PyTorch-BigGraph: A Large-scale Graph Embedding System

Graph embedding methods produce unsupervised node features from graphs that can then be used for a variety of machine learning tasks. Modern graphs, particularly in industrial applications, contain billions of nodes and trillions of edges, which exceeds the capability of existing embedding systems... (read more)

PDF Abstract

Datasets


Results from the Paper


 Ranked #1 on Link Prediction on YouTube (Macro F1 metric)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Link Prediction FB15k PyTorch BigGraph (ComplEx) Hits@10 0.872 # 2
MRR filtered 0.79 # 2
MRR raw 0.242 # 1
Link Prediction LiveJournal PBG (1 partition) Hits@10 0.857 # 1
MR 245.9 # 1
Link Prediction LiveJournal PyTorch BigGraph MRR 0.749 # 1
Link Prediction YouTube PyTorch BigGraph Macro F1 40.9 # 1
Micro F1 48 # 1

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet