignore the difficulty in learning labeling patterns of boundaries, hindering the performance of parcellation. To this end,...

Writing is a fundamental skill linked closely with academic achievement, day‐to‐day communication, formal negotiations, and more. However, due to their lack of contextual experience, learning to write has been a demanding and complex cognitive process for most learners. As a result, learners struggle to exhibit positive learning behaviours and cogn...

Creative writing is a valuable skill that enables learners to become proficient writers. One reason students often struggle with creative writing is their lack of contextual experiences. Spherical video-based virtual reality (SVVR) has been argued to support students’ writing through immersive virtual experiences. However, what specific pedagogical...

Graph convolutional networks (GCN) are viewed as one of the most popular representations among the variants of graph neural networks over graph data and have shown powerful performance in empirical experiments. That l2-based graph smoothing enforces the global smoothness of GCN, while (soft) l1-based sparse graph learning tends to promote signal sp...

To improve the robustness of graph neural networks (GNN), graph structure learning (GSL) has attracted great interest due to the pervasiveness of noise in graph data. Many approaches have been proposed for GSL to jointly learn a clean graph structure and corresponding representations. To extend the previous work, this paper proposes a novel regular...

To ease the process of building Knowledge Graphs (KGs) from scratch, a cost-effective method is required to enrich a KG using the triples extracted from a corpus. However, it is challenging to enrich a KG with newly extracted triples since they contain noisy information. This paper proposes to refine a KG by leveraging information extracted from a...

Reference-based super-resolution (RefSR) has gained considerable success in the field of super-resolution with the addition of high-resolution reference images to reconstruct low-resolution (LR) inputs with more high-frequency details, thereby overcoming some limitations of single image super-resolution (SISR). Previous research in the field of Ref...

Graph convolutional networks (GCN) are viewed as one of the most popular representations among the variants of graph neural networks over graph data and have shown powerful performance in empirical experiments. That $\ell_2$-based graph smoothing enforces the global smoothness of GCN, while (soft) $\ell_1$-based sparse graph learning tends to promo...

In social networks, the discovery of community structures has received considerable attention as a fundamental problem in various network analysis tasks. However, due to privacy concerns or access restrictions, the network structure is often unknown, thereby rendering established community detection approaches ineffective without costly network top...

Quantum entanglement (QE) is the phenomenon that when several particles interact, the properties of each particle will be integrated into the properties of the overall system, and the properties of each particle cannot be described independently from others. QE can be proved by violating Bell Inequality, that is, it can describe strong statistical...

In this work, we develop an Aligned Entropic Reproducing Kernel (AERK) for graph classification. We commence by performing the Continuous-time Quantum Walk (CTQW) on each graph structure, and computing the Averaged Mixing Matrix (AMM) to describe how the CTQW visit all vertices from a starting vertex. More specifically, we show how this AMM matrix...

In this work, we propose a spectral-based graph convolutional network for directed graphs. The proposed model employs the classic singular value decomposition (SVD) to perform signal decomposition directly on the asymmetric adjacency matrix. This strategy is simple, which allows many existing spectral-based methods to be adapted to directed graphs....

Graph neural networks (GNNs) have a powerful ability to capture long-range spatial correlations in hyperspectral images (HSIs). However, existing GNN-based HSI classification methods are vulnerable to hand-crafted graphs, as the manner in which these graphs are constructed are often inappropriate and are likely to violate intrinsic graph properties...

Immersive technology has received extensive attention in both L1 and L2 writing education. Its unique capabilities to offer virtual experiences alongside real-world experiences can create authentic learning environments that support students' experiential learning and enable the observation of events beyond the confines of traditional classrooms. H...

Graph representation learning (GRL) is critical for graph-structured data analysis. However, most of the existing graph neural networks (GNNs) heavily rely on labeling information, which is normally expensive to obtain in the real world. Although some existing works aim to effectively learn graph representations in an unsupervised manner, they suff...

