Graph Matching Networks for Learning the Similarity of Graph Structured Objects

Abstract

This paper addresses the challenging problem of retrieval and matching of graph structured objects, and makes two key contributions. First, we demonstrate how Graph Neural Networks (GNN), which have emerged as an effective model for various supervised prediction problems defined on structured data, can be trained to produce embedding of graphs in vector spaces that enables efficient similarity reasoning. Second, we propose a novel Graph Matching Network model that, given a pair of graphs as input, computes a similarity score between them by jointly reasoning on the pair through a new cross-graph attention-based matching mechanism. We demonstrate the effectiveness of our models on different domains including the challenging problem of control-flow-graph based function similarity search that plays an important role in the detection of vulnerabilities in software systems. The experimental analysis demonstrates that our models are not only able to exploit structure in the context of similarity learning but they can also outperform domain-specific baseline systems that have been carefully hand-engineered for these problems.

arXiv commentAccepted as a conference paper at ICML 2019

Cited by in corpus (63)

• Graph Neural Networks: A Review of Methods and Applications
• Metrics for Graph Comparison: A Practitioner's Guide
• Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining
• GoGNN: Graph of Graphs Neural Network for Predicting Structured Entity Interactions
• Multilevel Graph Matching Networks for Deep Graph Similarity Learning
• Learning Multi-Attention Context Graph for Group-Based Re-Identification
• Foundations of Population-Based SHM, Part IV: The Geometry of Spaces of Structures and their Feature Spaces
• Graph Communal Contrastive Learning
• Neural Subgraph Matching
• CLARE: A Semi-supervised Community Detection Algorithm
• Contrastive Learning with Hard Negative Samples
• Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree
• Medical Entity Disambiguation Using Graph Neural Networks
• ProGraML: Graph-based Deep Learning for Program Optimization and Analysis
• Optimal Transport Graph Neural Networks
• Entity Alignment with Reliable Path Reasoning and Relation-Aware Heterogeneous Graph Transformer
• Embedding API Dependency Graph for Neural Code Generation
• AEDNet: Adaptive Edge-Deleting Network For Subgraph Matching
• Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation
• Topological Coding and Topological Matrices Toward Network Overall Security
• A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs
• Exchangeable deep neural networks for set-to-set matching and learning
• Reinforcement Learning Based Quantum Circuit Optimization via ZX-Calculus
• Deep Graph Similarity Learning: A Survey
• Neighborhood Matching Network for Entity Alignment
• Ego-Vehicle Action Recognition based on Semi-Supervised Contrastive Learning
• Bi-Level Graph Neural Networks for Drug-Drug Interaction Prediction
• Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
• Learning to Represent Programs with Heterogeneous Graphs
• SEED: Semantic Graph based Deep detection for type-4 clone
• Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art
• Self-supervised Representation Learning for Evolutionary Neural Architecture Search
• A contribution to Optimal Transport on incomparable spaces
• Cross-Global Attention Graph Kernel Network Prediction of Drug Prescription
• DeepHunter: A Graph Neural Network Based Approach for Robust Cyber Threat Hunting
• VLG-Net: Video-Language Graph Matching Network for Video Grounding
• Are Negative Samples Necessary in Entity Alignment? An Approach with High Performance, Scalability and Robustness
• CoSimGNN: Towards Large-scale Graph Similarity Computation
• Co-attention Graph Pooling for Efficient Pairwise Graph Interaction Learning
• LayoutGMN: Neural Graph Matching for Structural Layout Similarity
• Single Neuron Segmentation using Graph-based Global Reasoning with Auxiliary Skeleton Loss from 3D Optical Microscope Images
• Contrastive Attraction and Contrastive Repulsion for Representation Learning
• High-Order Relation Construction and Mining for Graph Matching
• A Graph Deep Learning Framework for High-Level Synthesis Design Space Exploration
• Hierarchical Graph Matching Network for Graph Similarity Computation
• SPA-GCN: Efficient and Flexible GCN Accelerator with an Application for Graph Similarity Computation
• Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching
• GraphCode2Vec: Generic Code Embedding via Lexical and Program Dependence Analyses
• Deep Data Flow Analysis
• Normalized topological indices discriminate between architectures of branched macromolecules
• Informed Machine Learning for Improved Similarity Assessment in Process-Oriented Case-Based Reasoning
• Efficient Joint Object Matching via Linear Programming
• A Relational Model for One-Shot Classification
• Precise system-wide concatic malware unpacking
• Graph Partitioning and Graph Neural Network based Hierarchical Graph Matching for Graph Similarity Computation
• pix2rule: End-to-end Neuro-symbolic Rule Learning
• Combinatorial Learning of Graph Edit Distance via Dynamic Embedding
• Sequential Aggregation and Rematerialization: Distributed Full-batch Training of Graph Neural Networks on Large Graphs
• Casting graph isomorphism as a point set registration problem using a simplex embedding and sampling
• A Statistical Relational Approach to Learning Distance-based GCNs
• Learning-based Efficient Graph Similarity Computation via Multi-Scale Convolutional Set Matching
• Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphs
• SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features