Edge2Node: Reducing Edge Prediction to Node Classification

6 Nov 2023  ·  Zahed Rahmati ·

Despite the success of graph neural network models in node classification, edge prediction (the task of predicting missing or potential links between nodes in a graph) remains a challenging problem for these models. A common approach for edge prediction is to first obtain the embeddings of two nodes, and then a predefined scoring function is used to predict the existence of an edge between the two nodes. Here, we introduce a preliminary idea called Edge2Node which suggests to directly obtain an embedding for each edge, without the need for a scoring function. This idea wants to create a new graph H based on the graph G given for the edge prediction task, and then suggests reducing the edge prediction task on G to a node classification task on H. We anticipate that this introductory method could stimulate further investigations for edge prediction task.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Property Prediction ogbl-collab E2N Test Hits@50 0.9515 ± 0.1410 # 1
Validation Hits@50 0.9546 ± 0.1270 # 9
Number of params 526851 # 16
Ext. data No # 1
Link Prediction ogbl-collab Edge2Node Test Hits@50 0.9515 # 1
Link Property Prediction ogbl-ppa ** E2N** Test Hits@100 0.8911 ± 0.1266 # 1
Validation Hits@100 0.8857 ± 0.1331 # 1
Number of params 526851 # 11
Ext. data No # 1

Methods