Results 81 to 90 of about 1,367 (116)

Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach

Graph Neural Networks (GNNs) have proven to be highly effective for node classification tasks across diverse graph structural patterns. Traditionally, GNNs employ a uniform global filter, typically a low-pass filter for homophilic graphs and a high-pass ...
Han, Haoyu, Huang, Wei, Li, Juanhui, Liu, Hui, Lu, Hanqing, Luo, Chen, Tang, Jiliang, Tang, Xianfeng   +7 more
core  

Re-evaluating the Advancements of Heterophilic Graph Learning

arXiv admin note: substantial text overlap with arXiv:2407 ...
Luan, Sitao, Lu, Qincheng, Hua, Chenqing, Wang, Xinyu, Zhu, Jiaqi, Chang, Xiao-Wen   +5 more
openaire   +2 more sources

AGS-GNN: Attribute-guided Sampling for Graph Neural Networks

We propose AGS-GNN, a novel attribute-guided sampling algorithm for Graph Neural Networks (GNNs) that exploits node features and connectivity structure of a graph while simultaneously adapting for both homophily and heterophily in graphs.
Das, Siddhartha Shankar, Ferdous, S M, Halappanavar, Mahantesh M, Pothen, Alex, Serra, Edoardo   +4 more
core  

Regulation of the microtubular cytoskeleton by Polycystin-1 favors focal adhesions turnover to modulate cell adhesion and migration [PDF]

, 2015

core   +1 more source

Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs

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 numerous methods have been proposed to address this challenge, they primarily focus on architectural designs without ...
Qiu, Ruizhong, Li, Ting-Wei, Li, Gaotang, Tong, Hanghang   +3 more
openaire   +2 more sources

Enhancing Graph Learning via Adaptive Neighborhood Feature Mixing [PDF]

Graph Neural Networks (GNNs) have demonstrated remarkable success across various graph-related tasks; however, their performance often suffers when dealing with heterophilic graphs, where connected nodes tend to have dissimilar characteristics.

core   +1 more source

GLANCE: Graph Logic Attention Network with Cluster Enhancement for Heterophilous Graph Representation Learning

Graph Neural Networks (GNNs) have demonstrated significant success in learning from graph-structured data but often struggle on heterophilous graphs, where connected nodes differ in features or class labels. This limitation arises from indiscriminate neighbor aggregation and insufficient incorporation of higher-order structural patterns.
Zhongtian Sun, Anoushka Harit, Alexandra Cristea, Christl A. Donnelly, Pietro Liò   +4 more
openaire   +2 more sources

Graph Neural Networks for Graphs with Heterophily: A Survey

Recent years have witnessed fast developments of graph neural networks (GNNs) that have benefited myriads of graph analytic tasks and applications. In general, most GNNs depend on the homophily assumption that nodes belonging to the same class are more ...
Jin, Di, Li, Ming, Liu, Yixin, Pan, Shirui, Wang, Yi, Yu, Philip S., Zhang, Miao, Zheng, Xin   +7 more
core  

Some of the next articles are maybe not open access.

Related searches:

Graph Aggregating-Repelling Network: Do Not Trust All Neighbors in Heterophilic Graphs

Neural Networks
Graph neural networks (GNNs) have demonstrated exceptional performance in processing various types of graph data, such as citation networks and social networks, etc. Although many of these GNNs prove their superiority in handling homophilic graphs, they often overlook the other kind of widespread heterophilic graphs, in which adjacent nodes tend to ...
Hao Wang, Jinyong Wen, Weiwen Zhang
exaly   +3 more sources

Taming over-smoothing representation on heterophilic graphs

Information Sciences, 2023
Kai Guo, Zeyuan Liu
exaly   +2 more sources