About
213
Publications
20,059
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
3,668
Citations
Current institution
Publications
Publications (213)
Open intent classification is critical for the development of dialogue systems, aiming to accurately classify known intents into their corresponding classes while identifying unknown intents. Prior boundary-based methods assumed known intents fit within compact spherical regions, focusing on coarse-grained representation and precise spherical decis...
Graph Neural Networks (GNNs) have demonstrated significant achievements in processing graph data, yet scalability remains a substantial challenge. To address this, numerous graph coarsening methods have been developed. However, most existing coarsening methods are training-dependent, leading to lower efficiency, and they all require a predefined co...
The previous advancements in pathology image understanding primarily involved developing models tailored to specific tasks. Recent studies have demonstrated that the large vision-language model can enhance the performance of various downstream tasks in medical image understanding. In this study, we developed a domain-specific large vision-language...
The traditional graph representation methods can fit the information of graph with low-dimensional vectors, but they cannot interpret their composition, resulting in insufficient security. Graph decoupling, as a method of graph representation, can analyze the latent factors composing the graph representation vectors. However, in current graph decou...
Objective:
Accurate decoding of electroencephalogram (EEG) signals has become more significant for the brain-computer interface (BCI). Specifically, motor imagery and motor execution (MI/ME) tasks enable the control of external devices by decoding EEG signals during imagined or real movements. However, accurately decoding MI/ME signals remains a c...
In recent years, with the rapid development of the Internet, multisource information fusion has become a forefront issue due to its ability to merge different information. Granular computing (GrC), as a methodology simulating human hierarchical cognition, provides a new approach for multisource information fusion. However, on one hand, the existing...
Fuzzy rough set theory is effective for processing datasets with complex attributes, supported by a solid mathematical foundation and closely linked to kernel methods in machine learning. Attribute reduction algorithms and classifiers based on fuzzy rough set theory exhibit promising performance in the analysis of high-dimensional multivariate comp...
Federated Learning (FL) facilitates collaborative model training while prioritizing privacy by avoiding direct data sharing. However, most existing articles attempt to address challenges within the model's internal parameters and corresponding outputs, while neglecting to solve them at the input level. To address this gap, we propose a novel framew...
Graph variational autoencoders (VAEs) have been widely used to address the representation problem of graph nodes. However, most existing graph VAEs focus on minimizing reconstruction loss and overlook the uncertainty in the latent distribution and the issue of posterior collapse during training. An Adversarial Regularize Graph Variational Autoencod...
The distribution of the labeled data can greatly affect the performance of a semi-supervised learning (SSL) model. Most existing SSL models select the labeled data randomly and equally allocate the labeling quota among the classes, leading to considerable unstableness and degeneration of performance. This study unsupervisedly constructs a leading f...
Granular-ball computing (GBC) proposed by Xia adaptively generates a different neighborhood for each object, resulting in greater generality and flexibility. Moreover, GBC greatly improves the efficiency by replacing point input with granular-ball. However, the current GB-based classifiers rigidly assign a specific class label to each data instance...
Open intent classification is critical for the development of dialogue systems, aiming to accurately classify known intents into their corresponding classes while identifying unknown intents. Prior boundary-based methods assumed known intents fit within compact spherical regions, focusing on coarse-grained representation and precise spherical decis...
Graph Neural Networks (GNNs) have demonstrated significant achievements in processing graph data, yet scalability remains a substantial challenge. To address this, numerous graph coarsening methods have been developed. However, most existing coarsening methods are training-dependent, leading to lower efficiency, and they all require a predefined co...
Xu Gong Qun Liu Jing He- [...]
Guoyin Wang
Drug-target interaction (DTI) prediction is a tough task with critical applications in drug repurposing and design scenarios, as it significantly reduces resource consumption and accelerates the drug discovery process. With the proliferation of experimentally measured pharmaceutical data and increasingly complex drug-target interactions, deep DTI a...
This paper presents a novel framework for continual feature selection (CFS) in data preprocessing, particularly in the context of an open and dynamic environment where unknown classes may emerge. CFS encounters two primary challenges: the discovery of unknown knowledge and the transfer of known knowledge. To this end, the proposed CFS method combin...
Traditional fuzzy set methods, designed around the finest granularity of inputs-individual points and their membership degrees-often struggle with inefficiencies and label noise. To overcome these challenges, we introduce granular-ball computing into the fuzzy set, creating the new granular-ball fuzzy set framework. This approach uses granular-ball...
