As the dimensionality of the decision space in multi-objective optimization problems increases, the decision space expands exponentially, presenting significant challenges to the search efficiency of traditional multi-objective evolutionary algorithms in large-scale multi-objective optimization problems. To quickly locate promising search regions in the vast decision space, this paper proposes utilizing denoising diffusion probabilistic models to generate promising solutions, based on which a novel elite-guided large-scale multi-objective evolutionary algorithm is introduced. Specifically, in our proposed method, the population is divided into elite and poor solutions, with each poor solution paired with an elite solution. The elite solutions serve as generation targets, and their paired poor solutions act as conditions during the training of the generative model. Our approach allows the model to not only capture the distribution of elite solutions but also effectively model the evolutionary trajectory from poor solutions to elite solutions. The entire population is used as conditions, and the trained generative model generates ideal positions, which are then updated to produce offspring solutions. Experimental results on large-scale multi-objective benchmark functions demonstrate that the proposed algorithm outperforms four state-of-the-art large-scale multi-objective evolutionary algorithms.

Missing data in spatiotemporal systems presents a significant challenge for modern applications, ranging from environmental monitoring to urban traffic management. The integrity of spatiotemporal data often deteriorates due to hardware malfunctions and software failures in real-world deployments. Current approaches based on machine learning and deep learning struggle to model the intricate interdependencies between spatial and temporal dimensions effectively and, more importantly, suffer from cumulative errors during the data imputation process, which propagate and amplify through iterations. To address these limitations, we propose CoFILL, a novel Conditional Diffusion Model for spatiotemporal data imputation. CoFILL builds on the inherent advantages of diffusion models to generate high-quality imputations without relying on potentially error-prone prior estimates. It incorporates an innovative dual-stream architecture that processes temporal and frequency domain features in parallel. By fusing these complementary features, CoFILL captures both rapid fluctuations and underlying patterns in the data, which enables more robust imputation. The extensive experiments demonstrate that CoFILL's noise prediction network successfully transforms random noise into meaningful values that align with the true data distribution. The results also show that CoFILL outperforms state-of-the-art methods in terms of imputation accuracy. The source code is publicly available at https://github.com/joyHJL/CoFILL.

BACKGROUND AND OBJECTIVE: Timely treatment is crucial for cancer patients, so it's important to administer the appropriate treatment as soon as possible. Because individuals can respond differently to a given drug due to their unique genomic profiles, we aim to use their genomic information to predict how various drugs will affect them and determine the best course of treatment. METHODS: We present Kernelized Residual Stacking (KRS), a new multi-task learning approach, and use it to predict the responses to anti-cancer drugs based on genomic data. We demonstrate the superior predictive performance of KRS, outperforming popular competitors, by utilizing the Genomics of Drug Sensitivity in Cancer (GDSC) study and the Cancer Cell Line Encyclopedia (CCLE) study. Downstream analysis of feature genes selected by KRS is conducted to discover novel therapies. RESULTS: We used two genomic studies to show that KRS outperforms a few popular competitors in predicting drugs' susceptibilities. Through downstream analysis of feature genes selected by KRS, we found that the PI3K-Akt pathway could alter drugs' susceptibilities, and its expression correlated positively with the hub gene ERBB2. We discovered eight novel small molecules based on these feature genes, which could be developed into novel combination therapies with anti-cancer drugs. CONCLUSIONS: KRS outperforms competitors in prediction performance and selects feature genes highly correlated with drugs' susceptibilities. Novel biological results are found by investigating KRS's feature genes.

