526 Hits in 4.0 sec

An Interpretable Graph Generative Model with Heterophily [article]

Sudhanshu Chanpuriya, Ryan A. Rossi, Anup Rao, Tung Mai, Nedim Lipka, Zhao Song, Cameron Musco
2021 arXiv   pre-print
We propose the first edge-independent graph generative model that is a) expressive enough to capture heterophily, b) produces nonnegative embeddings, which allow link predictions to be interpreted in terms  ...  Many models for graphs fall under the framework of edge-independent dot product models.  ...  CONCLUSION We introduce an interpretable, edge-independent graph generative model that is highly expressive at representing both heterophily and overlapping communities.  ... 
arXiv:2111.03030v1 fatcat:sc64kdqmnzdtvabhtajw6wqkum

Graph Neural Networks with Heterophily [article]

Jiong Zhu, Ryan A. Rossi, Anup Rao, Tung Mai, Nedim Lipka, Nesreen K. Ahmed, Danai Koutra
2021 arXiv   pre-print
The proposed framework incorporates an interpretable compatibility matrix for modeling the heterophily or homophily level in the graph, which can be learned in an end-to-end fashion, enabling it to go  ...  In this work, we propose a novel framework called CPGNN that generalizes GNNs for graphs with either homophily or heterophily.  ...  W911NF1810397, an Adobe Digital Experience research faculty award, an Amazon faculty award, a Google faculty award, and AWS Cloud Credits for Research.  ... 
arXiv:2009.13566v3 fatcat:cwiivtjlxnck7bslu6fcvtx6oq

Graph Neural Networks for Graphs with Heterophily: A Survey [article]

Xin Zheng, Yixin Liu, Shirui Pan, Miao Zhang, Di Jin, Philip S. Yu
2022 arXiv   pre-print
Specifically, we propose a systematic taxonomy that essentially governs existing heterophilic GNN models, along with a general summary and detailed analysis.  ...  However, as a ubiquitous graph property in numerous real-world scenarios, heterophily, i.e., nodes with different labels tend to be linked, significantly limits the performance of tailor-made homophilic  ...  Currently, most of heterophilic GNNs are generally evaluated on the first 6 benchmark datasets in Table 2 , with node heterophily and edge heterophily to measure the heterophilic degree of a graph.  ... 
arXiv:2202.07082v1 fatcat:26d5mpnfzbb7fmloytdbj67yxa

GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily [article]

Lun Du, Xiaozhou Shi, Qiang Fu, Xiaojun Ma, Hengyu Liu, Shi Han, Dongmei Zhang
2022 arXiv   pre-print
We conduct extensive experiments on various datasets with different homophily-heterophily properties.  ...  For node-level tasks, GNNs have strong power to model the homophily property of graphs (i.e., connected nodes are more similar) while their ability to capture the heterophily property is often doubtful  ...  GENERALIZATION BOUND OF GCN WITH REGARD TO HOMOPHILY RATIO In this section, we theoretically analyze the generalization ability of Graph Convolutional Networks (GCNs) with regard to different homophily-heterophily  ... 
arXiv:2110.15777v3 fatcat:vy3fql3avjbavoq3bkcoucg7ba

Demystifying Graph Convolution with a Simple Concatenation [article]

Zhiqian Chen, Zonghan Zhang
2022 arXiv   pre-print
in the heterophily case.  ...  On the other hand, many GConv-based models do not quantify the effect of graph topology and node features on performance, and are even surpassed by some models that do not consider graph structure or node  ...  For graph concatenation model, we adopt Deepwalk [20] to generate graph embeddings which are later concatenated with the node features.  ... 
arXiv:2207.12931v1 fatcat:corlluporbhkdgtd6upj4z5lt4

Unifying Homophily and Heterophily Network Transformation via Motifs [article]

Yan Ge, Jun Ma, Li Zhang, Haiping Lu
2020 arXiv   pre-print
H2NT can be used as an enhancer to be integrated with any existing network embedding methods without requiring any changes to latter methods.  ...  However, there is no general and universal solution that takes both into consideration.  ...  A recent transformation model graph diffusion convolution (GDC) [Klicpera et al., 2019] generates a new network by constructing a diffusion graph obtained by a polynomial function, and then sparsify  ... 
arXiv:2012.11400v2 fatcat:llwy5qsp6beuhf57d5gojadxbm

NCGNN: Node-Level Capsule Graph Neural Network for Semisupervised Classification [article]

Rui Yang, Wenrui Dai, Chenglin Li, Junni Zou, Hongkai Xiong
2022 arXiv   pre-print
In this paper, we propose a Node-level Capsule Graph Neural Network (NCGNN) to address these problems with an improved message passing scheme.  ...  Therefore, it can relieve the over-smoothing issue and learn effective node representations over graphs with homophily or heterophily.  ...  viewed as an ensemble of GNN models.  ... 
arXiv:2012.03476v2 fatcat:cuy5bd5ldbcbzfbkkwqpcwewt4

Powerful Graph Convolutioal Networks with Adaptive Propagation Mechanism for Homophily and Heterophily [article]

