G-CREWE: Graph CompREssion With Embedding for Network Alignment

  title={G-CREWE: Graph CompREssion With Embedding for Network Alignment},
  author={Kyle Kai Qin and Flora D. Salim and Yongli Ren and Wei Shao and Mark Heimann and Danai Koutra},
  journal={Proceedings of the 29th ACM International Conference on Information \& Knowledge Management},
  • K. K. Qin, Flora D. Salim, Danai Koutra
  • Published 30 July 2020
  • Computer Science
  • Proceedings of the 29th ACM International Conference on Information & Knowledge Management
Network alignment is useful for multiple applications that require increasingly large graphs to be processed. Existing research approaches this as an optimization problem or computes the similarity based on node representations. However, the process of aligning every pair of nodes between relatively large networks is time-consuming and resource-intensive. In this paper, we propose a framework, called G-CREWE (Graph CompREssion With Embedding) to solve the network alignment problem. G-CREWE uses… 

Figures and Tables from this paper

iMap: Incremental Node Mapping between Large Graphs Using GNN

iMap is proposed, a novel sub-graph expansion based alignment framework to incrementally construct meaningful sub-Graphs and perform alignment on each sub- graph pair iteratively, which reduces the unnecessary computation cost in the original raw networks and improves effectiveness via excluding possible noises.

Refining Network Alignment to Improve Matched Neighborhood Consistency

The refinement method, RefiNA, is straightforward to implement, admits scalable sparse approximation, and can be paired post hoc with any network alignment method, making them robust enough to align graphs that are 5× more topologically different than were considered in prior work.

Uncertainty‐aware network alignment

The P2P matching constraint is addressed by introducing an adversarial learning paradigm, which relaxes the exact matching assumption during training with an across‐domain generative procedure to reduce the matching errors on testing nodes.

Cross-Network Learning with Partially Aligned Graph Convolutional Networks

This paper proposes partially aligned graph convolutional networks to learn node representations across the models and investigates multiple methods (including model sharing, regularization, and alignment reconstruction) as well as theoretical analysis to positively transfer knowledge across the (small) set of partially aligned nodes.

Unsupervised Adversarial Network Alignment with Reinforcement Learning

A novel network alignment framework that combines generative adversarial network (GAN) and reinforcement learning (RL) techniques to tackle the above critical challenges and develops an RL based optimization approach to solve the vertex matching problem in the discrete space of the GAN model.

Variational Cross-Network Embedding for Anonymized User Identity Linkage

This paper proposes a novel and concise unsupervised embedding method, VCNE, by utilizing the network structural information in the AUIL problem, and introduces a variational cross-network embedding learning framework to jointly study the Gaussian embeddings instead of the existing deterministic embedding from the angle of vector space.

A benchmark and comprehensive survey on knowledge graph entity alignment via representation learning

A comprehensive tutorial-type survey on representative entity alignment techniques that use the new approach of representation learning is provided, a framework for capturing the key characteristics of these techniques is presented, and a benchmark addressing the limitation of existing benchmark datasets is proposed.

CAPER: Coarsen, Align, Project, Refine - A General Multilevel Framework for Network Alignment

CAPER is a multilevel alignment framework that Coarsens the input graphs, Aligns the coarsened graphs, Projects the alignment solution to finer levels and Refines the alignment Solution, which can improve upon diverse network alignment methods by an average of 33% in accuracy and/or an order of magnitude faster in runtime performance.

A Comprehensive Survey on Knowledge Graph Entity Alignment via Representation Learning

A framework for capturing the key characteristics of these techniques, a proposed two datasets to address the limitation of existing benchmark datasets, and extensive experiments using the proposed datasets give a clear picture of how the techniques work.

Integrated Defense for Resilient Graph Matching

An integrated defense model, IDRGM, is proposed for resilient graph matching with two novel defense techniques to defend against the above two attacks simultaneously and the robustness of the model is evaluated on real datasets against state-of-the-art algorithms.



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.

HashAlign: Hash-Based Alignment of Multiple Graphs

This paper proposes HashAlign, an efficient and intuitive hash-based framework for network alignment that leverages structural properties and other node and edge attributes (if available) simultaneously that quickly aligns multiple graphs while avoiding the all-pairwise-comparison problem.

Multilevel Network Alignment

The proposed coarsen-align-interpolate method overcomes the O(n2) lower bound, achieving a linear complexity and helps reveal the alignment between rich patterns of the input networks at multiple levels (e.g., node, clusters, super-clusters, etc.).

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.

HARP: Hierarchical Representation Learning for Networks

HARP is a general meta-strategy to improve all of the state-of-the-art neural algorithms for embedding graphs, including DeepWalk, LINE, and Node2vec, and it is demonstrated that applying HARP’s hierarchical paradigm yields improved implementations for all three of these methods.

Structural Deep Network Embedding

This paper proposes a Structural Deep Network Embedding method, namely SDNE, which first proposes a semi-supervised deep model, which has multiple layers of non-linear functions, thereby being able to capture the highly non- linear network structure and exploits the first-order and second-order proximity jointly to preserve the network structure.

Layered label propagation: a multiresolution coordinate-free ordering for compressing social networks

Experiments performed show that combining the order produced by the proposed algorithm with the WebGraph compression framework provides a major increase in compression with respect to all currently known techniques, both on web graphs and on social networks.

iNEAT: Incomplete Network Alignment

It is argued that network alignment and completion are inherently complementary with each other, and hence it is proposed to jointly address them so that the two tasks can benefit from each other.

Graph summarization with quality guarantees

This work develops the first polynomial-time approximation algorithms to compute the best possible summary of a certain size under both measures of the original graph.

node2vec: Scalable Feature Learning for Networks

In node2vec, an algorithmic framework for learning continuous feature representations for nodes in networks, a flexible notion of a node's network neighborhood is defined and a biased random walk procedure is designed, which efficiently explores diverse neighborhoods.