This article focuses on addressing the issue of asynchronous${H_\infty}$control for Takagi-Sugeno (T-S) fuzzy Markov jump systems with generally incomplete transition probabilities (TPs). The delay is assumed to vary periodically, resulting in one monotonically increasing interval and one monotonically decreasing interval during each period. Meanwhile, a new Lyapunov-Krasovskii functional (LKF) is devised, which depends on membership functions (MFs) and two looped functions formulated for the monotonic intervals. Since the modes and TPs of the original system are assumed to be unavailable, an asynchronous switching fuzzy controller on the basis of hidden Markov model is proposed to stabilize the fuzzy Markov jump systems (FMJSs) with generally incomplete TPs. Consequently, a stability criterion with improved practicality and reduced conservatism is derived, ensuring the stochastic stability and${H_\infty}$performance of the closed-loop system. Finally, this technique is employed to the tunnel diode circuit system, and a comparison example is given, which verifies the practicality and superiority of the method.Note to Practitioners—As a category of stochastic hybrid nonlinear systems driven by continuous time and discrete events, FMJSs have significant applications in practical engineering such as aircraft control systems and large-scale manufacturing systems. However, the real-time acquisition of system mode information and TPs is difficult due to technological constraints and limited resources. Moreover, the presence of periodically varying delay is prevalent in many industrial processes, resulting in degradation of dynamic system performance and instability. Therefore, it is necessary to study the FMJSs with generally incomplete TPs and periodically varying delays in asynchronous framework. Accordingly, unlike previous work, the designed LKF relies on system modes, MFs, and two looped functions for monotonic intervals. This new LKF exhibits a high degree of flexibility, fully leveraging the information of MFs and periodically varying delays, which can significantly reduce conservatism.

Anomaly detection is playing an increasingly important role in Internet of Things applications since anomalous events may cause some damage to the physical–social environment monitored by different kinds of smart object devices. In some cases, the occurrence of an anomalous event is caused by the fusion impact derived from several primary monitoring factors. Considering this, we propose a novel anomaly detection mechanism for the events with multiple decisive primary attributes in a collaborative device–edge–cloud architecture, in which a propagation and influence-based correlation is further explored in the edge layer for improving the detection efficiency. During the detection process, multiple primary attributes first cooperate to detect an anomaly in the edge layer in advance. If an anomaly occurs in the subregion managed by an edge device, social-aware interaction relationships between edge devices are further integrated to give a guidance on the detection of correlative anomaly in neighbor subregions. The cloud further analyzes the primary attributes information and the interaction relationship to determine the secondary attributes that are helpful in identifying the final anomaly. A large number of experiments show that our method is superior to the alternative methods in terms of energy consumption, detection time, and accuracy.

Anomaly event coverage is usually related to several attributes, among which the primary attribute dominates at the time of improving detection efficiency. In the case of Internet of Things (IoT) devices with complex social-aware relationships, IoT nodes with primary attributes should cooperate with each other through their social-aware interactions, to detect potential event anomalies and further determine the coverage of such anomalies. Existing research has put a lot of effort into designing IoT detection frameworks to discover anomalous sensor data, rarely caring about the social-aware interactions. This paper targets this important efficiency problem, and develops a novel anomaly detection mechanism in collaborative social-edge-cloud architecture. The focus of it is to first construct a vector space based Aggregation Behavior Comparison Detection Model, and quantify the change of monitoring behavior by defining the clustering threshold of vector space. This can quickly judge whether a local social network is abnormal and speed up the abnormal detection rate. If it is, a Social Behavior Correlation Detection Model is further designed based on the correlation of primary attributes derived from the dominating social-aware interaction behavior captured by (primary) edge nodes. This strategy can help detect specific “abnormal” areas managed by one or more edge devices with higher accuracy. In the process of anomaly detection, we also propose a spatial index tree to store the information of IoT nodes, so as to effectively collect and route the perceived data of IoT nodes for anomaly analysis. Experimental results demonstrate that our anomaly detection method promotes the detection efficiency and accuracy in comparison with the state of art’s techniques.

Edge computing is a popular paradigm in solving the problems of long time delay and high energy consumption in Internet of Things (IoT) network, which can effectively realize the IoT task offloading by collaboration of multiple edge servers. Nevertheless, how to choose the appropriate edge servers for offloading the dependent subtasks is still a big challenge, considering the limited resources and computing power of the edge servers as well as the start and end execution time of each subtask. These factors have a great impact on the execution efficiency of the whole task. At present, most of the research works focus on single-hop or multi-hop task offloading, where the edge servers farther away are not considered in the offloading decision. Such task offloading strategy is not optimal, and difficult to achieve high parallel execution of tasks, resulting in some delay-sensitive tasks not being completed within the specified time. In this paper, a two-stage optimization method is proposed to solve the resource allocation problem between edge servers and tasks. In the first stage, we group tasks according to their priorities, and the group with a higher priority is given the preference to resource allocation, thereby ensuring the timeliness of delay-sensitive tasks. Within the same group, resources are competed according to the game theory, and the total delay of all tasks is optimized. In the second stage, we aim to optimize the energy consumption of each task without increasing its completion time by allocating the computing resources to its subtasks based on their maximum completion time. For group resource allocation, we propose a spatial index tree to store the information of all edge servers for optimal server selection. During the selection process, an online learning based double prediction model is utilized to reduce the energy consumption caused by information transmission. We have evaluated the performance of the experiment on iFogSim simulator, and the experimental results show that our proposed method can achieve better performance in terms of time delay and energy consumption.

