LPFormer: An Adaptive Graph Transformer for Link Prediction
Open Access
- 24 August 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2686-2698
Abstract
Link prediction is a common task on graph-structured data that has seen applications in a variety of domains. Classically, hand-crafted heuristics were used for this task. Heuristic measures are chosen such that they correlate well with the underlying factors related to link formation. In recent years, a new class of methods has emerged that combines the advantages of message-passing neural networks (MPNN) and heuristics methods. These methods perform predictions by using the output of an MPNN in conjunction with a "pairwise encoding" that captures the relationship between nodes in the candidate link. They have been shown to achieve strong performance on numerous datasets. However, current pairwise encodings often contain a strong inductive bias, using the same underlying factors to classify all links. This limits the ability of existing methods to learn how to properly classify a variety of different links that may form from different factors. To address this limitation, we propose a new method, LPFormer, which attempts to adaptively learn the pairwise encodings for each link. LPFormer models the link factors via an attention module that learns the pairwise encoding that exists between nodes by modeling multiple factors integral to link prediction. Extensive experiments demonstrate that LPFormer can achieve SOTA performance on numerous datasets while maintaining efficiency. The code is available at The code is available at https://github.com/HarryShomer/LPFormer.Keywords
All Related Versions
Funding Information
- Army Research Office
- NSF (National Science Foundation)
- Snap
- Cisco Systems
- Home Depot
- JP Morgan Faculty Award
- Johnson and Johnson
- Amazon Faculty Award
This publication has 17 references indexed in Scilit:
- Multi-Scale attributed node embeddingJournal of Complex Networks, 2021
- Applications of link prediction in social networks: A reviewJournal of Network and Computer Applications, 2020
- Structural Diversity and Homophily2017
- Strong Localization in Personalized PageRank VectorsLecture Notes in Computer Science, 2015
- Triadic Closure Pattern Analysis and Prediction in Social NetworksIEEE Transactions on Knowledge and Data Engineering, 2015
- Predicting missing links via local informationThe European Physical Journal B, 2009
- The heat kernel as the pagerank of a graphProceedings of the National Academy of Sciences, 2007
- Local Graph Partitioning using PageRank Vectors2006
- Link prediction approach to collaborative filtering2005
- A New Status Index Derived from Sociometric AnalysisPsychometrika, 1953