GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding

2 Mar 2019Zhaocheng ZhuShizhen XuMeng QuJian Tang

Learning continuous representations of nodes is attracting growing interest in both academia and industry recently, due to their simplicity and effectiveness in a variety of applications. Most of existing node embedding algorithms and systems are capable of processing networks with hundreds of thousands or a few millions of nodes... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Link Prediction FB15k SimplE MR 74 # 6
MRR 0.779 # 10
[email protected] 0.876 # 10
[email protected] 0.818 # 7
[email protected] 0.721 # 6
training time (s) 2105 # 1
Link Prediction FB15k-237 RotatE MRR 0.314 # 21
[email protected] 0.511 # 18
[email protected] 0.347 # 15
[email protected] 0.217 # 18
MR 176 # 5
training time (s) 857 # 1
Link Prediction WN18 SimplE MRR 0.948 # 7
[email protected] 0.954 # 8
[email protected] 0.950 # 5
[email protected] 0.944 # 5
MR 412 # 4
training time (s) 1042 # 1
Link Prediction WN18RR RotatE MRR 0.490 # 5
[email protected] 0.589 # 3
[email protected] 0.508 # 4
[email protected] 0.439 # 9
MR 1845 # 4
training time (s) 828 # 1
Node Classification YouTube LINE runtime (s) 70.09 # 1
[email protected]% 40.61 # 1
[email protected]% 33.69 # 1