By interpreting Graph Neural Networks (GNNs) as the message passing from the spatial perspective, their success is attributed to Laplacian smoothing. However, it also leads to serious over-smoothing issue by stacking many layers. Recently, many efforts have been paid to overcome this issue in semi-supervised learning. Unfortunately, it is more serious in unsupervised node representation learning task due to the lack of supervision information. Thus, most of the unsupervised or self-supervised GNNs often employ \textit{one-layer GCN} as the encoder. Essentially, the over-smoothing issue is caused by the over-simplification of the existing message passing, which possesses two intrinsic limits: blind message and uniform passing. In this paper, a novel Diverse and Interactive Message Passing (DIMP) is proposed for self-supervised learning by overcoming these limits. Firstly, to prevent the message from blindness and make it interactive between two connected nodes, the message is determined by both the two connected nodes instead of the attributes of one node. Secondly, to prevent the passing from uniformness and make it diverse over different attribute channels, different propagation weights are assigned to different elements in the message. To this end, a natural implementation of the message in DIMP is the element-wise product of the representations of two connected nodes. From the perspective of numerical optimization, the proposed DIMP is equivalent to performing an overlapping community detection via expectation-maximization (EM). Both the objective function of the community detection and the convergence of EM algorithm guarantee that DMIP can prevent from over-smoothing issue. Extensive evaluations on node-level and graph-level tasks demonstrate the superiority of DIMP on improving performance and overcoming over-smoothing issue.

Graph Neural Networks have been widely employed for multimodal fusion and embedding. To overcome over-smoothing issue, residual connections, which are designed for alleviating vanishing gradient problem in NNs, are adopted in Graph Neural Networks (GNNs) to incorporate local node information. However, these simple residual connections are ineffective on networks with heterophily, since the roles of both convolutional operations and residual connections in GNNs are significantly different from those in classic NNs. By considering the specific smoothing characteristic of graph convolutional operation, deep layers in GNNs are expected to focus on the data which can't be properly handled in shallow layers. To this end, a novel and universal Difference Residual Connections (DRC), which feed the difference of the output and input of previous layer as the input of the next layer, is proposed. Essentially, Difference Residual Connections is equivalent to inserting layers with opposite effect (e.g., sharpening) into the network to prevent the excessive effect (e.g., over-smoothing issue) induced by too many layers with the similar role (e.g., smoothing) in GNNs. From the perspective of optimization, DRC is the gradient descent method to minimize an objective function with both smoothing and sharpening terms. The analytic solution to this objective function is determined by both graph topology and node attributes, which theoretically proves that DRC can prevent over-smoothing issue. Extensive experiments demonstrate the superiority of DRC on real networks with both homophily and heterophily, and show that DRC can automatically determine the model depth and be adaptive to both shallow and deep models with two complementary components.

Although existing Graph Neural Networks (GNNs) based on message passing achieve state-of-the-art, the over-smoothing issue, node similarity distortion issue and dissatisfactory link prediction performance can’t be ignored. This paper summarizes these issues as the interference between topology and attribute for the first time. By leveraging the recently proposed optimization perspective of GNNs, this interference is analyzed and ascribed to that the learned representation in GNNs essentially compromises between the topology and node attribute. To alleviate the interference, this paper attempts to break this compromise by proposing a novel objective function, which fits node attribute and topology with different representations and introduces mutual exclusion constraints to reduce the redundancy in both representations. The mutual exclusion employs the statistical dependence, which regards the representations from topology and attribute as the observations of two random variables, and is implemented with Hilbert-Schmidt Independence Criterion. Derived from the novel objective function, a novel GNN, i.e., Graph Neural Network Beyond Compromise (GNN-BC), is proposed to iteratively updates the representations of topology and attribute by simultaneously capturing semantic information and removing the common information, and the final representation is the concatenation of them. The performance improvements on node classification and link prediction demonstrate the superiority of GNN-BC on relieving the interference.

