no code implementations • 28 Jan 2024 • Rongping Ye, Xiaobing Pei, Haoran Yang, Ruiqi Wang
In this paper, we propose HeIHNN, a hyperedge interaction-aware hypergraph neural network, which captures the interactions among hyperedges during the convolution process and introduce a novel mechanism to enhance information flow between hyperedges and nodes.
no code implementations • 6 Jan 2024 • Yingying He, Xiaobing Pei, Lihong Shen
DQNLog leverages a small amount of labeled data and a large-scale unlabeled dataset, effectively addressing the challenges of imbalanced data and limited labeling.
no code implementations • 8 Dec 2023 • Xiaobing Pei, Haoran Yang, Gang Shen
Recent studies have shown that attackers can catastrophically reduce the performance of GNNs by maliciously modifying the graph structure or node features on the graph.
no code implementations • 31 Aug 2022 • Mingwei Zhou, Xiaobing Pei
Most current methods generate adversarial examples with the $L_p$ norm specification.
1 code implementation • 12 Jan 2022 • Yidi Wang, Xiaobing Pei, Haoxi Zhan
To utilize the multi-view information sufficiently, we design a specific graph learning method by introducing graph regularization and a local structure fusion pattern.
no code implementations • 30 Apr 2021 • Haoxi Zhan, Xiaobing Pei
In this paper, we develop deeper insights into the Mettack algorithm, which is a representative grey-box attacking method, and then we propose a gradient-based black-box attacking algorithm.
no code implementations • 11 Dec 2020 • Haoxi Zhan, Xiaobing Pei
While being able to achieve desirable performance when the perturbation rates are low, such methods are still vulnerable to high perturbation rates.
no code implementations • 21 Oct 2019 • He Tang, Xiaobing Pei, Shilong Huang, Xin Li, Chao Liu
The clinical treatment of degenerative and developmental lumbar spinal stenosis (LSS) is different.