Enhancing the Network Embedding Quality with Structural Similarity

Lyu, Tianshu; Zhang, Yuan; Zhang, Yan

doi:10.1145/3132847.3132900

Cited by 59 publications

(46 citation statements)

References 20 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%

“…Structural and Neighborhood Similarity preserving network embedding (SNS). SNS [40] enhances a random walk based method with structural role proximity. To preserve vertex structural roles, SNS represents each vertex as a Graphlet Degree Vector with each element being the number of times the given vertex is touched by the corresponding orbit of graphlets.…”

Section: Structural Role Proximity Preserving Nrlmentioning

confidence: 99%

“…where r vi is the output representation of v i and h vi is the hidden layer representation for predicting v i , which is aggregated from the input representations r u , for each u in C(v i ) and S(v i ). Summary: struct2vec [38] and GraphWave [39] take advantage of structural role proximity to learn vertex representations that facilitate specific structural role dependent tasks, e.g., vertex classification in traffic networks, while SNS [40] enhances a random walk based microscopic structure preserving NRL algorithm with structural role proximity. Technically, random walk is employed by struct2vec and SNS, while matrix factorization is adopted by GraphWave.…”

Section: Structural Role Proximity Preserving Nrlmentioning

confidence: 99%

See 3 more Smart Citations

Network Representation Learning: A Survey

Zhang

Yin

Zhu

2020

IEEE Trans. Big Data

554

352

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: Structural Role Proximity Preserving Nrlmentioning

confidence: 99%

Section: Structural Role Proximity Preserving Nrlmentioning

confidence: 99%

See 2 more Smart Citations

Network Representation Learning: A Survey

Zhang

Yin

Zhu

2020

IEEE Trans. Big Data

554

352

View full text Add to dashboard Cite

show abstract

“…Specifically, we prove the following theorem. 6 https://nlp.stanford.edu/projects/glove/ Theorem VI.1. Given our particular cell embedding approach, ∀c i , c j ∈ C, ||u ci − u cj || 2 2 ≤ S(c i , c j ), where is a constant and S(c i , c j ) is the semantic gap between c i , c j .…”

Section: Appendix B: Details Of Cell Embeddingmentioning

confidence: 99%

cube2net: Efficient Query-Specific Network Construction with Data Cube Organization

Yang

2019

2019 International Conference on Data Mining Workshops (ICDMW)

View full text Add to dashboard Cite

Networks are widely used to model objects with interactions and have enabled various downstream applications. However, in the real world, network mining is often done on particular query sets of objects, which does not require the construction and computation of networks including all objects in the datasets. In this work, for the first time, we propose to address the problem of query-specific network construction, to break the efficiency bottlenecks of existing network mining algorithms and facilitate various downstream tasks. To deal with real-world massive networks with complex attributes, we propose to leverage the well-developed data cube technology to organize network objects w.r.t. their essential attributes. An efficient reinforcement learning algorithm is then developed to automatically explore the data cube structures and construct the optimal query-specific networks. With extensive experiments of two classic network mining tasks on different real-world large datasets, we show that our proposed cube2net pipeline is general, and much more effective and efficient in query-specific network construction, compared with other methods without the leverage of data cube or reinforcement learning.

show abstract

AI Algorithms in Networks

2022

Artificial Intelligence and Quantum Computing for Advanced Wireless Networks

View full text Add to dashboard Cite

Enhancing the Network Embedding Quality with Structural Similarity

Cited by 59 publications

References 20 publications

Network Representation Learning: A Survey

Network Representation Learning: A Survey

cube2net: Efficient Query-Specific Network Construction with Data Cube Organization

AI Algorithms in Networks

Contact Info

Product

Resources

About