Understanding Negative Sampling in Graph Representation Learning - CrossMinds.ai
Understanding Negative Sampling in Graph Representation Learning
Aug 13, 202023 views
Zhen Yang
Graph representation learning has been extensively studied in recent years, in which sampling is a critical point. Prior arts usually,focus on sampling positive node pairs, while the strategy for negative sampling is left insufficiently explored. To bridge the gap,,we systematically analyze the role of negative sampling from the,perspectives of both objective and risk, theoretically demonstrating that negative sampling is as important as positive sampling,in determining the optimization objective and the resulted variance. To the best of our knowledge, we are the first to derive the,theory and quantify that a nice negative sampling distribution is,𝑝,𝑛,(,𝑢,|,𝑣,) ∝,𝑝,𝑑,(,𝑢,|,𝑣,),𝛼,,,0,
SIGKDD_2020
Recommended