Timezone: »

 
Oral
Graph Matching Networks for Learning the Similarity of Graph Structured Objects
Yujia Li · Chenjie Gu · Thomas Dullien · Oriol Vinyals · Pushmeet Kohli

Tue Jun 11 04:00 PM -- 04:20 PM (PDT) @ Hall A

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.

Author Information

Yujia Li (DeepMind)
Chenjie Gu (DeepMind)
Thomas Dullien (Google)
Oriol Vinyals (DeepMind)

Oriol Vinyals is a Research Scientist at Google. He works in deep learning with the Google Brain team. Oriol holds a Ph.D. in EECS from University of California, Berkeley, and a Masters degree from University of California, San Diego. He is a recipient of the 2011 Microsoft Research PhD Fellowship. He was an early adopter of the new deep learning wave at Berkeley, and in his thesis he focused on non-convex optimization and recurrent neural networks. At Google Brain he continues working on his areas of interest, which include artificial intelligence, with particular emphasis on machine learning, language, and vision.

Pushmeet Kohli (DeepMind)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors