Spectral Graph Neural Networks process graph signals using the spectral properties of the normalized graph Laplacian matrix. However, the frequent occurrence of repeated eigenvalues limits the expressiveness of spectral GNNs. To address this, we propose a higher-dimensional sheaf Laplacian matrix, which not only encodes the graph's topological information but also increases the upper bound on the number of distinct eigenvalues. The sheaf Laplacian matrix is derived from carefully designed perturbations of the block form of the normalized graph Laplacian, yielding a perturbed sheaf Laplacian (PSL) matrix with more distinct eigenvalues. We provide a theoretical analysis of the expressiveness of spectral GNNs equipped with the PSL and establish perturbation bounds for the eigenvalues. Extensive experiments on benchmark datasets for node classification demonstrate that incorporating the perturbed sheaf Laplacian enhances the performance of spectral GNNs.

Graph machine learning (GML) has made great progress in node classification, link prediction, graph classification, and so on. However, graphs in reality are often structurally imbalanced, that is, only a few hub nodes have a denser local structure and higher influence. The imbalance may compromise the robustness of existing GML models, especially in learning tail nodes. This article proposes a selective graph augmentation method to solve this problem. Firstly, a Pagerank-based sampling strategy is designed to identify hub nodes and tail nodes in the graph. Secondly, a selective augmentation strategy is proposed, which drops the noise neighbors of hub nodes on one side, and discovers the latent neighbors and generates pseudo neighbors for tail nodes on the other side. Also, it can alleviate the structural imbalance between two types of nodes. Finally, a GNN model is retrained on the augmented graph. Extensive experiments demonstrate that the proposed method can significantly improve the backbone GNNs and achieve superior performance to its competitors of graph augmentation methods and hub/tail aware methods.

Virtualization technologies provide solutions for cloud computing. Virtual resource scheduling is a crucial task in data centers, and the power consumption of virtual resources is a critical foundation of virtualization scheduling. Containers are the smallest unit of virtual resource scheduling and migration. Although many practical models for estimating the power consumption of virtual machines (VMs) have been proposed, few power estimation models of containers have been put forth. In this paper, we propose a fast-training piecewise regression model based on a decision tree for VM power metering and estimate the power of containers configured on the VM by treating the container as a group of processes on the VM. We select appropriate features from the collected metrics of VMs/containers to help our model fit the nonlinear relationship between power and features well. Besides, we optimize the leaf nodes of the regression tree, realizing the effective power metering of virtualization environments. We evaluate the proposed model on 13 tasks in PARSEC and compare it with several commonly used models in data centers. The experimental results prove the effectiveness of the proposed model, and the estimated power of containers is in line with expectations.

Power forecasting has a guiding effect on power-aware scheduling strategies to reduce unnecessary power consumption in data centers. Many metrics related to power consumption can be collected in physical servers, such as the status of CPU, memory, and other components. However, most existing methods empirically exploit a small number of metrics to forecast power consumption. To this end, this article uses feature selection based on causality to explore the metrics that strongly influence the power consumption of different tasks. Moreover, we propose a tensor-based dual-stage attention LSTM to forecast the non-linear and non-periodic power consumption. In the proposed model, a multi-way delay embedding transform is utilized to convert the time series into tensors along the temporal direction. The LSTM combines with the tensor technique and the attention mechanism to capture the temporal pattern effectively. In addition, we adopt the cost-sensitive loss function to optimize the specific power forecasting problem in data centers. The experimental results demonstrate that our method can achieve up to 1.4% to 4.3% forecasting accuracy improvement compared with the state-of-the-art models.

Summary Due to the rapid increase in the number and scale of data centers, the information and communication technology (ICT) equipment in data centers consumes an enormous amount of power. A power prediction model is therefore essential for decision‐making optimization and power management of ICT equipment. However, it is difficult to predict the power consumption of data centers accurately due to the complex power patterns and nonlinear interdependencies among components. Existing methods either rely on standard formulas, or simply treat it as time series, both leading to poor power prediction accuracy. To overcome those limitations, in this article, we present a systematic power prediction framework called characteristic aware attention‐augmented deep learning‐based prediction method. In particular, we first analyze the different power consumption series to illustrate their different temporal characteristics. Second, we perform different data processing for the corresponding characteristics of power series samples. Third, we propose an accurate and efficient neural network model to predict future power consumption with the pretreated data. The experimental results show that the proposed model is able to achieve superior prediction accuracy.