Protein-protein interactions (PPIs) are essential to understanding cellular mechanisms, signaling networks, disease processes, and drug development, as they represent the physical contacts and functional associations between proteins. Recent advances have witnessed the achievements of artificial intelligence (AI) methods aimed at predicting PPIs. H...
Traditional clustering algorithms often focus on the most fine-grained information and achieve clustering by calculating the distance between each pair of data points or implementing other calculations based on points. This way is not inconsistent with the cognitive mechanism of "global precedence" in human brain, resulting in those methods' bad pe...
In large-scale decision systems with high dimensions, constructing an efficient feature selection method via an uncertainty measure, has become a critical problem in fuzzy rough sets. However, the uncertainty method constructed through fuzzy rough sets for feature selection has the following limitations: (1) the composition of the uncertainty cause...
In actual scenarios, whether manually or automatically annotated, label noise is inevitably generated in the training data, which can affect the effectiveness of deep CNN models. The popular solutions require data cleaning or designing additional optimizations to punish the data with mislabeled data, thereby enhancing the robustness of models. Howe...
Currently, three-way decision with neighborhood rough sets (3WDNRS) is widely used in many fields. The core of 3WDNRS is to calculate threshold pairs to divide a neighborhood space into three pairwise disjoint regions. The majority of research on 3WDNRS mainly aims to calculate thresholds with the given risk parameters to minimize the misclassifica...
Ke Liu Tao Yang Zhuliang Yu- [...]
Wei Wu
italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Object:
Transformer-based neural networks have been applied to the electroencephalography (EEG) decoding for motor imagery (MI). However, most networks focus on applying the self-attention mechanism to extract global temporal information, while the cro...
The previous advancements in pathology image understanding primarily involved developing models tailored to specific tasks. Recent studies has demonstrated that the large vision-language model can enhance the performance of various downstream tasks in medical image understanding. In this study, we developed a domain-specific large language-vision a...
In multimodal data processing of image captioning, data from different modalities usually exhibit distinct feature distributions. The gap in unimodal representation makes capturing cross-modal mappings in multimodal learning challenging. Current image captioning models transform images into captions directly. However, this approach results in large...
On-the-fly Fine-grained sketch-based image retrieval (On-the-fly FG-SBIR) framework aim to break the barriers that sketch drawing requires excellent skills and is time-consuming. Considering such problems, a partial sketch with fewer strokes contains only the little local information, and the drawing process may show great difference among users, r...
Three-way decision with neighborhood rough sets (3WDNRS) is adept at addressing uncertain problems involving continuous data by configuring the neighborhood radius. However, on one hand, the inputs of 3WDNRS are individual neighborhood granules, which reduce the decision efficiency and generality; on other hand, the thresholds of 3WDNRS require pri...
Artificial intelligence (AI) systems surpass certain human intelligence abilities in a statistical sense as a whole, but are not yet the true realization of these human intelligence abilities and behaviors. There are differences, and even contradictions, between the cognition and behavior of AI systems and humans. With the goal of achieving general...
Deep neural networks have been widely applied in many fields, but it is found that they are vulnerable to adversarial examples, which can mislead the DNN-based models with imperceptible perturbations. Many adversarial attack methods can achieve great success rates when attacking white-box models, but they usually exhibit poor transferability when a...
Currently, image-text-driven multi-modal deep learning models have demonstrated their outstanding potential in many fields. In practice, tasks centered around facial images have broad application prospects. This paper presents \textbf{FaceCaption-15M}, a large-scale, diverse, and high-quality dataset of facial images accompanied by their natural la...
The granular-ball (GB)-based classifier introduced by Xia, exhibits adaptability in creating coarse-grained information granules for input, thereby enhancing its generality and flexibility. Nevertheless, the current GB-based classifiers rigidly assign a specific class label to each data instance and lacks of the necessary strategies to address unce...
Granular-ball support vector machine (GBSVM) is a significant attempt to construct a classifier using the coarse-to-fine granularity of a granular ball as input, rather than a single data point. It is the first classifier whose input contains no points. However, the existing model has some errors, and its dual model has not been derived. As a resul...
Group decision-making (GDM) characterized by complexity and uncertainty is an essential part of various life scenarios. Most existing researches lack tools to fuse information quickly and interpret decision results for partially formed decisions. This limitation is particularly noticeable when there is a need to improve the efficiency of GDM. To ad...
