no code implementations • 9 May 2024 • Jiying Zhang, Zijing Liu, Yu Wang, Yu Li
We propose a novel diffusion model termed SubGDiff for involving the molecular subgraph information in diffusion.
no code implementations • 30 Oct 2022 • Fuyang Li, Jiying Zhang, Xi Xiao, Bin Zhang, Dijun Luo
This paper proposes a two-phase paradigm to aggregate comprehensive information on discrete structures leading to a Discount Markov Diffusion Learnable Kernel (DMDLK).
no code implementations • 19 Aug 2022 • Guanzi Chen, Jiying Zhang, Xi Xiao, Yang Li
In this paper, we present a novel test time adaptation strategy named Graph Adversarial Pseudo Group Contrast (GAPGC), for graph neural networks TTA, to better adapt to the Out Of Distribution (OOD) test data.
no code implementations • 31 Mar 2022 • Guanzi Chen, Jiying Zhang, Xi Xiao, Yang Li
In recent years, hypergraph learning has attracted great attention due to its capacity in representing complex and high-order relationships.
2 code implementations • 31 Mar 2022 • Jiying Zhang, Fuyang Li, Xi Xiao, Tingyang Xu, Yu Rong, Junzhou Huang, Yatao Bian
As a powerful tool for modeling complex relationships, hypergraphs are gaining popularity from the graph learning community.
1 code implementation • 20 Mar 2022 • Jiying Zhang, Xi Xiao, Long-Kai Huang, Yu Rong, Yatao Bian
In this paper, we present a novel optimal transport-based fine-tuning framework called GTOT-Tuning, namely, Graph Topology induced Optimal Transport fine-Tuning, for GNN style backbones.
Ranked #1 on Graph Classification on BBBP
1 code implementation • 12 Jun 2021 • Jiying Zhang, Yuzhao Chen, Xi Xiao, Runiu Lu, Shu-Tao Xia
Hypergraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph-structured data.
1 code implementation • 10 Jun 2021 • Jiying Zhang, Yuzhao Chen, Xi Xiao, Runiu Lu, Shu-Tao Xia
HyperGraph Convolutional Neural Networks (HGCNNs) have demonstrated their potential in modeling high-order relations preserved in graph structured data.
no code implementations • 17 Mar 2021 • Yuzhao Chen, Yatao Bian, Jiying Zhang, Xi Xiao, Tingyang Xu, Yu Rong, Junzhou Huang
Though the multiscale graph learning techniques have enabled advanced feature extraction frameworks, the classic ensemble strategy may show inferior performance while encountering the high homogeneity of the learnt representation, which is caused by the nature of existing graph pooling methods.