English
Related papers

Related papers: Non-Homophilic Graph Pre-Training and Prompt Learn…

200 papers

Graph neural networks (GNNs) have emerged as a powerful tool for modeling graph-structured data. However, existing GNNs often struggle with heterophilic graphs, where connected nodes tend to have dissimilar features or labels. While…

Machine Learning · Computer Science 2026-02-10 Ruizhong Qiu , Ting-Wei Li , Gaotang Li , Hanghang Tong

The pre-train then fine-tune approach has advanced GNNs by enabling general knowledge capture without task-specific labels. However, an objective gap between pre-training and downstream tasks limits its effectiveness. Recent graph prompting…

Machine Learning · Computer Science 2025-01-28 Qin Chen , Liang Wang , Bo Zheng , Guojie Song

Recently, ''pre-training and fine-tuning'' has been adopted as a standard workflow for many graph tasks since it can take general graph knowledge to relieve the lack of graph annotations from each application. However, graph tasks with node…

Social and Information Networks · Computer Science 2023-12-19 Xiangguo Sun , Hong Cheng , Jia Li , Bo Liu , Jihong Guan

In-context learning is the ability of a pretrained model to adapt to novel and diverse downstream tasks by conditioning on prompt examples, without optimizing any parameters. While large language models have demonstrated this ability, how…

Machine Learning · Computer Science 2023-05-23 Qian Huang , Hongyu Ren , Peng Chen , Gregor Kržmanc , Daniel Zeng , Percy Liang , Jure Leskovec

Heterophilic Graph Neural Networks (HGNNs) have shown promising results for semi-supervised learning tasks on graphs. Notably, most real-world heterophilic graphs are composed of a mixture of nodes with different neighbor patterns,…

Machine Learning · Computer Science 2025-02-26 Jinluan Yang , Zhengyu Chen , Teng Xiao , Wenqiao Zhang , Yong Lin , Kun Kuang

Graph self-supervised learning has gained increasing attention due to its capacity to learn expressive node representations. Many pretext tasks, or loss functions have been designed from distinct perspectives. However, we observe that…

Machine Learning · Computer Science 2022-03-23 Wei Jin , Xiaorui Liu , Xiangyu Zhao , Yao Ma , Neil Shah , Jiliang Tang

Graph Neural Networks (GNNs) have become pivotal tools for a range of graph-based learning tasks. Notably, most current GNN architectures operate under the assumption of homophily, whether explicitly or implicitly. While this underlying…

Machine Learning · Computer Science 2024-06-19 Kun Wang , Guibin Zhang , Xinnan Zhang , Junfeng Fang , Xun Wu , Guohao Li , Shirui Pan , Wei Huang , Yuxuan Liang

Despite the recent progress in Graph Neural Networks (GNNs), it remains challenging to explain the predictions made by GNNs. Existing explanation methods mainly focus on post-hoc explanations where another explanatory model is employed to…

Machine Learning · Computer Science 2021-12-03 Zaixi Zhang , Qi Liu , Hao Wang , Chengqiang Lu , Cheekong Lee

Many widely used datasets for graph machine learning tasks have generally been homophilous, where nodes with similar labels connect to each other. Recently, new Graph Neural Networks (GNNs) have been developed that move beyond the homophily…

Machine Learning · Computer Science 2021-10-28 Derek Lim , Felix Hohne , Xiuyu Li , Sijia Linda Huang , Vaishnavi Gupta , Omkar Bhalerao , Ser-Nam Lim

Many applications of machine learning require a model to make accurate pre-dictions on test examples that are distributionally different from training ones, while task-specific labels are scarce during training. An effective approach to…

Machine Learning · Computer Science 2020-02-20 Weihua Hu , Bowen Liu , Joseph Gomes , Marinka Zitnik , Percy Liang , Vijay Pande , Jure Leskovec

Graph neural networks (GNNs) have shown great prowess in learning representations suitable for numerous graph-based machine learning tasks. When applied to semi-supervised node classification, GNNs are widely believed to work well due to…

Machine Learning · Computer Science 2023-07-24 Yao Ma , Xiaorui Liu , Neil Shah , Jiliang Tang

Graph Neural Networks (GNNs) have achieved remarkable performance in modeling graphs for various applications. However, most existing GNNs assume the graphs exhibit strong homophily in node labels, i.e., nodes with similar labels are…

Machine Learning · Computer Science 2023-02-20 Enyan Dai , Shijie Zhou , Zhimeng Guo , Suhang Wang

Graph neural networks (GNNs) have emerged as a powerful tool for modeling graph-structured data. However, existing GNNs often struggle with heterophilic graphs, where connected nodes tend to have dissimilar features or labels. While…

Machine Learning · Computer Science 2025-09-17 Ruizhong Qiu , Ting-Wei Li , Gaotang Li , Hanghang Tong

Under circumstances of heterophily, where nodes with different labels tend to be connected based on semantic meanings, Graph Neural Networks (GNNs) often exhibit suboptimal performance. Current studies on graph heterophily mainly focus on…

Machine Learning · Computer Science 2024-11-13 Yilun Zheng , Jiahao Xu , Lihui Chen

Graph neural networks (GNNs) are widely applied in graph data modeling. However, existing GNNs are often trained in a task-driven manner that fails to fully capture the intrinsic nature of the graph structure, resulting in sub-optimal node…

Machine Learning · Computer Science 2024-07-17 Zhenhua Huang , Kunhao Li , Shaojie Wang , Zhaohong Jia , Wentao Zhu , Sharad Mehrotra

Prompt learning has attracted increasing attention in the graph domain as a means to bridge the gap between pretext and downstream tasks. Existing studies on heterogeneous graph prompting typically use feature prompts to modify node…

Machine Learning · Computer Science 2025-02-14 Feiyang Wang , Zhongbao Zhang , Junda Ye , Li Sun , Jianzhong Qi

Graph Neural Networks (GNNs) have proven to be useful for many different practical applications. However, many existing GNN models have implicitly assumed homophily among the nodes connected in the graph, and therefore have largely…

Machine Learning · Computer Science 2021-06-16 Jiong Zhu , Ryan A. Rossi , Anup Rao , Tung Mai , Nedim Lipka , Nesreen K. Ahmed , Danai Koutra

Self-supervised learning has shown its promising capability in graph representation learning in recent work. Most existing pre-training strategies usually choose the popular Graph neural networks (GNNs), which can be seen as a special form…

Machine Learning · Computer Science 2023-06-16 Yilin Ding , Zhen Liu , Hao Hao

In recent years, graph prompting has emerged as a promising research direction, enabling the learning of additional tokens or subgraphs appended to the original graphs without requiring retraining of pre-trained graph models across various…

Machine Learning · Computer Science 2025-05-28 Qunzhong Wang , Xiangguo Sun , Hong Cheng

Graph neural networks (GNNs) provide important prospective insights in applications such as social behavior analysis and financial risk analysis based on their powerful learning capabilities on graph data. Nevertheless, GNNs' predictive…

Machine Learning · Computer Science 2024-12-23 Yuecen Wei , Xingcheng Fu , Lingyun Liu , Qingyun Sun , Hao Peng , Chunming Hu