A Structural Graph Representation Learning Framework

Rossi, Ryan A.; Ahmed, Nesreen K.; Koh, Eunyee; Kim, Sung‐Chul; Rao, Anup; Abbasi-Yadkori, Yasin

doi:10.1145/3336191.3371843

Cited by 35 publications

(18 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where N is the total number of graphs in the training set, K = N (N − 1)/2 is the total number of pairs from the training set, y i j is the ground-truth label for the pair of graphs G i and G j where y i j = 1 for similar pairs and y i j = −1 for dissimilar pairs, and s i j is the similarity score estimated by the model. More general forms of higher-order information [e.g., motifs (Ahmed et al 2015(Ahmed et al , 2017b] have been used for learning graph representations (Rossi et al 2018(Rossi et al , 2020a and would likely benefit the learning.…”

Section: Siamese Gnn Models For Graph Similarity Learningmentioning

confidence: 99%

Deep graph similarity learning: a survey

Ahmed

Willke

et al. 2021

Data Min Knowl Disc

Self Cite

View full text Add to dashboard Cite

In many domains where data are represented as graphs, learning a similarity metric among graphs is considered a key problem, which can further facilitate various learning tasks, such as classification, clustering, and similarity search. Recently, there has been an increasing interest in deep graph similarity learning, where the key idea is to learn a deep learning model that maps input graphs to a target space such that the distance in the target space approximates the structural distance in the input space. Here, we provide a comprehensive review of the existing literature of deep graph similarity learning. We propose a systematic taxonomy for the methods and applications. Finally, we discuss the challenges and future directions for this problem.

show abstract

Section: Siamese Gnn Models For Graph Similarity Learningmentioning

confidence: 99%

Deep graph similarity learning: a survey

Ahmed

Willke

et al. 2021

Data Min Knowl Disc

Self Cite

View full text Add to dashboard Cite

show abstract

“…It treats graph diffusion kernels as probability distributions over networks and calculates embeddings by using characteristic functions of the distributions. HONE [133] analyzes motifs of a weighted graph where an edge's weight is the count of the co-occurrences of the two endpoints in a specific motif. The main limitation of these matrix factorization methods is low computational efficiency resulting from calculating pair-wise node similarity.…”

Section: Role Discovery Modelsmentioning

confidence: 99%

Role-Aware Information Spread in Online Social Networks

Bartal

Jagodnik

2021

Entropy

View full text Add to dashboard Cite

Understanding the complex process of information spread in online social networks (OSNs) enables the efficient maximization/minimization of the spread of useful/harmful information. Users assume various roles based on their behaviors while engaging with information in these OSNs. Recent reviews on information spread in OSNs have focused on algorithms and challenges for modeling the local node-to-node cascading paths of viral information. However, they neglected to analyze non-viral information with low reach size that can also spread globally beyond OSN edges (links) via non-neighbors through, for example, pushed information via content recommendation algorithms. Previous reviews have also not fully considered user roles in the spread of information. To address these gaps, we: (i) provide a comprehensive survey of the latest studies on role-aware information spread in OSNs, also addressing the different temporal spreading patterns of viral and non-viral information; (ii) survey modeling approaches that consider structural, non-structural, and hybrid features, and provide a taxonomy of these approaches; (iii) review software platforms for the analysis and visualization of role-aware information spread in OSNs; and (iv) describe how information spread models enable useful applications in OSNs such as detecting influential users. We conclude by highlighting future research directions for studying information spread in OSNs, accounting for dynamic user roles.

show abstract

“…Role-aware models embed structurally similar nodes close in the latent space, independent of network position [4], [45]. A few approaches [33] employ strict definitions of structural equivalence to embed nodes with identical local structures to the same point in the latent space, while others utilize structural node features (e.g., node degrees, motif count statistics) to extend classical proximity-preserving embedding methods, e.g., feature-based matrix factorization [46] and random walk methods [5]. Notably, a few methods design structural GCNs via motif adjacency matrices [34], [35], [47].…”

Section: I R E L At E D W O R Kmentioning

confidence: 99%

Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework

Ashok

Wang

Krishnan

et al. 2020

2020 IEEE International Conference on Data Mining (ICDM)

View full text Add to dashboard Cite

We present InfoMotif, a new semi-supervised, motifregularized, learning framework over graphs. We overcome two key limitations of message passing in popular graph neural networks (GNNs): localization (a k-layer GNN cannot utilize features outside the k-hop neighborhood of the labeled training nodes) and over-smoothed (structurally indistinguishable) representations. We propose the concept of attributed structural roles of nodes based on their occurrence in different network motifs, independent of network proximity. Two nodes share attributed structural roles if they participate in topologically similar motif instances over co-varying sets of attributes. Further, InfoMotif achieves architecture independence by regularizing the node representations of arbitrary GNNs via mutual information maximization. Our training curriculum dynamically prioritizes multiple motifs in the learning process without relying on distributional assumptions in the underlying graph or the learning task. We integrate three state-of-the-art GNNs in our framework, to show significant gains (3-10% accuracy) across six diverse, real-world datasets. We see stronger gains for nodes with sparse training labels and diverse attributes in local neighborhood structures.

show abstract

A Structural Graph Representation Learning Framework

Cited by 35 publications

References 28 publications

Deep graph similarity learning: a survey

Deep graph similarity learning: a survey

Role-Aware Information Spread in Online Social Networks

Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework

Contact Info

Product

Resources

About