no code implementations • 22 May 2024 • Xingtong Yu, Zhenghao Liu, Yuan Fang, Xinming Zhang
For dynamic graph modeling, dynamic graph neural networks (DGNNs) have emerged as a mainstream technique, which are generally pre-trained on the link prediction task, leaving a significant gap from the objectives of downstream tasks such as node classification.
no code implementations • 22 May 2024 • Xingtong Yu, Chang Zhou, Yuan Fang, Xinming Zhang
To address these issues, we propose MDGPT, a text free Multi-Domain Graph Pre-Training and adaptation framework designed to exploit multi-domain knowledge for graph learning.
no code implementations • 2 Feb 2024 • Xingtong Yu, Yuan Fang, Zemin Liu, Yuxia Wu, Zhihao Wen, Jianyuan Bo, Xinming Zhang, Steven C. H. Hoi
Finally, we outline prospective future directions for few-shot learning on graphs to catalyze continued innovation in this field.
no code implementations • 4 Dec 2023 • Xingtong Yu, Yuan Fang, Zemin Liu, Xinming Zhang
In this paper, we propose HGPROMPT, a novel pre-training and prompting framework to unify not only pre-training and downstream tasks but also homogeneous and heterogeneous graphs via a dual-template design.
1 code implementation • 28 Nov 2023 • Xingtong Yu, Chang Zhou, Yuan Fang, Xinming Zhang
Hence, in this paper, we propose MultiGPrompt, a novel multi-task pre-training and prompting framework to exploit multiple pretext tasks for more comprehensive pre-trained knowledge.
2 code implementations • 26 Nov 2023 • Xingtong Yu, Zhenghao Liu, Yuan Fang, Zemin Liu, Sihong Chen, Xinming Zhang
In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs.
1 code implementation • 23 Nov 2023 • Peng Xia, Xingtong Yu, Ming Hu, Lie Ju, Zhiyong Wang, Peibo Duan, ZongYuan Ge
We explore constructing the class hierarchy into a graph, with its nodes representing the textual or image features of each category.
Fine-Grained Visual Recognition Graph Representation Learning
1 code implementation • 16 Sep 2023 • Wenyu Zhang, Xin Deng, Baojun Jia, Xingtong Yu, Yifan Chen, Jin Ma, Qing Ding, Xinming Zhang
Additionally, we introduce the MLP-based Sequential Residual Block (MSRB) for robust feature extraction from text images, and a Local Contour Awareness loss ($\mathcal{L}_{lca}$) to enhance the model's perception of details.
2 code implementations • 16 Feb 2023 • Zemin Liu, Xingtong Yu, Yuan Fang, Xinming Zhang
In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner.
1 code implementation • 7 Feb 2023 • Xingtong Yu, Zemin Liu, Yuan Fang, Xinming Zhang
However, typical GNNs employ a node-centric message passing scheme that receives and aggregates messages on nodes, which is inadequate in complex structure matching for isomorphism counting.
no code implementations • 29 Sep 2021 • Xingtong Yu, Zemin Liu, Yuan Fang, Xinming Zhang
At the graph level, we modulate the graph representation conditioned on the query subgraph, so that the model can be adapted to each unique query for better matching with the input graph.