Graph neural networks (GNNs) have shown strong graph-structured data processing capabilities. However, most of them are generated based on the message-passing mechanism and lack of the systematic approach to guide their developments. Meanwhile, a unified point of view is hard to explain the design concepts of different GNN models. This paper presen...

Aspect-based sentiment analysis (ABSA) aims to use interactions between aspect terms and their contexts to predict sentiment polarity for given aspects in sentences. Current mainstream approaches use deep neural networks (DNNs) combined with additional linguistic information to improve performance. DNN-based methods, however, lack explanation and t...

Gastric cancer is one of the deadliest cancers worldwide. Accurate prognosis is essential for effective clinical assessment and treatment. Spatial patterns in the tumor microenvironment (TME) are conceptually indicative of the staging and progression of gastric cancer patients. Using spatial patterns of the TME by integrating and transforming the m...

To alleviate the challenges of building Knowledge Graphs (KG) from scratch, a more general task is to enrich a KG using triples from an open corpus, where the obtained triples contain noisy entities and relations. It is challenging to enrich a KG with newly harvested triples while maintaining the quality of the knowledge representation. This paper...

Graph Convolutional Networks (GCNs), as a prominent example of graph neural networks, are receiving extensive attention for their powerful capability in learning node representations on graphs. There are various extensions, either in sampling and/or node feature aggregation, to further improve GCNs' performance, scalability and applicability in var...

Gastric cancer is one of the deadliest cancers worldwide. An accurate prognosis is essential for effective clinical assessment and treatment. Spatial patterns in the tumor microenvironment (TME) are conceptually indicative of the staging and progression of gastric cancer patients. Using spatial patterns of the TME by integrating and transforming th...

Writing is a recording process involving complex dynamic behaviours, which is closely connected with authentic contexts. A free authentic context can form a link with students' life experience and their prior knowledge, so that students' deep writing skills can be stimulated. However, in traditional writing activities, the lack of authentic experie...

Learning efficient graph representation is the key to favorably addressing downstream tasks on graphs, such as node or graph property prediction. Given the non-Euclidean structural property of graphs, preserving the original graph data's similarity relationship in the embedded space needs specific tools and a similarity metric. This paper develops...

Learning efficient graph representation is the key to favorably addressing downstream tasks on graphs, such as node or graph property prediction. Given the non-Euclidean structural property of graphs, preserving the original graph data’s similarity relationship in the embedded space needs specific tools and a similarity metric. This paper develops...

Recent advances in graph convolutional networks (GCNs), which mainly focus on how to exploit information from different hops of neighbors in an efficient way, have brought substantial improvement to many graph data modeling tasks. Most of the existing GCN-based models however are built on the basis of a fixed adjacency matrix, i.e., a single view t...

In this work, the “effective dimension” of the output of the hidden layer of a one-hidden-layer neural network with random inner weights of its computational units is investigated. To do this, a polynomial approximation of the sigmoidal activation function of each computational unit is used, whose degree is chosen based both on a desired upper boun...

Pedestrians are often vulnerable users of urban roads and ensuring their safety is a pressing challenge in the filed of intelligent transportation. Multiple pedestrian tracking is one of the key technologies for traffic statistics and abnormal behavior analysis, etc. Detection-based tracking methods have achieved remarkable results and have become...

Vector spherical harmonics on the unit sphere of ℝ ³ have broad applications in geophysics, quantum mechanics, and astrophysics. In the representation of a tangent vector field, one needs to evaluate the expansion and the Fourier coefficients of vector spherical harmonics. In this article, we develop fast algorithms (FaVeST) for vector spherical ha...

Graph neural networks (GNNs), with their promising potential to learn effective graph representation, have been widely used for recommender systems, in which the given graph data contains abundant users, items, and their historical interaction information. How to obtain preferable latent representations for both users and items is one of the key is...

Graph neural networks (GNNs) extend the functionality of traditional neural networks to graph-structured data. Similar to CNNs, an optimized design of graph convolution and pooling is key to success. Borrowing ideas from physics, we propose path integral-based GNNs (PAN) for classification and regression tasks on graphs. Specifically, we consider a...