Virtualization technologies provide solutions of cloud computing. Virtual resource scheduling is a crucial task in data centers, and the power consumption of virtual resources is a critical foundation of virtualization scheduling. Containers are the smallest unit of virtual resource scheduling and migration. Although many effective models for estimating power consumption of virtual machines (VM) have been proposed, few power estimation models of containers have been put forth. In this paper, we offer a fast-training piecewise regression model based on decision tree to build a VM power estimation model and estimate the containers' power by treating the container as a group of processes on the VM. In our model, we characterize the nonlinear relationship between power and features and realize the effective estimation of the containers on the VM. We evaluate the proposed model on 13 workloads in PARSEC and compare it with several models. The experimental results prove the effectiveness of our proposed model on most workloads. Moreover, the estimated power of the containers is in line with expectations.

In recent years, many researchers have started to construct Graph Neural Networks (GNNs) to deal with graph classification task. Those GNNs can fit into a framework named Message Passing Neural Networks (MPNNs), which consists of two phases: a Message Passing phase used for updating node embeddings and a Readout phase. In Readout phase, node embeddings are aggregated to extract graph feature used for classification. However, the above operation may obscure the effect of the node embedding of each node on graph classification. Therefore, a node voting based graph classification model is proposed in this paper, called Node Voting net (NVnet). Similar to the MPNNs, NVnet also contains the Message Passing phase. The main differences between NVnet and MPNNs are: 1, A decoder for graph reconstruction is added to NVnet to make node embeddings contain graph structure information as much as possible; 2, In NVnet, the Readout phase is replaced by a new phase called Node Voting phase. In this new phase, an attention layer based on the gate mechanism is constructed to help each node to observe the node embeddings of other nodes in the graph, and each node predicts the class of the graph from its own perspective. The above process is called node voting. After voting, the results of all nodes are aggregated to get the final graph classification result. In addition, considering that aggregation operation may also obscure the differences between node voting results, a regularization term is added to drive node voting results to reach group consensus. We evaluate the performance of NVnet on 4 benchmark datasets. The experimental results show that NVnet performs well on graph classification task.

Most Graph Convolutional Networks (GCNs) used for graph classification task can fit into the Message Passing Neural Networks (MPNNs) framework. However, traditional MPNNs don't consider global information in the message passing phase in which the node embeddings are updated. In this paper, we propose a new model called Cross Message Passing Graph Neural Network (CMPGNN). The new model consists of two message passing phases, of which one is the local message passing phase used for node embeddings updating and another is the global message passing phase used for graph feature updating. Several convolutional layers are stacked together in the local message passing phase, in which different convolutional layers are used to update the node embeddings at different time steps. Each convolutional layer updates node embeddings not only according to the outputs calculated at the previous convolutional layer but also to the graph feature calculated at the previous time step. A readout layer shared by all time steps is used in the global message passing phase. At each time step, after the node embeddings are updated, the readout layer aggregates the embeddings of all nodes by using a global gated network, and feeds the aggregation result into a Gated Recurrent Unit (GRU) to update the graph feature.The above two message passing phases are executed alternatively. After all time steps, the graph feature obtained by the readout layer is fed into a MultiLayer perception for graph classification. We evaluate the performance of CMPGNN on 6 graph classification datasets. Experimental results show that compared with other 10 baselines, CMPGNN achieves the highest accuracy on 4 of the 6 benchmark datasets.

With the development of location-based social networks (LBSNs), Point-of-Interest (POI) recommendation has attracted lots of attention. Most of the existing studies focus on recommending POIs to users based on their recent check-ins. However, the recent check-ins may contain some daily check-ins that users are not really interested in. If a model treats the recent check-ins equally, it is non-trivial to capture the actual preference of users. To address the issue of mining the actual preferences of users in the POI recommendation, we propose an attention-based deep learning POI recommendation framework (ADPR), which consists of a latent representation method and an attention-based deep convolutional neural network. To learn the embedding of users and POIs, we propose a latent representation method, which incorporates the geographical influence and the categories of POIs to capture the relationships between POIs better. Further, we propose an attention-based deep convolutional neural network, which employs the attention mechanism to filter the important information in the recent check-ins, to recommend POIs to users based on the latent representations of users and the recent check-ins. We conduct experiments on a real-world LBSN dataset to evaluate our framework, and the experimental results show the effectiveness of our framework.

