Deep Graph Matching Consensus

This work presents a two-stage neural architecture for learning and refining structural correspondences between graphs. First, we use localized node embeddings computed by a graph neural network to obtain an initial ranking of soft correspondences between nodes... Secondly, we employ synchronous message passing networks to iteratively re-rank the soft correspondences to reach a matching consensus in local neighborhoods between graphs. We show, theoretically and empirically, that our message passing scheme computes a well-founded measure of consensus for corresponding neighborhoods, which is then used to guide the iterative re-ranking process. Our purely local and sparsity-aware architecture scales well to large, real-world inputs while still being able to recover global correspondences consistently. We demonstrate the practical effectiveness of our method on real-world tasks from the fields of computer vision and entity alignment between knowledge graphs, on which we improve upon the current state-of-the-art. Our source code is available under deep-graph-matching-consensus. read more

PDF Abstract ICLR 2020 PDF ICLR 2020 Abstract


Results from the Paper

Ranked #6 on Entity Alignment on DBP15k zh-en (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Entity Alignment DBP15k zh-en Deep Graph Matching Consensus (L=10) Hits@1 0.8012 # 6
Entity Alignment DBP15k zh-en BootEA Hits@1 0.6294 # 17
Entity Alignment DBP15k zh-en MuGNN Hits@1 0.494 # 22
Entity Alignment DBP15k zh-en NAEA Hits@1 0.6501 # 16
Entity Alignment DBP15k zh-en GCN-Align Hits@1 0.4125 # 26
Entity Alignment DBP15k zh-en Deep Graph Matching Consensus Hits@1 0.7075 # 12
Entity Alignment DBP15k zh-en GMNN Hits@1 0.6793 # 15


No methods listed for this paper. Add relevant methods here