• Corpus ID: 246285324

On the Power of Gradual Network Alignment Using Dual-Perception Similarities

  title={On the Power of Gradual Network Alignment Using Dual-Perception Similarities},
  author={Jin-Duk Park and Cong Tran and Won-Yong Shin and Xin Cao},
Network alignment (NA) is the task of finding the correspondence of nodes between two networks based on the network structure and node attributes. Our study is motivated by the fact that, since most of existing NA methods have attempted to discover all node pairs at once, they do not harness information enriched through interim discovery of node correspondences to more accurately find the next correspondences during the node matching. To tackle this challenge, we propose Grad-Align, a new NA… 

Grad-Align+: Empowering Gradual Network Alignment Using Attribute Augmentation

Experimental results demonstrate that Grad-Align+ exhibits a) superiority over benchmark NA methods, (b) empirical validation of the theoretical findings, and (c) the effectiveness of the attribute augmentation module.



Grad-Align: Gradual Network Alignment via Graph Neural Networks (Student Abstract)

Grad-Align is a new NA method that gradually discovers node pairs by making full use of either node pairs exhibiting strong consistency or prior matching information, and consistently outperforms state-of-the-art NA methods in terms of the alignment accuracy.

Adaptive Network Alignment with Unsupervised and Multi-order Convolutional Networks

This paper proposes a fully unsupervised network alignment framework based on a multi-order embedding model that learns the embeddings of each node using a graph convolutional neural representation, which proves to satisfy consistency constraints.

FINAL: Fast Attributed Network Alignment

This paper proposes a family of algorithms to leverage the node/edge attribute information to guide (topology-based) alignment process, and develops effective and scalable algorithms to solve the problem from an optimization perspective.

REGAL: Representation Learning-based Graph Alignment

This work proposes REGAL (REpresentation learning-based Graph ALignment), a framework that leverages the power of automatically-learned node representations to match nodes across different graphs, and devise xNetMF, an elegant and principled node embedding formulation that uniquely generalizes to multi-network problems.

Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View

Two methods to alleviate the over-smoothing issue of GNNs are proposed: MADReg which adds a MADGap-based regularizer to the training objective; AdaEdge which optimizes the graph topology based on the model predictions.

BIG-ALIGN: Fast Bipartite Graph Alignment

This work focuses on aligning bipartite graphs, a problem which has been largely ignored by the extensive existing work on graph matching, despite the ubiquity of those graphs, and introduces a new optimization formulation and proposes an effective and fast algorithm to solve it.

A Survey on Network Embedding

This survey focuses on categorizing and then reviewing the current development on network embedding methods, and point out its future research directions, covering the structure- and property-preserving network embeding methods, the network embedded methods with side information, and the advanced information preserving network embedting methods.

Aligning Users across Social Networks Using Network Embedding

This paper proposes to learn a network embedding with the followership/ followee-ship of each user explicitly modeled as input/output context vector representations so as to preserve the proximity of users with "similar" followers/followees in the embedded space.

Joint Link Prediction and Network Alignment via Cross-graph Embedding

It is argued that these two tasks are relevant and present a joint link prediction and network alignment framework, whereby a novel cross-graph node embedding technique is devised to allow for information propagation.

Inside the atoms: ranking on a network of networks

This paper proposes a new network data model, a Network of Networks (NoN), where each node of the main network itself can be further represented as another (domain-specific) network, where the nodes are the ranking objects with the finest granularity.