Graph representation learning (GRL) is critical for graph-structured data analysis. However, most of the existing graph neural networks (GNNs) heavily rely on labeling information, which is normally expensive to obtain in the real world. Existing unsupervised GRL methods suffer from certain limitations, such as the heavy reliance on monotone contra...

Gastric cancer is one of the deadliest cancers worldwide. Accurate prognosis is essential for effective clinical assessment and treatment. Spatial patterns in the tumor microenvironment (TME) are conceptually indicative of the staging and progression of gastric cancer patients. Using spatial patterns of the TME by integrating and transforming the m...

In conventional IoT predictive maintenance solutions, fault detection methods typically incorporate all the measured sensor variables and are usually deployed in the cloud, resulting in a heavy burden on the network bandwidth. To address this problem, this paper develops an artificial intelligence-assisted distributed system for manufacturing plant...

Sentiment evolution is a key component of interactions in blended learning. Although interactions have attracted considerable attention in online learning contexts, there is scant research on examining sentiment evolution over different interactions in blended learning environments. Thus, in this study, sentiment evolution at different interaction...

Multiple pedestrian tracking in video surveillance is still a pressing challenge, especially under static and dynamic occlusions and target appearance variations. Considering these complex environments in video surveillance, a multiple pedestrian tracking system with special processing procedures is proposed in this paper. In the proposed tracking...

This paper presents a new approach for assembling graph neural networks based on framelet transforms. The latter provides a multi-scale representation for graph-structured data. With the framelet system, we can decompose the graph feature into low-pass and high-pass frequencies as extracted features for network training, which then defines a framel...

Studies have demonstrated that stochastic configuration networks (SCNs) have good potential for rapid data modeling because of their sufficient adequate learning power, which is theoretically guaranteed. Empirical studies have verified that the learner models produced by SCNs can usually achieve favorable test performance in practice but more in-de...

Graph Neural Networks (GNNs) have recently caught great attention and achieved significant progress in graph-level applications. In this paper, we propose a framework for graph neural networks with multiresolution Haar-like wavelets, or MathNet, with interrelated convolution and pooling strategies. The underlying method takes graphs in different st...

Stochastic configuration networks (SCNs) as a class of randomized learner model have been successfully employed in data analytics due to its universal approximation capability and fast modeling property. The technical essence lies in stochastically configuring the hidden nodes (or basis functions) based on a supervisory mechanism rather than data-i...

Good recommendation for difficulty exercises can effectively help to point the students/users in the right direction, and potentially empower their learning interests. It is however challenging to select the exercises with reasonable difficulty for students as they have different learning status and the size of exercise bank is quite large. The cla...

The analysis of spatial observations on a sphere is important in areas such as geosciences, physics and embryo research, just to name a few. The purpose of the package rcosmo is to conduct efficient information processing, visualisation, manipulation and spatial statistical analysis of Cosmic Microwave Background (CMB) radiation and other spherical...

A random net is a shallow neural network where the hidden layer is frozen with random assignment and the output layer is trained by convex optimization. Using random weights for a hidden layer is an effective method to avoid the inevitable non-convexity in standard gradient descent learning. It has recently been adopted in the study of deep learnin...

Graph neural networks (GNNs) extends the functionality of traditional neural networks to graph-structured data. Similar to CNNs, an optimized design of graph convolution and pooling is key to success. Borrowing ideas from physics, we propose a path integral based graph neural networks (PAN) for classification and regression tasks on graphs. Specifi...

Deep Graph Neural Networks (GNNs) are useful models for graph classification and graph-based regression tasks. In these tasks, graph pooling is a critical ingredient by which GNNs adapt to input graphs of varying size and structure. We propose a new graph pooling operation based on compressive Haar transforms --- \emph{HaarPooling}. HaarPooling imp...

Graph Neural Networks (GNNs) have become a topic of intense research recently due to their powerful capability in high-dimensional classification and regression tasks for graph-structured data. However, as GNNs typically define the graph convolution by the orthonormal basis for the graph Laplacian, they suffer from high computational cost when the...