From One to All: Learning to Match Heterogeneous and Partially Overlapped GraphsWeston HunterHui QianChao ZhangNenggan Zheng
1. Introduction and Related Work Our objective in this paper is to marry the (shallow) graph matching to the deep learning formulations. We pro- The problem of graph matching – establishing corre- pose to build models where the graphs are defined over spondences between two graphs ...
在该论文中图匹配网络相比于图嵌入模型取得了更好的实验结果,图匹配网络在以节点为中心聚集信息时加入了该节点和另一个图的匹配信息,在改论文中提到Compared to the graph embedding model, the matching model has the ability to change the representation of the graphs based on the other graph it is compare...
On the other hand, from the top view, protein graphs and their interactions are considered nodes and edges of the PPI graph, respectively. Correspondingly, two GNNs are respectively employed to learn from protein graphs in the bottom view (BGNN) and learn from a PPI graph in the top view ...
Higher-order sequence learning using a structured graph representation - clone-structured cognitive graphs (CSCG) – can explain how the hippocampus learns cognitive maps. CSCG provides novel explanations for transferable schemas and transitive inference in the hippocampus, and for how place cells, splitt...
GNNs utilize the adjacency matrix A and attribute vectors \(\chi\) of nodes in a graph to extract final representation vectors (embeddings) of nodes and graphs. Modern GNNs widely follow a recursive neighbor aggregation strategy, also known as the message passing mechanism, where the process is...
Mathematical graphs are a natural representation for a collection of atoms (e.g., molecules or crystals). Graph deep learning models have been shown to consistently deliver exceptional performance as surrogate models for the prediction of materials properties. In this repository, we have reimplemented...
Generalized Matrix Means for Semi-Supervised Learning with Multilayer Graphs. [pdf] [code] Pedro Mercado, Francesco Tudisco, Matthias Hein. NeurIPS 2019 A Unified Framework for Data Poisoning Attack to Graph-based Semi-supervised Learning. [pdf] Xuanqing Liu, Si Si, Xiaojin Zhu, Yang Li, Cho...
In previous work, we addressed this challenge through a deep learning-based framework, called DeepMatch, that allows us to detect in-vehicle presence with a high degree of accuracy. DeepMatch utilizes the smartphone of a passenger to analyse and match the event streams of its own sensors with...
Be able to apply unsupervised learning algorithms Be able to implement NLP models Be familiar with Recommendation Systems Be able to implement computer vision models Be able to model graphs and network data Be able to implement models for timeseries and forecasting Be familiar with Reinforcement Lear...