More Like this

1. Stochastic Iterative Graph Matching

   Liu, Linfeng; Hughs, Mike; Hassoun, Soha; Liu, Li-Ping (July 2021, International Conference on Machine Learning)

   null (Ed.)

   Recent works apply Graph Neural Networks (GNNs) to graph matching tasks and show promising results. Considering that model outputs are complex matchings, we devise several techniques to improve the learning of GNNs and obtain a new model, Stochastic Iterative Graph MAtching (SIGMA). Our model predicts a distribution of matchings, instead of a single matching, for a graph pair so the model can explore several probable matchings. We further introduce a novel multi-step matching procedure, which learns how to refine a graph pair’s matching results incrementally. The model also includes dummy nodes so that the model does not have to find matchings for nodes without correspondence. We fit this model to data via scalable stochastic optimization. We conduct extensive experiments across synthetic graph datasets as well as biochemistry and computer vision applications. Across all tasks, our results show that SIGMA can produce significantly improved graph matching results compared to state-of-the-art models. Ablation studies verify that each of our components (stochastic training, iterative matching, and dummy nodes) offers noticeable improvement. 

   more » « less
2. Effective Federated Graph Matching

   Zhou, Yang; Zhang, Zijie; Zhang, Zeru; Lyu, Lingjuan; Ku, Wei-Shinn (July 2024, Proceedings of the 41st International Conference on Machine Learning (ICML'24))
3. Stochastic Iterative Graph Matching

   Liu, Linfeng; Hughes, Michael C; Hassoun, Soha; Liu, Liping (July 2021, Proceedings of the 38th International Conference on Machine Learning)

   Meila, Marina; Zhang, Tong (Ed.)

   Recent works apply Graph Neural Networks (GNNs) to graph matching tasks and show promising results. Considering that model outputs are complex matchings, we devise several techniques to improve the learning of GNNs and obtain a new model, Stochastic Iterative Graph MAtching (SIGMA). Our model predicts a distribution of matchings, instead of a single matching, for a graph pair so the model can explore several probable matchings. We further introduce a novel multi-step matching procedure, which learns how to refine a graph pair’s matching results incrementally. The model also includes dummy nodes so that the model does not have to find matchings for nodes without correspondence. We fit this model to data via scalable stochastic optimization. We conduct extensive experiments across synthetic graph datasets as well as biochemistry and computer vision applications. Across all tasks, our results show that SIGMA can produce significantly improved graph matching results compared to state-of-the-art models. Ablation studies verify that each of our components (stochastic training, iterative matching, and dummy nodes) offers noticeable improvement. 

   more » « less
4. SeedGNN: Graph Neural Network for Supervised Seeded Graph Matching

   Yu, Liren; Xu, Jiaming; Lin, Xiaojun (July 2023, International Conference on Machine Learning)
5. Efficient Belief Propagation for Graph Matching

   https://doi.org/10.1109/ICASSP40776.2020.9053147  

   Onaran, Efe; Villar, Soledad (May 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP))