no code implementations • 30 Dec 2021 • Jiyang Bai, Yuxiang Ren, Jiawei Zhang
We demonstrate the effectiveness and efficiency of MeGuide in training various GNNs on multiple datasets.
1 code implementation • 14 Jan 2021 • Yuxiang Ren, Jiyang Bai, Jiawei Zhang
Graph classification is a critical research problem in many applications from different domains.
no code implementations • 17 Feb 2020 • Jiyang Bai, Yuxiang Ren, Jiawei Zhang
To deal with these problems, in this paper, we propose a general subgraph-based training framework, namely Ripple Walk Training (RWT), for deep and large graph neural networks.
no code implementations • 26 Jul 2019 • Jiyang Bai, Yuxiang Ren, Jiawei Zhang
To resolve this problem and further maximize the advantages of genetic algorithm with base learners, we propose to implement the boosting strategy for input model training, which can subsequently improve the effectiveness of genetic algorithm.
no code implementations • 25 Jul 2019 • Jiyang Bai, Yuxiang Ren, Jiawei Zhang
Optimization algorithms with momentum, e. g., (ADAM), have been widely used for building deep learning models due to the faster convergence rates compared with stochastic gradient descent (SGD).