Abstract | ||
---|---|---|
Link prediction is one of the most important tasks in graph machine learning, which aims at predicting whether two nodes in a network have an edge. Real-world graphs typically contain abundant node and edge attributes, thus how to perform link prediction by simultaneously learning structure and attribute information from both interactions/paths between two associated nodes and local neighborhood among node's ego subgraph is intractable. To address this issue, we develop a novel Path-aware Graph Neural Network (PaGNN) method for link prediction, which incorporates interaction and neighborhood information into graph neural networks via broadcasting and aggregating operations. And a cache strategy is developed to accelerate the inference process. Extensive experiments show a superior performance of our proposal over state-of-the-art methods on real-world link prediction tasks. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1007/978-3-030-86520-7_24 | MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2021: RESEARCH TRACK, PT II |
DocType | Volume | ISSN |
Conference | 12976 | 0302-9743 |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
11 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shuo Yang | 1 | 0 | 1.01 |
Binbin Hu | 2 | 118 | 11.27 |
Zhiqiang Zhang | 3 | 95 | 14.65 |
Wang Sun | 4 | 0 | 0.34 |
Yang Wang | 5 | 51 | 12.17 |
Jun Zhou | 6 | 614 | 95.94 |
Hongyu Shan | 7 | 0 | 0.34 |
Yuetian Cao | 8 | 0 | 0.34 |
Borui Ye | 9 | 0 | 0.68 |
Yanming Fang | 10 | 19 | 2.07 |
Yuan Qi | 11 | 23 | 2.83 |