In the real world, data distributions often exhibit multiple granularities. However, the majority of existing neighbor-based machine-learning methods rely on manually setting a single-granularity for neighbor relationships. These methods typically handle each data point using a single-granularity approach, which severely affects their accuracy and...
The metaverse is an Artificial Intelligence (AI)-generated virtual world, in which people can game, work, learn, and socialize. The realization of metaverse not only requires a large amount of computing resources to realize the rendering of the virtual world, but also requires communication resources to realize real-time transmission of massive dat...
The metaverse is an Artificial Intelligence (AI) -generated virtual world, in which people can game, work, learn and socialize. The realization of metaverse not only requires a large amount of computing resources to realize the rendering of the virtual world, but also requires communication resources to realize real-time transmission of massive dat...
Electroencephalographic (EEG) source imaging (ESI) is a powerful method for studying brain functions and surgical resection of epileptic foci. However, accurately estimating the location and extent of brain sources remains challenging due to noise and background interference in EEG signals. To reconstruct extended brain sources, we propose a new ES...
Granular ball computing (GBC), as an efficient, robust, and scalable learning method, has become a popular research topic of granular computing. GBC includes two stages: granular ball generation (GBG) and multi-granularity learning based on the granular ball (GB). However, the stability and efficiency of existing GBG methods need to be further impr...
Although deep convolution neural network (DCNN) has achieved great success in computer vision field, such models are considered to lack interpretability in decision‐making. One of fundamental issues is that its decision mechanism is considered to be a “black‐box” operation. The authors design the binary tree structure convolution (BTSC) module and...
Deep learning has excelled in single-image super-resolution (SISR) applications, yet the lack of interpretability in most deep learning-based SR networks hinders their applicability, especially in fields like medical imaging that require transparent computation. To address these problems, we present an interpretable frequency division SR network th...
Sketch education is an essential component of arts education. In recent years, with the development of society, the demand for sketch courses has been steadily increasing. However, the existing teaching resources are severely lacking, and unable to meet the requirements of high-quality teaching. This paper has designed and implemented a sketching s...
Multimodal Emotion Recognition in Conversations (MERC) is an important topic in human-computer interaction. In the MERC task, conversations exhibit dynamic emotional dependency, including inter-speaker and intra-speaker emotional dependency, both are vital in understanding the content. However, current research primarily integrates these two emotio...
By thinking, information processing and decision-making in threes, the idea, theory and methods of three-way decision have been successfully applied to various domains. However, the current three-way decision has two following limitations. On the one hand, the narrow three-way decision associated with rough sets either has trouble processing contin...
Pawlak rough set (PRS) and neighborhood rough set (NRS) are the two most common rough set theoretical models. Although the PRS can use equivalence classes to represent knowledge, it is unable to process continuous data. On the other hand, NRSs, which can process continuous data, rather lose the ability of using equivalence classes to represent know...
Joint relational triple extraction treats entity recognition and relation extraction as a joint task to extract relational triples, and this is a critical task in information extraction and knowledge graph construction. However, most existing joint models still fall short in terms of extracting overlapping triples. Moreover, these models ignore the...
Feature selection method with rough sets based on incremental learning has the major advantage of the higher efficiency in a dynamic information system, which has attracted extensive research. However, the incremental approximation feature selection with an accelerator (IAFSA) remains ambiguous for a dynamic information system with fuzzy decisions...
As one of the rapidly developing methodologies for dealing with complex problems in line with human cognition, granular computing has made significant achievements in knowledge discovery. Neighborhood classifier, as a typical description of granular computing, is an effective method for the classification of continuous data. However, in the phase o...
Granular computing, a new paradigm for solving large-scale and complex problems, has made significant progresses in knowledge discovery. Granular ball computing (GBC) is a novel granular computing method, which can rapidly generate scalable and robust information granules, that is, granular balls. However, a comprehensive index for measuring the pe...
In order to solve the problem that the traditional spectral clustering algorithm is time-consuming and resource consuming when applied to large-scale data, resulting in poor clustering effect or even unable to cluster, this paper proposes a spectral clustering algorithm based on granular-ball(GBSC). The algorithm changes the construction method of...
Density peaks clustering algorithm (DP) has difficulty in clustering large-scale data, because it requires the distance matrix to compute the density and
$\delta$
-distance for each object, which has
$O(n^2)$
time complexity. Granular ball (GB) is a coarse-grained representation of data. It is based on the fact that an object and its local neig...
