Network Alignment Using Graphlet Signature and High Order Proximity

Almulhim, Aljohara Fahad; Dave, Vachik S.; Hasan, Mohammad Al

doi:10.1007/978-3-030-37599-7_12

Cited by 2 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, attentively aggregating the hierarchical structural features enhances the node expressivity, thereby overcoming the over-smoothing problem. While some approaches have also used graphlet information (Almulhim et al, 2019) however, they treat them as node attributes, as opposed to our method, which uses the graphlets as structural features to determine their correlation across the networks. Several other existing methods that have also used higher-order structures (Zhang et al, 2019;Qiu et al, 2021;Xia et al, 2021), to generate the node representations neither make any attempt to learn the embeddings jointly nor consider capturing the structural variations across the network.…”

Section: Introductionmentioning

confidence: 99%

SAlign: A Graph Neural Attention Framework for Aligning Structurally Heterogeneous Networks

Saxena

Chandra²

2023

jair

View full text Add to dashboard Cite

Network alignment techniques that map the same entities across multiple networks assume that the mapping nodes in two different networks have similar attributes and neighborhood proximity. However, real-world networks often violate such assumptions, having diverse attributes and structural properties. Node mapping across such structurally heterogeneous networks remains a challenge. Although capturing the nodes’ entire neighborhood (in low-dimensional embeddings) may help deal with these characteristic differences, the issue of over-smoothing in the representations that come from higherorder learning still remains a major problem. To address the above concerns, we propose SAlign: a supervised graph neural attention framework for aligning structurally heterogeneous networks that learns the correlation of structural properties of mapping nodes using a set of labeled (mapped) anchor nodes. SAlign incorporates nodes’ graphlet information with a novel structure-aware cross-network attention mechanism that transfers the required higher-order structure information across networks. The information exchanged across networks helps in enhancing the expressivity of the graph neural network, thereby handling any potential over-smoothing problem. Extensive experiments on three real datasets demonstrate that SAlign consistently outperforms the state-of-the-art network alignment methods by at least 1.3-8% in terms of accuracy score. The code is available at https://github.com/shruti400/SAlign for reproducibility.

show abstract