Aligning Users Across Social Networks by Joint User and Label Consistence Representation

Li, Xiang; Su, Yijun; Gao, Neng; Tang, Wei; Xiang, Ji; Wang, Yuewu

doi:10.1007/978-3-030-36711-4_55

Cited by 3 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Existing unsupervised solutions for graph alignment can be roughly divided into two categories. The first category, referred to as "embedthen-cross-compare" [5,11,24,47,50,57,58], tackles the problem by first generating node representation (i.e., node embeddings) for both graphs. Then, the alignment probability of two nodes is computed by specific similarity measures based on their embeddings.…”

Section: Analysis Of State-of-the-art Solutionsmentioning

confidence: 99%

“…Earlier works for the unsupervised setting focus on the consistency principle [65] and adopt various methods including matrix factorization [15,16], locality sensitive hashing [14], and random walk with restart (RWR) based feature propagation [65]. The research focus then gradually moves on to embedding-based [5,11,24,29,30,40,47,50,58] and optimal transport-based solutions [4,44,46,55] for better model capability. Refer to Section 2.2 for a more detailed discussion of recent studies.…”

Section: Other Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Assembly Information Model Based on Knowledge Graph

Chen

Bao

Zheng

et al. 2020

J. Shanghai Jiaotong Univ. (Sci.)

View full text Add to dashboard Cite

Unsupervised graph alignment finds the one-to-one node correspondence between a pair of attributed graphs by only exploiting graph structure and node features. One category of existing works first computes the node representation and then matches nodes with close embeddings, which is intuitive but lacks a clear objective tailored for graph alignment in the unsupervised setting. The other category reduces the problem to optimal transport (OT) via Gromov-Wasserstein (GW) learning with a well-defined objective but leaves a large room for exploring the design of transport cost. We propose a principled approach to combine their advantages motivated by theoretical analysis of model expressiveness. By noticing the limitation of discriminative power in separating matched and unmatched node pairs, we improve the cost design of GW learning with feature transformation, which enables feature interaction across dimensions. Besides, we propose a simple yet effective embedding-based heuristic inspired by the Weisfeiler-Lehman test and add its prior knowledge to OT for more expressiveness when handling non-Euclidean data. Moreover, we are the first to guarantee the oneto-one matching constraint by reducing the problem to maximum weight matching. The algorithm design effectively combines our OT and embedding-based predictions via stacking, an ensemble learning strategy. We propose a model framework named CombAlign integrating all the above modules to refine node alignment progressively. Through extensive experiments, we demonstrate significant improvements in alignment accuracy compared to state-of-the-art approaches and validate the effectiveness of the proposed modules.

show abstract

Section: Analysis Of State-of-the-art Solutionsmentioning

confidence: 99%

Section: Other Related Workmentioning

confidence: 99%

Assembly Information Model Based on Knowledge Graph

Chen

Bao

Zheng

et al. 2020

J. Shanghai Jiaotong Univ. (Sci.)

View full text Add to dashboard Cite

show abstract

“…Specifically, this article presents a survey of the state-of-the-art algorithms for graph comparisons, identifying the study of nondeterminism as a research domain still in its infancy. While variations of graph comparison have been extensively used for real-world problems such as protein matching in biology (Ma and Liao, 2020), identifying nondeterminism in HPC simulations (Bell et al, 2021), and social network comparison (Liu et al, 2016); Zhang and Philip, 2015), graph comparison methods have limited deployment in HPC nondeterminism. Furthermore, while there exist several surveys on different aspects of graph comparison, including the latest methods on graph isomorphism (Grohe and Schweitzer, 2020), subgraph isomorphism and mining (Jiang et al, 2013), and graph kernel methods (Kriege et al, 2020); Borgwardt et al, 2020), these articles do not explicitly focus on applying these methods to capture and interpret aspects of nondeterminism in HPC applications.…”

Section: Introductionmentioning

confidence: 99%

A Survey of Graph Comparison Methods with Applications to Nondeterminism in High-Performance Computing

Bhowmick

Bell

Taufer

2023

The International Journal of High Performance Computing Applica

View full text Add to dashboard Cite

The convergence of extremely high levels of hardware concurrency and the effective overlap of computation and communication in asynchronous executions has resulted in increasing nondeterminism in High-Performance Computing (HPC) applications. Nondeterminism can manifest at multiple levels: from low-level communication primitives to libraries to application-level functions. No matter its source, nondeterminism can drastically increase the cost of result reproducibility, debugging workflows, testing parallel programs, or ensuring fault-tolerance. Nondeterministic executions of HPC applications can be modeled as event graphs, and the applications’ nondeterministic behavior can be understood and, in some cases, mitigated using graph comparison algorithms. However, a connection between graph comparison algorithms and approaches to understanding nondeterminism in HPC still needs to be established. This survey article moves the first steps toward establishing a connection between graph comparison algorithms and nondeterminism in HPC with its three contributions: it provides a survey of different graph comparison algorithms and a timeline for each category’s significant works; it discusses how existing graph comparison methods do not fully support properties needed to understand nondeterministic patterns in HPC applications; and it presents the open challenges that should be addressed to leverage the power of graph comparisons for the study of nondeterminism in HPC applications.

show abstract

User Alignment with Jumping Seed Alignment Information Propagation

Gao

et al. 2020

2020 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

Aligning Users Across Social Networks by Joint User and Label Consistence Representation

Cited by 3 publications

References 29 publications

Assembly Information Model Based on Knowledge Graph

Assembly Information Model Based on Knowledge Graph

A Survey of Graph Comparison Methods with Applications to Nondeterminism in High-Performance Computing

User Alignment with Jumping Seed Alignment Information Propagation

Contact Info

Product

Resources

About