Recently, a switching method is applied to deal with the membership function-dependent Lyapunov-Krasovskii functional (LKF) for fuzzy systems with time delay; however, the Lyapunov matrices are only linear dependent on the grades of membership which leads to linear switching (Wang and Lam, 2019). In this article, the linear dependence on the grades of membership is extended to homogenous polynomially membership function dependent (HPMFD) and the linear switching is extended to polynomial matrix switching, based on which the obtained result contains the previous one as a special case. Furthermore, in order to fully use the introduced variables without speial structure, an iteration algorithm is designed to construct the switching controller and the initial condition of the algorithm is also discussed. The final simulation demonstrates the effectiveness of the developed new results.

Although many graph convolutional neural networks (GCNNs) have achieved superior performances in semisupervised node classification, they are designed from either the spatial or spectral perspective, yet without a general theoretical basis. Besides, most of the existing GCNNs methods tend to ignore the ubiquitous noises in the network topology and node content and are thus unable to model these uncertainties. These drawbacks certainly reduce their effectiveness in integrating network topology and node content. To provide a probabilistic perspective to the GCNNs, we model the semisupervised node classification problem as a topology-constrained probabilistic latent space model, probabilistic graph convolutional network (PGCN). By representing the nodes in a more efficient distribution form, the proposed framework can seamlessly integrate the node content and network topology. When specifying the distribution in PGCN to be a Gaussian distribution, the transductive node classification problems can be solved by the general framework and a specific method, called PGCN with the Gaussian distribution representation (PGCN-G), is proposed. To overcome the overfitting problem in covariance estimation and reduce the computational complexity, PGCN-G is further improved to PGCN-G+ by imposing the covariance matrices of all vertices to possess the identical singular vectors. The optimization algorithm based on expectation-maximization indicates that the proposed method can iteratively denoise the network topology and node content with respect to each other. Besides the effectiveness of this top-down framework demonstrated via extensive experiments, it can also be deduced to cover the existing methods, graph convolutional network, graph attention network, and Gaussian mixture model and elaborate their characteristics and relationships by specific derivations.

Many efforts have been paid to enhance Graph Convolutional Network from the perspective of propagation under the philosophy that ``Propagation is the essence of the GCNNs". Unfortunately, its adverse effect is over-smoothing, which makes the performance dramatically drop. To prevent the over-smoothing, many variants are presented. However, the perspective of propagation can't provide an intuitive and unified interpretation to their effect on prevent over-smoothing. In this paper, we aim at providing a novel explanation to the question of "Why do attributes propagate in GCNNs?''. which not only gives the essence of the oversmoothing, but also illustrates why the GCN extensions, including multi-scale GCN and GCN with initial residual, can improve the performance. To this end, an intuitive Graph Representation Learning (GRL) framework is presented. GRL simply constrains the node representation similar with the original attribute, and encourages the connected nodes possess similar representations (pairwise constraint). Based on the proposed GRL, exiting GCN and its extensions can be proved as different numerical optimization algorithms, such as gradient descent, of our proposed GRL framework. Inspired by the superiority of conjugate gradient descent compared to common gradient descent, a novel Graph Conjugate Convolutional (GCC) network is presented to approximate the solution to GRL with fast convergence. Specifically, GCC adopts the obtained information of the last layer, which can be represented as the difference between the input and output of the last layer, as the input to the next layer. Extensive experiments demonstrate the superior performance of GCC.

Most attempts on extending Graph Neural Networks (GNNs) to Heterogeneous Information Networks (HINs) implicitly take the direct assumption that the multiple homogeneous attributed networks induced by different meta-paths are complementary. The doubts about the hypothesis of complementary motivate an alternative assumption of consensus. That is, the aggregated node attributes shared by multiple homogeneous attributed networks are essential for node representations, while the specific ones in each homogeneous attributed network should be discarded. In this paper, a novel Heterogeneous Graph Information Bottleneck (HGIB) is proposed to implement the consensus hypothesis in an unsupervised manner. To this end, information bottleneck (IB) is extended to unsupervised representation learning by leveraging self-supervision strategy. Specifically, HGIB simultaneously maximizes the mutual information between one homogeneous network and the representation learned from another homogeneous network, while minimizes the mutual information between the specific information contained in one homogeneous network and the representation learned from this homogeneous network. Model analysis reveals that the two extreme cases of HGIB correspond to the supervised heterogeneous GNN and the infomax on homogeneous graph, respectively. Extensive experiments on real datasets demonstrate that the consensus-based unsupervised HGIB significantly outperforms most semi-supervised SOTA methods based on complementary assumption.