Movie investors seek for high box-office revenue. Usually, it is not an easy task for investors to estimate the return on their invests for movies, due to the complicated factors that could impact the box-office revenue, such as movie stars' appeal, potential audience reactions, movie genre, and so on. In this paper, we design and implement SMAS, an investor-oriented Social Media Analysis System focusing on movie invests, which provides various modules for capturing public opinions, assessing the value of movie stars, analyzing the temporal changes of their box-office impact, and predicting box-office revenues.

Understanding contents in social networks by inferring high-quality latent topics from short texts is a significant task in social analysis, which is challenging because social network contents are usually extremely short, noisy and full of informal vocabularies.Due to the lack of sufficient word co-occurrence instances, well-known topic modeling methods such as LDA and LSA cannot uncover high-quality topic structures.Existing research works seek to pool short texts from social networks into pseudo documents or utilize the explicit relations among these short texts such as hashtags in tweets to make classic topic modeling methods work.In this paper, we explore this problem by proposing a topic model for noisy short texts with multiple relations called MRTM (Multiple Relational Topic Modeling).MRTM exploits both explicit and implicit relations by introducing a document-attribute distribution and a two-step random sampling strategy.Extensive experiments, compared with stateof-the-art topic modeling approaches, demonstrate that MRTM can alleviate the word co-occurrence sparsity and uncover highquality latent topics from noisy short texts.

Understanding contents in social networks by inferring high-quality latent topics from short texts is a significant task in social analysis, which is challenging because social network contents are usually extremely short, noisy and full of informal vocabularies. Due to the lack of sufficient word co-occurrence instances, well-known topic modeling methods such as LDA and LSA cannot uncover high-quality topic structures. Existing research works seek to pool short texts from social networks into pseudo documents or utilize the explicit relations among these short texts such as hashtags in tweets to make classic topic modeling methods work. In this paper, we explore this problem by proposing a topic model for noisy short texts with multiple relations called MRTM (Multiple Relational Topic Modeling). MRTM exploits both explicit and implicit relations by introducing a document-attribute distribution and a two-step random sampling strategy. Extensive experiments, compared with the state-of-the-art topic modeling approaches, demonstrate that MRTM can alleviate the word co-occurrence sparsity and uncover high-quality latent topics from noisy short texts.

Many systems, such as distributed operating systems, complex networks, and high throughput web-based applications, are continuously generating large volume of event logs. These logs contain useful information to help system administrators to understand the system running status and to pinpoint the system failures. Generally, due to the scale and complexity of modern systems, the generated logs are beyond the analytic power of human beings. Therefore, it is imperative to develop a comprehensive log analysis system to support effective system management. Although a number of log mining techniques have been proposed to address specific log analysis use cases, few research and industrial efforts have been paid on providing integrated systems with an end-to-end solution to facilitate the log analysis routines.

In large scale and complex IT service environments, a problematic incident is logged as a ticket and contains the ticket summary (system status and problem description). The system administrators log the step-wise resolution description when such tickets are resolved. The repeating service events are most likely resolved by inferring similar historical tickets. With the availability of reasonably large ticket datasets, we can have an automated system to recommend the best matching resolution for a given ticket summary. In this paper, we first identify the challenges in real-world ticket analysis and develop an integrated framework to efficiently handle those challenges. The framework first quantifies the quality of ticket resolutions using a regression model built on carefully designed features. The tickets, along with their quality scores obtained from the resolution quality quantification, are then used to train a deep neural network ranking model that outputs the matching scores of ticket summary and resolution pairs. This ranking model allows us to leverage the resolution quality in historical tickets when recommending resolutions for an incoming incident ticket. In addition, the feature vectors derived from the deep neural ranking model can be effectively used in other ticket analysis tasks, such as ticket classification and clustering. The proposed framework is extensively evaluated with a large real-world dataset.

We study the problem of detecting the shape anomalies in this paper. Our shape anomaly detection algorithm is performed on the one-dimensional representation (time series) of shapes, whose similarity is modeled by a generalized segmental hidden Markov model (HMM) under a scaling, translation and rotation invariant manner. Experimental results show that our proposed approach can find shape anomalies in a large collection of shapes effectively and efficiently.

Graphs are popularly used to model structural relationships between objects. In many application domains such as social networks, sensor networks and telecommunication, graphs evolve over time. In this paper, we study a new problem of discovering the subgraphs that exhibit significant changes in evolving graphs. This problem is challenging since it is hard to define changing regions that are closely related to the actual changes (i.e., additions/deletions of edges/nodes) in graphs. We formalize the problem, and design an efficient algorithm that is able to identify the changing subgraphs incrementally. Our experimental results on real datasets show that our solution is very efficient and the resultant subgraphs are of high quality.