Diffusion-based Negative Sampling on Graphs for Link Prediction

arXiv:2403.17259v1 Announce Type: new
Abstract: Link prediction is a fundamental task for graph analysis with important applications on the Web, such as social network analysis and recommendation systems, etc. Modern graph link prediction methods often employ a contrastive approach to learn robust node representations, where negative sampling is pivotal. Typical negative sampling methods aim to retrieve hard examples based on either predefined heuristics or automatic adversarial approaches, which might be inflexible or difficult to control. Furthermore, in the context of …

abstract analysis applications arxiv cs.lg cs.si diffusion etc graph graphs learn link prediction modern negative network node pivotal prediction recommendation recommendation systems robust sampling social systems type web