In this article, the homogenous polynomially membership functions dependent (HPMFD) matrices are used to study the interval type-2 Takagi-Sugeno fuzzy systems. First, some necessary notations of the HPMFD matrices are introduced. Next, based on these notations, the time derivative of the HPMFD matrices is discussed and a switching method is proposed to ensure that the time derivative of the HPMFD matrices is negative. Then, a HPMFD controller is designed and new stabilization conditions are obtained by using the HPMFD Lyapunov function. In the end, the simulations show that the method in this article is less conservative than the existing ones in the literatures.

Most of the existing Graph Neural Networks (GNNs) are deliberately designed for semi-supervised learning tasks, where supervision information (labelled node) is utilized to mitigate the oversmoothing problem of message passing. Unfortunately, the oversmoothing problem tends to be more severe in unsupervised tasks, since supervision information is not available. Since community structure/cluster is an essential characteristic of network, a natural approach to reduce the oversmoothing problem is to also constrain the node embeddings to maintain their own characteristics to prevent all the node embeddings from becoming too similar to be distinguished. In this paper, a novel Optimal Transport based Graph Neural Network (OT-GNN) is proposed to overcome the oversmoothing problem in unsupervised GNNs by imposing the equal-sized clustering constraints to the obtained node embeddings. To solve the combinatorial optimization problem, the constrained objective function of unsupervised GNN is relaxed to an Optimal Transport problem, and a fast version of the Sinkhorm-Knopp algorithm is adopted to handle large networks. Extensive experiments on node clustering and classification demonstrate the superior performance of our proposed OT-GNN.

Motivated by the capability of Generative Adversarial Network on exploring the latent semantic space and capturing semantic variations in the data distribution, adversarial learning has been adopted in network embedding to improve the robustness. However, this important ability is lost in existing adversarially regularized network embedding methods, because their embedding results are directly compared to the samples drawn from perturbation (Gaussian) distribution without any rectification from real data. To overcome this vital issue, a novel Joint Adversarial Network Embedding (JANE) framework is proposed to jointly distinguish the real and fake combinations of the embeddings, topology information and node features. JANE contains three pluggable components, Embedding module, Generator module and Discriminator module. The overall objective function of JANE is defined in a min-max form, which can be optimized via alternating stochastic gradient. Extensive experiments demonstrate the remarkable superiority of the proposed JANE on link prediction (3% gains in both AUC and AP) and node clustering (5% gain in F1 score).

Existing topic modeling approaches possess several issues, including the overfitting issue of Probablistic Latent Semantic Indexing (pLSI), the failure of capturing the rich topical correlations among topics in Latent Dirichlet Allocation (LDA), and high inference complexity. In this paper, we provide a new method to overcome the overfitting issue of pLSI by using the amortized inference with word embedding as input, instead of the Dirichlet prior in LDA. For generative topic model, the large number of free latent variables is the root of overfitting. To reduce the number of parameters, the amortized inference replaces the inference of latent variable with a function which possesses the shared (amortized) learnable parameters. The number of the shared parameters is fixed and independent of the scale of the corpus. To overcome the limited application of amortized inference to independent and identically distributed (i.i.d) data, a novel graph neural network, Graph Attention TOpic Network (GATON), is proposed to model the topic structure of non-i.i.d documents according to the following two observations. First, pLSI can be interpreted as stochastic block model (SBM) on a specific bi-partite graph. Second, graph attention network (GAT) can be explained as the semi-amortized inference of SBM, which relaxes the i.i.d data assumption of vanilla amortized inference. GATON provides a novel scheme, i.e. graph convolution operation based scheme, to integrate word similarity and word co-occurrence structure. Specifically, the bag-of-words document representation is modeled as a bi-partite graph topology. Meanwhile, word embedding, which captures the word similarity, is modeled as attribute of the word node and the term frequency vector is adopted as the attribute of the document node. Based on the weighted (attention) graph convolution operation, the word co-occurrence structure and word similarity patterns are seamlessly integrated for topic identification. Extensive experiments demonstrate that the effectiveness of GATON on topic identification not only benefits the document classification, but also significantly refines the input word embedding.

