no code implementations • 17 Apr 2024 • Kaiwen Dong, Zhichun Guo, Nitesh V. Chawla
Link prediction (LP) is a fundamental task in graph representation learning, with numerous applications in diverse domains.
no code implementations • 17 Apr 2024 • Kaiwen Dong, Zhichun Guo, Nitesh V. Chawla
Graph structured data, specifically text-attributed graphs (TAG), effectively represent relationships among varied entities.
no code implementations • 15 Feb 2024 • Zhichun Guo, Tong Zhao, Yozen Liu, Kaiwen Dong, William Shiao, Neil Shah, Nitesh V. Chawla
Graph Neural Networks (GNNs) are prominent in graph machine learning and have shown state-of-the-art performance in Link Prediction (LP) tasks.
no code implementations • 12 Feb 2024 • Kaiwen Dong, Haitao Mao, Zhichun Guo, Nitesh V. Chawla
In this work, we introduce the Universal Link Predictor (UniLP), a novel model that combines the generalizability of heuristic approaches with the pattern learning capabilities of parametric models.
1 code implementation • 2 Sep 2023 • Kaiwen Dong, Zhichun Guo, Nitesh V. Chawla
This discrepancy stems from a fundamental limitation: while MPNNs excel in node-level representation, they stumble with encoding the joint structural features essential to link prediction, like CN.
Ranked #1 on Link Property Prediction on ogbl-citation2
1 code implementation • 29 Nov 2022 • Kaiwen Dong, Yijun Tian, Zhichun Guo, Yang Yang, Nitesh V. Chawla
In this paper, we first identify the dataset shift problem in the link prediction task and provide theoretical analyses on how existing link prediction methods are vulnerable to it.
1 code implementation • 21 Aug 2022 • Yijun Tian, Kaiwen Dong, Chunhui Zhang, Chuxu Zhang, Nitesh V. Chawla
In light of this, we study the problem of generative SSL on heterogeneous graphs and propose HGMAE, a novel heterogeneous graph masked autoencoder model to address these challenges.