Strong Transitivity Relations and Graph Neural Networks

1 Jan 2024  ·  Yassin Mohamadi, Mostafa Haghir Chehreghani ·

Local neighborhoods play a crucial role in embedding generation in graph-based learning. It is commonly believed that nodes ought to have embeddings that resemble those of their neighbors. In this research, we try to carefully expand the concept of similarity from nearby neighborhoods to the entire graph. We provide an extension of similarity that is based on transitivity relations, which enables Graph Neural Networks (GNNs) to capture both global similarities and local similarities over the whole graph. We introduce Transitivity Graph Neural Network (TransGNN), which more than local node similarities, takes into account global similarities by distinguishing strong transitivity relations from weak ones and exploiting them. We evaluate our model over several real-world datasets and showed that it considerably improves the performance of several well-known GNN models, for tasks such as node classification.

PDF Abstract

Results from the Paper


 Ranked #1 on Node Classification on Citeseer (1:1 Accuracy metric)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Benchmark
Node Classification Citeseer TransGNN 1:1 Accuracy 75.0 # 1
Node Classification Cora TransGNN 1:1 Accuracy 85.1 # 1

Methods