HCNA: Hyperbolic Contrastive Learning Framework for Self-Supervised Network Alignment

Saxena, Shruti; Chakraborty, Roshni; Chandra, Joydeep

doi:10.1016/j.ipm.2022.103021

Cited by 10 publications

(3 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Allmovie-IMDB: These are online movie guide service networks that connect two films if they have at least one actor in common (Trung et al, 2020;Saxena et al, 2022). It treats details like movie genre and cast as node attributes.…”

Section: Methodsmentioning

confidence: 99%

“…More recent approaches use an end-to-end learning framework to jointly train the embeddings of the two networks by optimizing a loss function over the dataset (Nguyen et al, 2021;Liu et al, 2019b). These alignment approaches utilize deep learning-based node embedding approaches, like adversarial-based training (Hong et al, 2020;Chen et al, 2019), graph convolutional network (Saxena et al, 2022;Trung et al, 2020;Cheng et al, 2019) for building node representations of both networks using common trainable parameters. Although these alignment approaches have shown promising results, they lack to jointly learn and transfer more useful complementary information across the partially aligned networks.…”

Section: Network Alignmentmentioning

confidence: 99%

See 1 more Smart Citation

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

Section: Methodsmentioning

confidence: 99%

Section: Network Alignmentmentioning

confidence: 99%

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

Saxena

Chandra²

2023

jair

View full text Add to dashboard Cite

show abstract

“…Network alignment is the first problem faced when fusing data from multiple networks. The main goal is to identify the node correspondence between two or more networks through analysis of network structure and node attributes, which is the basis of multi-source information fusion [4]. Earlier works mainly rely on explicit node similarity computation and iterative matching optimization for network alignment, resulting in limited alignment effects [5].…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised Rapid Network Alignment Framework via Network Coarsening

et al. 2023

View full text Add to dashboard Cite

Network alignment aims to identify the correspondence of nodes between two or more networks. It is the cornerstone of many network mining tasks, such as cross-platform recommendation and cross-network data aggregation. Recently, with the development of network representation learning techniques, researchers have proposed many embedding-based network alignment methods. The effect is better than traditional methods. However, several issues and challenges remain for network alignment tasks, such as lack of labeled data, mapping across network embedding spaces, and computational efficiency. Based on the graph neural network (GNN), we propose the URNA (unsupervised rapid network alignment) framework to achieve an effective balance between accuracy and efficiency. There are two phases: model training and network alignment. We exploit coarse networks to accelerate the training of GNN after first compressing the original networks into small networks. We also use parameter sharing to guarantee the consistency of embedding spaces and an unsupervised loss function to update the parameters. In the network alignment phase, we first use a once-pass forward propagation to learn node embeddings of original networks, and then we use multi-order embeddings from the outputs of all convolutional layers to calculate the similarity of nodes between the two networks via vector inner product for alignment. Experimental results on real-world datasets show that the proposed method can significantly reduce running time and memory requirements while guaranteeing alignment performance.

show abstract

Learning context-aware region similarity with effective spatial normalization over Point-of-Interest data

Jin,

Song,

Kan

et al. 2024

Information Processing & Management

View full text Add to dashboard Cite

HCNA: Hyperbolic Contrastive Learning Framework for Self-Supervised Network Alignment

Cited by 10 publications

References 48 publications

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

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

An Unsupervised Rapid Network Alignment Framework via Network Coarsening

Learning context-aware region similarity with effective spatial normalization over Point-of-Interest data

Contact Info

Product

Resources

About