Existing Embedding Algorithms Research Articles

Dual-channel embedding learning model for partially labeled attributed networks

Network embedding is an important fundamental work in many network application tasks, which encodes the input network from the high-dimensional and sparse topological space into a low-dimensional and dense vector space. Recently, there has been a growing interest in embedding learning on Partially Labeled Attributed Networks (PLANs) due to the increasing occurrence of node attributes and partially available category labels in real-world networks. Semi-supervised embedding learning is a standard approach employed in PLANs, utilizing category labels to supervise the learning process. However, the semi-supervised learning procedure can fail when labels are scarce, noisy, or unreliable. Additionally, most existing embedding algorithms have not successfully integrated heterogeneous information, such as labels, attributes, and structure. To address these issues, we develop a new model, the Dual-Channel Network Embedding (DcNE), which integrates different types of network information into embeddings from a mutual information (MI) perspective. Specifically, we construct a dual-channel information propagation framework to encode the input network in semi-supervised and self-supervised learning paradigms in parallel. Furthermore, a redundancy elimination module is implemented to capture and eliminate the redundant information between the two encoders. Finally, we propose a unified optimization model that integrates the two learning paradigms to collaborate effectively. In the experiments, we demonstrate the effectiveness of DcNE in various network analysis tasks using real-world datasets, establishing its superiority over state-of-the-art baselines.

Design and Application of Deep Hash Embedding Algorithm with Fusion Entity Attribute Information

Hash is one of the most widely used methods for computing efficiency and storage efficiency. With the development of deep learning, the deep hash method shows more advantages than traditional methods. This paper proposes a method to convert entities with attribute information into embedded vectors (FPHD). The design uses the hash method to quickly extract entity features, and uses a deep neural network to learn the implicit association between entity features. This design solves two main problems in large-scale dynamic data addition: (1) The linear growth of the size of the embedded vector table and the size of the vocabulary table leads to huge memory consumption. (2) It is difficult to deal with the problem of adding new entities to the retraining model. Finally, taking the movie data as an example, this paper introduces the encoding method and the specific algorithm flow in detail, and realizes the effect of rapid reuse of dynamic addition data model. Compared with three existing embedding algorithms that can fuse entity attribute information, the deep hash embedding algorithm proposed in this paper has significantly improved in time complexity and space complexity.

Image fragile watermarking algorithm based on deneighbourhood mapping

To address the security risk caused by fixed offset mapping and the limited recoverability of random mapping used in image watermarking, a self-embedding fragile image watermarking algorithm based on deneighbourhood mapping are proposed. First, the image is divided into several 2 × 2 blocks, and authentication watermark and recovery watermark are generated based on the average value of the image blocks. Then, the denighbourhood mapping is implemented as, for each image block, its mapping block is randomly selected outside its neighbourhood. Finally, the authentication watermark and the recovery watermark are embedded into the image block itself and its mapping block. Theoretical analysis indicates that in the case of continuous area tampering, the proposed watermarking algorithm can achieve a better recovery rate than that of the method based on the random mapping. The experimental results verify the rationality and effectiveness of the theoretical analysis. Moreover, compared with the existing embedding algorithms based on random mapping, chaos mapping, and Arnold mapping, in the case of continuous area tampering, the proposed algorithm also achieves a higher average recovery rate.

Deep semi-supervised learning via dynamic anchor graph embedding in latent space

Recently, deep semi-supervised graph embedding learning has drawn much attention for its appealing performance on the data with a pre-specified graph structure, which could be predefined or empirically constructed based on given data samples. However, the pre-specified graphs often contain considerable noisy/inaccurate connections and have a huge size for large datasets. Most existing embedding algorithms just take the graph off the shelf during the whole training stage and thus are easy to be misled by the inaccurate graph edges, as well as may result in large model size. In this paper, we attempt to address these issues by proposing a novel deep semi-supervised algorithm for simultaneous graph embedding and node classification, utilizing dynamic graph learning in neural network hidden layer space. Particularly, we construct an anchor graph to summarize the whole dataset using the hidden layer features of a consistency-constrained network. The anchor graph is used for sampling node neighborhood context, which is then presented together with node labels as contextual information to train an embedding network. The outputs of the consistency network and the embedding networks are finally concatenated together to pass a softmax function to perform node classification. The two networks are optimized jointly using both labeled and unlabeled data to minimize a single semi-supervised objective function, including a cross-entropy loss, a consistency loss and an embedding loss. Extensive experimental results on popular image and text datasets have shown that the proposed method is able to improve the performance of existing graph embedding and node classification methods, and outperform many state-of-the-art approaches on both types of datasets.

