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.

Accepted as a conference paper at ICML 2019

Cited by in corpus (27)

• Boosting the Speed of Entity Alignment 10*: Dual Attention Matching Network with Normalized Hard Sample Mining
• Foundations of Population-Based SHM, Part IV: The Geometry of Spaces of Structures and their Feature Spaces
• CLARE: A Semi-supervised Community Detection Algorithm
• Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree
• Medical Entity Disambiguation Using Graph Neural Networks
• AEDNet: Adaptive Edge-Deleting Network For Subgraph Matching
• Embedding API Dependency Graph for Neural Code Generation
• Knowledge Graph Alignment Network with Gated Multi-hop Neighborhood Aggregation
• A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs
• Neighborhood Matching Network for Entity Alignment
• Bi-Level Graph Neural Networks for Drug-Drug Interaction Prediction
• Lifelong Person Re-Identification via Adaptive Knowledge Accumulation
• Self-supervised Representation Learning for Evolutionary Neural Architecture Search
• Cross-Global Attention Graph Kernel Network Prediction of Drug Prescription
• A contribution to Optimal Transport on incomparable spaces
• DeepHunter: A Graph Neural Network Based Approach for Robust Cyber Threat Hunting
• Single Neuron Segmentation using Graph-based Global Reasoning with Auxiliary Skeleton Loss from 3D Optical Microscope Images
• Are Negative Samples Necessary in Entity Alignment? An Approach with High Performance, Scalability and Robustness
• LayoutGMN: Neural Graph Matching for Structural Layout Similarity
• Deep Data Flow Analysis
• Hierarchical Graph Matching Network for Graph Similarity Computation
• GraphCode2Vec: Generic Code Embedding via Lexical and Program Dependence Analyses
• A Relational Model for One-Shot Classification
• Combinatorial Learning of Graph Edit Distance via Dynamic Embedding
• Informed Machine Learning for Improved Similarity Assessment in Process-Oriented Case-Based Reasoning
• Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphs
• SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features