BACKGROUND: The interactions between proteins and aptamers are prevalent in organisms and play an important role in various life activities. Thanks to the rapid accumulation of protein-aptamer interaction data, it is necessary and feasible to construct an accurate and effective computational model to predict aptamers binding to certain interested proteins and protein-aptamer interactions, which is beneficial for understanding mechanisms of protein-aptamer interactions and improving aptamer-based therapies. RESULTS: In this study, a novel web server named PPAI is developed to predict aptamers and protein-aptamer interactions with key sequence features of proteins/aptamers and a machine learning framework integrated adaboost and random forest. A new method for extracting several key sequence features of both proteins and aptamers is presented, where the features for proteins are extracted from amino acid composition, pseudo-amino acid composition, grouped amino acid composition, C/T/D composition and sequence-order-coupling number, while the features for aptamers are extracted from nucleotide composition, pseudo-nucleotide composition (PseKNC) and normalized Moreau-Broto autocorrelation coefficient. On the basis of these feature sets and balanced the samples with SMOTE algorithm, we validate the performance of PPAI by the independent test set. The results demonstrate that the Area Under Curve (AUC) is 0.907 for prediction of aptamer, while the AUC reaches 0.871 for prediction of protein-aptamer interactions. CONCLUSION: These results indicate that PPAI can query aptamers and proteins, predict aptamers and predict protein-aptamer interactions in batch mode precisely and efficiently, which would be a novel bioinformatics tool for the research of protein-aptamer interactions. PPAI web-server is freely available at http://39.96.85.9/PPAI.

The success of graph convolutional neural networks (GCNNs) based semi-supervised node classification is credited to the attribute smoothing (propagating) over the topology. However, the attributes may be interfered by the utilization of the topology information. This distortion will induce a certain amount of misclassifications of the nodes, which can be correctly predicted with only the attributes. By analyzing the impact of the edges in attribute propagations, the simple edges, which connect two nodes with similar attributes, should be given priority during the training process compared to the complex ones according to curriculum learning. To reduce the distortions induced by the topology while exploit more potentials of the attribute information, Dual Self-Paced Graph Convolutional Network (DSP-GCN) is proposed in this paper. Specifically, the unlabelled nodes with confidently predicted labels are gradually added into the training set in the node-level self-paced learning, while edges are gradually, from the simple edges to the complex ones, added into the graph during the training process in the edge-level self-paced learning. These two learning strategies are designed to mutually reinforce each other by coupling the selections of the edges and unlabelled nodes. Experimental results of transductive semi-supervised node classification on many real networks indicate that the proposed DSP-GCN has successfully reduced the attribute distortions induced by the topology while it gives superior performances with only one graph convolutional layer.

Semi-supervised classification is a fundamental technology to process the structured and unstructured data in machine learning field. The traditional attribute-graph based semi-supervised classification methods propagate labels over the graph which is usually constructed from the data features, while the graph convolutional neural networks smooth the node attributes, i.e., propagate the attributes, over the real graph topology. In this paper, they are interpreted from the perspective of propagation, and accordingly categorized into symmetric and asymmetric propagation based methods. From the perspective of propagation, both the traditional and network based methods are propagating certain objects over the graph. However, different from the label propagation, the intuition ``the connected data samples tend to be similar in terms of the attributes", in attribute propagation is only partially valid. Therefore, a masked graph convolution network (Masked GCN) is proposed by only propagating a certain portion of the attributes to the neighbours according to a masking indicator, which is learned for each node by jointly considering the attribute distributions in local neighbourhoods and the impact on the classification results. Extensive experiments on transductive and inductive node classification tasks have demonstrated the superiority of the proposed method.

In this paper, we present an ant colony-based heuristic to solve QoS (quality of service) constrained multicast routing problems. Our algorithm considers multiple QoS metrics, such as bandwidth, delay, delay jitter and packet loss rate, to find the multicast tree that minimizes the total cost. We also explore the scalability of the ant algorithm. Our tests show that the algorithm can find optimal (or near-optimal) solutions quickly and that it has good scalability.