Tao Wang and Rui Wang and Di Jin and Dongxiao He and Yuxiao Huang
2021 arXiv   pre-print
., nodes with same class are prone to connect to each other), while ignoring the heterophily which exists in many real-world networks (i.e., nodes with different classes tend to form edges).  ...  Then we incorporate the learnable homophily degree into the graph convolution framework, which is trained in an end-to-end schema, enabling it to go beyond the assumption of homophily.  ...  CPGNN (Zhu et al. 2021 ) incorporates an interpretable compatibility matrix for modeling the heterophily or homophily level in graphs, enabling it to go beyond the assumption of strong homophily.  ... 
arXiv:2112.13562v1 fatcat:jwi4mrv4t5hjll5die46e4duzy

Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily [article]

Jie Chen, Shouzhen Chen, Junbin Gao, Zengfeng Huang, Junping Zhang, Jian Pu
2022 arXiv   pre-print
Due to the homophily assumption in graph convolution networks, a common consensus is that graph neural networks (GNNs) perform well on homophilic graphs but may fail on heterophilic graphs with many inter-class  ...  Extensive ablation studies and robustness analysis further verify the effectiveness, robustness, and interpretability of our framework.  ...  GPRGNN [13] modifies the convolution to the generalized page rank and learns an arbitrary K-order polynomial graph filter.  ... 
arXiv:2203.11200v2 fatcat:g3i3qyabavhbtflp3xpbi4htry

Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs [article]

Vijay Lingam, Rahul Ragesh, Arun Iyer, Sundararajan Sellamanickam
2021 arXiv   pre-print
Graph Neural Networks (GNNs) have shown excellent performance on graphs that exhibit strong homophily with respect to the node labels i.e. connected nodes have same labels.  ...  This work is an early investigation into methods that differ from aggregation based approaches.  ...  GPR-GNN [4] takes the idea proposed in APPNP and generalizes the Pagerank model that works well for graphs with varying homophily scores.  ... 
arXiv:2106.12807v1 fatcat:22kx74sgafdidm3b3cl2i63hca

Semi-Supervised Learning with Heterophily [article]

Wolfgang Gatterbauer
2016 arXiv   pre-print
We thus call this formulation Semi-Supervised Learning with Heterophily (SSLH) and show how it generalizes and improves upon a recently proposed approach called Linearized Belief Propagation (LinBP).  ...  We derive a family of linear inference algorithms that generalize existing graph-based label propagation algorithms by allowing them to propagate generalized assumptions about "attraction" or "compatibility  ...  I would like to thank Christos Faloutsos for continued support and Stephan Günneman for insightful comments on an early version of this paper.  ... 
arXiv:1412.3100v2 fatcat:pjhrn5tmoveqtojact3a6itapi

Improving Graph Neural Networks with Simple Architecture Design [article]

Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata
2021 arXiv   pre-print
Finally, we demonstrate with experiments that the model is scalable for large graphs with millions of nodes and billions of edges.  ...  These graphs are often created with assumed intrinsic relations between the entities.  ...  PRELIMINARIES Let = ( , ) be an undirected graph with nodes and edges.  ... 
arXiv:2105.07634v1 fatcat:q4lxkvn2ffa75cwox24lrqndte

How does Heterophily Impact Robustness of Graph Neural Networks? Theoretical Connections and Practical Implications [article]

Jiong Zhu, Junchen Jin, Donald Loveland, Michael T. Schaub, Danai Koutra
2022 arXiv   pre-print
Additionally, combining this design with explicit defense mechanisms against adversarial attacks leads to an improved robustness with up to 18.33% performance increase under attacks compared to the best-performing  ...  vaccinated model.  ...  W911NF1810397, an Adobe Digital Experience research faculty award, an Amazon faculty award, a Google faculty award, and AWS Cloud Credits for Research.  ... 
arXiv:2106.07767v3 fatcat:conprpfs6fe4ld6yprlikzyho4

Simplifying approach to Node Classification in Graph Neural Networks [article]

Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata
2021 arXiv   pre-print
than state-of-the-art GNN models in nine benchmark datasets for the node classification task, with remarkable improvements up to 51.1%.  ...  As different graph datasets show varying levels of homophily and heterophily in features and class label distribution, it becomes essential to understand which features are important for the prediction  ...  Preliminaries Let = ( , ) be an undirected graph with nodes and edges.  ... 
arXiv:2111.06748v1 fatcat:wswnvl3nonbmhi6jm2sn3cox3u

Label-informed Graph Structure Learning for Node Classification [article]

Liping Wang, Fenyu Hu, Shu Wu, Liang Wang
2021 arXiv   pre-print
To tackle this problem, some studies exploit different graph structure learning strategies to refine the original graph structure.  ...  Graph Neural Networks (GNNs) have achieved great success among various domains. Nevertheless, most GNN methods are sensitive to the quality of graph structures.  ...  We train the model using Adam optimizer [5] with an initial learning rate of 0.01.  ... 
arXiv:2108.04595v1 fatcat:l5f5fjf5obajhfkej6sgiizjui
« Previous Showing results 1 — 15 out of 526 results