Persona2vec: a flexible multi-role representations learning framework for graphs.

Graph embedding techniques, which learn low-dimensional representations of a graph, are achieving state-of-the-art performance in many graph mining tasks. Most existing embedding algorithms assign a single vector to each node, implicitly assuming that a single representation is enough to capture all characteristics of the node. However, across many domains, it is common to observe pervasively overlapping community structure, where most nodes belong to multiple communities, playing different roles depending on the contexts. Here, we propose persona2vec, a graph embedding framework that efficiently learns multiple representations of nodes based on their structural contexts. Using link prediction-based evaluation, we show that our framework is significantly faster than the existing state-of-the-art model while achieving better performance.

DSCD: Delay Sensitive Cross-Domain Virtual Network Embedding Algorithm

In the coming 5G era, more and more applications are time-delay sensitive, and the importance of low delay in fields such as telemedicine, autonomous driving and military order transmission is self-evident. However, for different application scenarios, their delay requirements are different. How to meet different Quality of service (QoS) requirements simultaneously becomes a challenge. The emergence of network virtualization (NV) technology can overcome this problem. However, it is difficult for the existing embedding algorithms to meet the requirements of virtual networks on time delay performance. Therefore, in order to study the delay problem of virtual network, we proposed a Delay Sensitive Cross-Domain Virtual Network Embedding Algorithm (DSCD-VNE) in this paper. First of all, different from the traditional virtual network embedding (VNE) algorithm, this algorithm divides the mapping process into a “node-link-node” three-stage embedding algorithm. Second, node resource metrics and set constraints are introduced in the generation phase of candidate link matrix. Third, the algorithm takes candidate link matrix as the core, and uses Kruskal minimum spanning tree to choose the link with the shortest delay for embedding. Fourth, path splitting mechanism and $K$ -shortest path algorithm are introduced with the aim of increasing the utilization of the substrate links in link mapping stage. The simulation results show that the proposed DSCD-VNE algorithm greatly improves the performance of the algorithm compared with the traditional node-link two-stage algorithm, especially in the aspect of delay, the improvement rate is as high as 77%.

Lifelong representation learning in dynamic attributed networks

Network embedding or network representation learning aims at learning a low-dimensional vector for each node in a network. The learned embeddings could advance various learning tasks in the network analysis area. Most existing embedding methods focus on plain and static networks while ignoring network dynamics. However, in real world networks, structure often evolves over time. In addition, many networks contain rich attributes and their attributes are changing over time. Naively applying existing embedding algorithms to each snapshot of dynamic network independently usually leads to unsatisfactory performance. In this paper, we present a Lifelong Dynamic Attributed Network Embedding Framework – LDANE. LDANE has a good mechanism to automatically expand the deep neural networks with the sizes of network growing and preserving what have learned from previous time steps. Furthermore, the proposed framework is carefully designed to flexibly incorporate the topology and attribute of nodes. We perform extensive experiments on both synthetic and real attributed networks to corroborate the significant advantages of the proposed framework compared with the existing state-of-the-art embedding techniques.

DYVINE: Fitness-Based Dynamic Virtual Network Embedding in Cloud Computing

Virtual network embedding (VNE) is the process of embedding the set of interconnected virtual machines onto the set of interconnected physical servers (PSs) in the cloud computing environment. The level of complexity of VNE problem increases when a large number of virtual machines with a set of resource demand need to be embedded onto a network of thousands of PSs. The key challenge of VNE is the efficient mapping of virtual networks (VNs), which may have dynamic resource demands. Existing solutions mainly emphasize on the embedding of static VN resulting in poor resource utilization and very low acceptance rate. To tackle such level of complexity in VNE, a fitness-based dynamic virtual network embedding (DYVINE) algorithm is proposed with the goal to maximize the resource utilization by maximizing the acceptance rate. Local and global fitness values of the virtual machines and VN, respectively, are used to utilize the maximum amount of physical resources. The proposed VNE algorithm allows the VN to be dynamic, which indicates that the structure and resource demand can be changed during its execution time. Furthermore, in order to reduce the embedding time in each time slot, a set of PSs is selected to host the VN instead of considering thousands of PSs, which may significantly increase the embedding time. The proposed embedding mechanism is evaluated through extensive simulation and is compared with similar existing embedding algorithms, which outperforms over others.

