A Simple Approach to Attributed Graph Embedding via Enhanced Autoencoder

Sheikh, Nasrullah; Kefato, Zekarias T.; Montresor, Alberto

doi:10.1007/978-3-030-36687-2_66

Cited by 5 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further, they suffer from severe efficiency issues due to the expensive training process of auto-encoders. SAGE2VEC [35] proposes an enhanced auto-encoder model that preserves global graph structure and meanwhile handles the non-linearity and sparsity of both graph structures and attributes. AdONE [1] designs an auto-encoder model for detecting and minimizing the effect of community outliers while generating embeddings.…”

Section: Related Work 61 Attributed Network Embeddingmentioning

confidence: 99%

Scaling attributed network embedding to massive graphs

et al. 2020

View full text Add to dashboard Cite

Given a graph G where each node is associated with a set of attributes, attributed network embedding (ANE) maps each node v ∈ G to a compact vector X v , which can be used in downstream machine learning tasks. Ideally, X v should capture node v 's affinity to each attribute, which considers not only v 's own attribute associations, but also those of its connected nodes along edges in G . It is challenging to obtain high-utility embeddings that enable accurate predictions; scaling effective ANE computation to massive graphs with millions of nodes pushes the difficulty of the problem to a whole new level. Existing solutions largely fail on such graphs, leading to prohibitive costs, low-quality embeddings, or both. This paper proposes PANE, an effective and scalable approach to ANE computation for massive graphs that achieves state-of-the-art result quality on multiple benchmark datasets, measured by the accuracy of three common prediction tasks: attribute inference, link prediction, and node classification. In particular, for the large MAG data with over 59 million nodes, 0.98 billion edges, and 2000 attributes, PANE is the only known viable solution that obtains effective embeddings on a single server, within 12 hours. PANE obtains high scalability and effectiveness through three main algorithmic designs. First, it formulates the learning objective based on a novel random walk model for attributed networks. The resulting optimization task is still challenging on large graphs. Second, PANE includes a highly efficient solver for the above optimization problem, whose key module is a carefully designed initialization of the embeddings, which drastically reduces the number of iterations required to converge. Finally, PANE utilizes multi-core CPUs through non-trivial parallelization of the above solver, which achieves scalability while retaining the high quality of the resulting embeddings. Extensive experiments, comparing 10 existing approaches on 8 real datasets, demonstrate that PANE consistently outperforms all existing methods in terms of result quality, while being orders of magnitude faster.

show abstract

Section: Related Work 61 Attributed Network Embeddingmentioning

confidence: 99%

Scaling attributed network embedding to massive graphs

et al. 2020

View full text Add to dashboard Cite

show abstract

“…NRL is usually carried out by exploring the structure of the graph and meta data, such as node attributes, attached to the graph (Perozzi et al, 2014;Grover & Leskovec, 2016;Tang et al, 2015;Perozzi et al, 2016;Yang et al, 2015;Pan et al, 2016;Sheikh et al, 2019b;Kefato et al, 2017;Sheikh et al, 2019a). Random walks are widely used to explore local/global neighborhood structures, which are then fed into a learning algorithm.…”

Section: Related Workmentioning

confidence: 99%

Graph Neighborhood Attentive Pooling

Kefato,

Girdzijauskas

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Network representation learning (NRL) is a powerful technique for learning lowdimensional vector representation of high-dimensional and sparse graphs. Most studies explore the structure and metadata associated with the graph using random walks and employ an unsupervised or semi-supervised learning schemes. Learning in these methods is context-free, because only a single representation per node is learned. Recently studies have argued on the sufficiency of a single representation and proposed a context-sensitive approach that proved to be highly effective in applications such as link prediction and ranking. However, most of these methods rely on additional textual features that require RNNs or CNNs to capture high-level features or rely on a community detection algorithm to identify multiple contexts of a node. In this study, without requiring additional features nor a community detection algorithm, we propose a novel context-sensitive algorithm called GAP that learns to attend on different parts of a node's neighborhood using attentive pooling networks. We show the efficacy of GAP using three real-world datasets on link prediction and node clustering tasks and compare it against 10 popular and state-ofthe-art (SOTA) baselines. GAP consistently outperforms them and achieves up to ≈ 9% and ≈ 20% gain over the best performing methods on link prediction and clustering tasks, respectively.

show abstract

“…Further, they suffer from severe efficiency issues due to the expensive training process of auto-encoders. [121] proposed an enhanced auto-encoder model that preserves global graph structure and meanwhile handles the non-linearity and sparsity of both graph structure and attributes. AdONE [8] proposed an auto-encoder model for detecting and minimizing the effect of community outliers while generating embeddings.…”

Section: Auto-encoder-based Methodsmentioning

confidence: 99%

Efficient and scalable techniques for pagerank-based graph analytics

Yang¹

View full text Add to dashboard Cite

A Simple Approach to Attributed Graph Embedding via Enhanced Autoencoder

Cited by 5 publications

References 18 publications

Scaling attributed network embedding to massive graphs

Scaling attributed network embedding to massive graphs

Graph Neighborhood Attentive Pooling

Efficient and scalable techniques for pagerank-based graph analytics

Contact Info

Product

Resources

About