Scholarlink

In this paper, an algorithm of Path-aware Siamese Graph neural network (PSG) for link prediction tasks is proposed. First, PSG captures both nodes and edge features for given two nodes, namely the structure information of k-neighborhoods and relay paths information of the nodes. Furthermore, a novel multi-task GNN framework with self-supervised contrastive learning is proposed for differentiation of positive links and negative links while content and behavior of nodes can be captured simultaneously. We evaluate the proposed algorithm PSG on two link property prediction datasets, ogbl-ddi and ogbl-collab. PSG achieves top-1 performance on ogbl-ddi until submission and top-3 performance on ogbl-collab. The experimental results verify the superiority of our proposed PSG. Our code is available at https://github.com/jingsonglv/PSG .

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Path-Aware Siamese Graph Neural Network for Link Prediction

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Jingsong Lv,
  • Zhao Li,
  • Hongyang Chen,
  • Ting Li

摘要

In this paper, an algorithm of Path-aware Siamese Graph neural network (PSG) for link prediction tasks is proposed. First, PSG captures both nodes and edge features for given two nodes, namely the structure information of k-neighborhoods and relay paths information of the nodes. Furthermore, a novel multi-task GNN framework with self-supervised contrastive learning is proposed for differentiation of positive links and negative links while content and behavior of nodes can be captured simultaneously. We evaluate the proposed algorithm PSG on two link property prediction datasets, ogbl-ddi and ogbl-collab. PSG achieves top-1 performance on ogbl-ddi until submission and top-3 performance on ogbl-collab. The experimental results verify the superiority of our proposed PSG. Our code is available at https://github.com/jingsonglv/PSG .