Virtual Network Embedding through Security Risk Awareness and Optimization

Network virtualization promises to play a dominant role in shaping the future Internet by overcoming the Internet ossification problem. However, due to the injecting of additional virtualization layers into the network architecture, several new security risks are introduced by the network virtualization. Although traditional protection mechanisms can help in virtualized environment, they are not guaranteed to be successful and may incur high security overheads. By performing the virtual network (VN) embedding in a security-aware way, the risks exposed to both the virtual and substrate networks can be minimized, and the additional techniques adopted to enhance the security of the networks can be reduced. Unfortunately, existing embedding algorithms largely ignore the widespread security risks, making their applicability in a realistic environment rather doubtful. In this paper, we attempt to address the security risks by integrating the security factors into the VN embedding. We first abstract the security requirements and the protection mechanisms as numerical concept of security demands and security levels, and the corresponding security constraints are introduced into the VN embedding. Based on the abstraction, we develop three security-risky modes to model various levels of risky conditions in the virtualized environment, aiming at enabling a more flexible VN embedding. Then, we present a mixed integer linear programming formulation for the VN embedding problem in different security-risky modes. Moreover, we design three heuristic embedding algorithms to solve this problem, which are all based on the same proposed node-ranking approach to quantify the embedding potential of each substrate node and adopt the k-shortest path algorithm to map virtual links. Simulation results demonstrate the effectiveness and efficiency of our algorithms.

DISCOVERING ROBUST EMBEDDINGS IN (DIS)SIMILARITY SPACE FOR HIGH-DIMENSIONAL LINGUISTIC FEATURES

Recent research has shown the effectiveness of rich feature representation for tasks in natural language processing (NLP). However, exceedingly large number of features do not always improve classification performance. They may contain redundant information, lead to noisy feature presentations, and also render the learning algorithms intractable. In this paper, we propose a supervised embedding framework that modifies the relative positions between instances to increase the compatibility between the input features and the output labels and meanwhile preserves the local distribution of the original data in the embedded space. The proposed framework attempts to support flexible balance between the preservation of intrinsic geometry and the enhancement of class separability for both interclass and intraclass instances. It takes into account characteristics of linguistic features by using an inner product-based optimization template. (Dis)similarity features, also known as empirical kernel mapping, is employed to enable computationally tractable processing of extremely high-dimensional input, and also to handle nonlinearities in embedding generation when necessary. Evaluated on two NLP tasks with six data sets, the proposed framework provides better classification performance than the support vector machine without using any dimensionality reduction technique. It also generates embeddings with better class discriminability as compared to many existing embedding algorithms.

Virtual network embedding through topology-aware node ranking

Virtualizing and sharing networked resources have become a growing trend that reshapes the computing and networking architectures. Embedding multiple virtual networks (VNs) on a shared substrate is a challenging problem on cloud computing platforms and large-scale sliceable network testbeds. In this paper we apply the Markov Random Walk (RW) model to rank a network node based on its resource and topological attributes. This novel topology-aware node ranking measure reflects the relative importance of the node. Using node ranking we devise two VN embedding algorithms. The first algorithm maps virtual nodes to substrate nodes according to their ranks, then embeds the virtual links between the mapped nodes by finding shortest paths with unsplittable paths and solving the multi-commodity flow problem with splittable paths. The second algorithm is a backtracking VN embedding algorithm based on breadth-first search, which embeds the virtual nodes and links during the same stage using node ranks. Extensive simulation experiments show that the topology-aware node rank is a better resource measure and the proposed RW-based algorithms increase the long-term average revenue and acceptance ratio compared to the existing embedding algorithms.