Gaussian mixture model (GMM) is widely used in many domains, e.g. data mining. The unsupervised learning of the finite mixture (ULFM) model based on the minimum message length (MML) criterion for mixtures enables adaptive model selection and parameter estimates. However, some datasets have a hierarchical structure. If the MML criterion does not con...
At present, image completion models are often used to handle images in public datasets and are not competent for tasks in practical scenarios such as USV scenes. On one hand, the practical missing regions are often located at the boundaries, which presents a challenge for the model to extract image features. On the other hand, real images are often...
Machine understanding and thinking require prior knowledge consisting of explicit and implicit knowledge. The current knowledge base contains various explicit knowledge but not implicit knowledge. As part of implicit knowledge, the typical characteristics of the things referred to by the concept are available by concept cognition for knowledge grap...
Unmanned Aerial Vehicles (UAVs) play an important role in the Internet of Things (IoT) , and form the paradigm of the Internet of UAVs, due to their characteristics of flexibility, mobility and low costs. However, resource constraints such as dynamic wireless channels, limited battery capacities and computation resources of UAVs make traditional me...
Granular ball computing (GBC), as an efficient, robust, and scalable learning method, has become a popular research topic of granular computing. GBC includes two stages: granular ball generation (GBG) and multi-granularity learning based on the granular ball (GB). However, the stability and efficiency of existing GBG methods need to be further impr...
From the perspective of human cognition, three-way decision (3WD) explores thinking, problem solving, and information processing in three paradigms. Rough fuzzy sets (RFS) are constructed to handle fuzzy concepts by extending the classical rough sets. In three-way decision with rough fuzzy sets (3WDRFS), current works are mainly concerned with calc...
Human cognition has a ``large-scale first'' cognitive mechanism, therefore possesses adaptive multi-granularity description capabilities. This results in computational characteristics such as efficiency, robustness, and interpretability. Although most existing artificial intelligence learning methods have certain multi-granularity features, they do...
Hierarchical quotient space structure (HQSS), as a typical description of granular computing (GrC), focuses on hierarchically granulating fuzzy data and mining hidden knowledge. The key step of constructing HQSS is to transform the fuzzy similarity relation into fuzzy equivalence relation. However, on one hand, the transformation process has high t...
In recent years, the problem of fuzzy clustering has been widely concerned. The membership iteration of existing methods is mostly considered globally, which has considerable problems in noisy environments, and iterative calculations for clusters with a large number of different sample sizes are not accurate and efficient. In this paper, starting f...
Most of the existing clustering methods are based on a single granularity of information, such as the distance and density of each data. This most fine-grained based approach is usually inefficient and susceptible to noise. Therefore, we propose a clustering algorithm that combines multi-granularity Granular-Ball and minimum spanning tree (MST). We...
Due to simplicity, K-means has become a widely used clustering method. However, its clustering result is seriously affected by the initial centers and the allocation strategy makes it hard to identify manifold clusters. Many improved K-means are proposed to accelerate it and improve the quality of initialize cluster centers, but few researchers pay...
In some specific scenarios, face sketch was used to identify a person. However, drawing a complete face sketch often needs skills and takes time, which hinder its widespread applicability in the practice. In this study, we proposed a new task named sketch less face image retrieval (SLFIR), in which the retrieval was carried out at each stroke and a...
User alignment aims to identify accounts of one natural person across networks. Nevertheless, different social purposes in multiple networks and randomness of following friends form the diverse local structures of the same person, leading to a high degree of non-isomorphism across networks. The edges resulting in non-isomorphism are harmful to lear...
Community structure can be used to analyze and understand the structural functions in a network, reveal its implicit information, and predict its dynamic development pattern. Existing community detection algorithms are very sensitive to the sparsity of network, and they have difficulty in obtaining stable community detection results. To address the...
Granular computing (GrC) is an efficient way to reveal descriptions of data in line with human cognition and plays a critical role in knowledge discovery. Information granules (IGs), the basic computing unit of GrC, are key components of knowledge representation and processing. Rough sets are one of the classical GrC models and generate IGs based o...
Feature selection achieves dimensionality reduction by selecting some effective features from the original feature set. However, in the process of feature selection, most conventional methods do not accurately describe various correlations between features and the dynamic changes of the relation, leading to an incomplete definition of the evaluatio...