PPNE: Property Preserving Network Embedding

Li, Chaozhuo; Wang, Senzhang; Yang, Dejian; Li, Zhoujun; Yang, Yang; Zhang, Xiaoming; Zhou, Jianshe

doi:10.1007/978-3-319-55753-3_11

Cited by 54 publications

(28 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Factorization strategies vary across different algo- Unsupervised Social Dim. [31], [32], [33] DeepWalk [6] LINE [1] GraRep [26] DNGR [9] SDNE [19] node2vec [34] HOPE [35] APP [36] M-NMF [28] GraphGAN [37] struct2vec [38] GraphWave [39] SNS [40] DP [41] HARP [42] TADW [7] HSCA [8] pRBM [29] UPP-SNE [43] PPNE [44] Semi-supervised DDRW [45] MMDW [46] TLINE [47] GENE [48] SemiNE [49] TriDNR [50] LDE [51] DMF [8] Planetoid [52] LANE [30] rithms according to their objectives. For example, in the Modularity Maximization method [31], eigen decomposition is performed on the modularity matrix to learn community indicative vertex representations [53]; in the TADW algorithm [7], inductive matrix factorization [54] is carried out on the vertexcontext matrix to simultaneously preserve vertex textual features and network structure in the learning of vertex representations.…”

Section: Categorizationmentioning

confidence: 99%

“…DeepWalk [6], node2vec [34], APP [36], DDRW [45], GENE [48], TriDNR [50], UPP-SNE [43], struct2vec [38], SNS [40], PPNE [44], SemiNE [49] relatively efficient only capture local structure Edge Modeling LINE [1], TLINE [47], LDE [51], pRBM [29], GraphGAN [37] efficient only capture local structure Deep Learning DNGR [9], SDNE [19] capture non-linearity high time cost…”

Section: Random Walkmentioning

confidence: 99%

“…To learn content augmented vertex representations, PPNE [44] jointly optimizes two objectives: (i) the structuredriven objective and (ii) the attribute-driven objective. Following DeepWalk, the structure-driven objective aims to make vertices sharing similar context vertices represented closely.…”

Section: Property Preserving Network Embedding (Ppne)mentioning

confidence: 99%

“…To integrate network structure, vertex attributes and vertex labels together, Planetoid jointly minimizes the two objectives (43) and (44) to learn vertex embedding e with deep neural networks.…”

Section: Predictive Labels and Neighbors With Embeddings Transductivementioning

confidence: 99%

See 3 more Smart Citations

Network Representation Learning: A Survey

Zhang

Yin

Zhu

2020

IEEE Trans. Big Data

526

339

View full text Add to dashboard Cite

With the widespread use of information technologies, information networks are becoming increasingly popular to capture complex relationships across various disciplines, such as social networks, citation networks, telecommunication networks, and biological networks. Analyzing these networks sheds light on different aspects of social life such as the structure of societies, information diffusion, and communication patterns. In reality, however, the large scale of information networks often makes network analytic tasks computationally expensive or intractable. Network representation learning has been recently proposed as a new learning paradigm to embed network vertices into a low-dimensional vector space, by preserving network topology structure, vertex content, and other side information. This facilitates the original network to be easily handled in the new vector space for further analysis. In this survey, we perform a comprehensive review of the current literature on network representation learning in the data mining and machine learning field. We propose new taxonomies to categorize and summarize the state-of-the-art network representation learning techniques according to the underlying learning mechanisms, the network information intended to preserve, as well as the algorithmic designs and methodologies. We summarize evaluation protocols used for validating network representation learning including published benchmark datasets, evaluation methods, and open source algorithms. We also perform empirical studies to compare the performance of representative algorithms on common datasets, and analyze their computational complexity. Finally, we suggest promising research directions to facilitate future study.Definition 2 (First-order Proximity). The first-order proximity is the local pairwise proximity between two connected vertices [1]. For each vertex pair (v i , v j ), if (v i , v j ) ∈ E, the first-order proximity between v i and v j is w ij ; otherwise, the first-order proximity between v i and v j is 0. The first-order proximity captures the direct neighbor relationships between vertices.Definition 3 (Second-order Proximity and High-order Proximity). The second-order proximity captures the 2-step relations between each pair of vertices [1]. For each vertex pair (v i , v j ), the second order proximity is determined by the number of common neighbors shared by the two vertices, which can also be measured by the 2-step transition probability from v i to v j equivalently. Compared with the second-order proximity, the highorder proximity [26] captures more global structure, which explores k-step (k ≥ 3) relations between each pair of vertices. For each vertex pair (v i , v j ), the higherorder proximity is measured by the k-step (k ≥ 3) transition probability from vertex v i to vertex v j , which can also be reflected by the number of k-step (k ≥ 3) paths from v i to v j . The second-order and high-order proximity capture the similarity between a pair of, indirectly connected, vertices with similar structural contex...

show abstract

Section: Categorizationmentioning

confidence: 99%

Section: Random Walkmentioning

confidence: 99%

Section: Property Preserving Network Embedding (Ppne)mentioning

confidence: 99%

Section: Predictive Labels and Neighbors With Embeddings Transductivementioning

confidence: 99%

See 2 more Smart Citations

Network Representation Learning: A Survey

Zhang

Yin

Zhu

2020

IEEE Trans. Big Data

526

339

View full text Add to dashboard Cite

show abstract

“…For instance, SDNE (Wang, Cui, and Zhu 2016) uses the sparse adjacency vector of vertices as raw features for each vertex, and applies an autoencoder to extract short and condense features for vertices under the supervision of edge existence. PPNE (Li et al 2017b) directly learns vertex embeddings with supervised learning on positive samples (connected vertex pairs) and negative samples (disconnected vertex pairs), also preserving the inherent properties of vertices during the learning process.…”

Section: Introductionmentioning

confidence: 99%

Learning Graph Representation With Generative Adversarial Nets

Wang¹,

Wang

et al. 2021

IEEE Trans. Knowl. Data Eng.

220

267

View full text Add to dashboard Cite

The goal of graph representation learning is to embed each vertex in a graph into a low-dimensional vector space. Existing graph representation learning methods can be classified into two categories: generative models that learn the underlying connectivity distribution in the graph, and discriminative models that predict the probability of edge existence between a pair of vertices. In this paper, we propose Graph-GAN, an innovative graph representation learning framework unifying above two classes of methods, in which the generative model and discriminative model play a game-theoretical minimax game. Specifically, for a given vertex, the generative model tries to fit its underlying true connectivity distribution over all other vertices and produces "fake" samples to fool the discriminative model, while the discriminative model tries to detect whether the sampled vertex is from ground truth or generated by the generative model. With the competition between these two models, both of them can alternately and iteratively boost their performance. Moreover, when considering the implementation of generative model, we propose a novel graph softmax to overcome the limitations of traditional softmax function, which can be proven satisfying desirable properties of normalization, graph structure awareness, and computational efficiency. Through extensive experiments on real-world datasets, we demonstrate that Graph-GAN achieves substantial gains in a variety of applications, including link prediction, node classification, and recommendation, over state-of-the-art baselines.

show abstract

AI Algorithms in Networks

2022

Artificial Intelligence and Quantum Computing for Advanced Wireless Networks

View full text Add to dashboard Cite

PPNE: Property Preserving Network Embedding

Cited by 54 publications

References 19 publications

Network Representation Learning: A Survey

Network Representation Learning: A Survey

Learning Graph Representation With Generative Adversarial Nets

AI Algorithms in Networks

Contact Info

Product

Resources

About