Is Homophily a Necessity for Graph Neural Networks?

Ma, Yao; Liu, Xiaorui; Shah, Neil; Tang, Jiliang

doi:10.48550/arxiv.2106.06134

Cited by 14 publications

(26 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The behaviors of graph neural networks have been investigated in the context of label homophily for connected node pairs in graphs (Ma et al, 2021b). Label homophily in graphs is typically defined to characterize the similarity of connected node labels in graphs.…”

Section: Label and Sensitive Homophily In Graphsmentioning

confidence: 99%

“…From the perspective of fairness, we also define the sensitive homophily coefficient to represent the sensitive attribute similarity among connected node pairs. Informally, the coefficient for label homophily and sensitive homophily are defined as the fraction of the edges connecting the nodes of the same class label and sensitive attributes in a graph (Zhu et al, 2020;Ma et al, 2021b). We also provide the formal definition as follows:…”

Section: Label and Sensitive Homophily In Graphsmentioning

confidence: 99%

Section: Label and Sensitive Homophily In Graphsmentioning

confidence: 99%

“…Recent works (Ma et al, 2021b;Chien et al, 2021;Zhu et al, 2020) aim to understand the relation between the message passing in GNNs and label homophily from the interactions between GNNs (model) and graph topology (data). For graph data with a high label homophily coefficient, existing works (Ma et al, 2021b;Tang et al, 2020) have demonstrated, either provably or empirically, that the nodes with higher node degree obtain more prediction benefits in GCN, compared to the benefits that peripheral nodes obtain. As for graph data with a low label homophily coefficient, GNNs does not necessarily lead to better prediction performance compared with MLP since since the node features of neighbors with different labels contaminates the node features during feature aggregation.…”

Section: Label and Sensitive Homophily In Graphsmentioning

confidence: 99%

See 3 more Smart Citations

FMP: Toward Fair Graph Message Passing against Topology Bias

Jiang¹,

Han²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Despite recent advances in achieving fair representations and predictions through regularization, adversarial debiasing, and contrastive learning in graph neural networks (GNNs), the working mechanism (i.e., message passing) behind GNNs inducing unfairness issue remains unknown. In this work, we theoretically and experimentally demonstrate that representative aggregation in message passing schemes accumulates bias in node representation due to topology bias induced by graph topology. Thus, a Fair Message Passing (FMP) scheme is proposed to aggregate useful information from neighbors but minimize the effect of topology bias in a unified framework considering graph smoothness and fairness objectives. The proposed FMP is effective, transparent, and compatible with back-propagation training. An acceleration approach on gradient calculation is also adopted to improve algorithm efficiency. Experiments on node classification tasks demonstrate that the proposed FMP outperforms the state-ofthe-art baselines in effectively and efficiently mitigating bias on three real-world datasets.

show abstract

Section: Label and Sensitive Homophily In Graphsmentioning

confidence: 99%

Section: Label and Sensitive Homophily In Graphsmentioning

confidence: 99%

Section: Label and Sensitive Homophily In Graphsmentioning

confidence: 99%

Section: Label and Sensitive Homophily In Graphsmentioning

confidence: 99%

See 2 more Smart Citations

FMP: Toward Fair Graph Message Passing against Topology Bias

Jiang¹,

Han²,

Chen³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Although GNNs have achieved remarkable results on a wide range of scenarios, their ability to model different properties of graphs has not been analyzed. Many previous studies show that GNNs are more effective in dealing with graphs with good homophily property (i.e., connected nodes are more similar), while their ability to capture heterophily property (i.e., connected nodes are more opposite) is often doubtful [15,16,21,25,32,34]. In addition, even for the graphs with good homophily property, existing works do not model them well enough because they usually treat the homophily as a global property which could be consistently satisfied everywhere in the whole graph.…”

Section: Introductionmentioning

confidence: 99%

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

Du¹,

Shi²,

Fu³

et al. 2021

Preprint

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) are widely used on a variety of graph-based machine learning tasks. 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 heterophily property is often doubtful. This is partially caused by the design of the feature transformation with the same kernel for the nodes in the same hop and the followed aggregation operator. One kernel cannot model the similarity and the dissimilarity (i.e., the positive and negative correlation) between node features simultaneously even though we use attention mechanisms like Graph Attention Network (GAT), since the weight calculated by attention is always a positive value. In this paper, we propose a novel GNN model based on a bi-kernel feature transformation and a selection gate. Two kernels capture homophily and heterophily information respectively, and the gate is introduced to select which kernel we should use for the given node pairs. We conduct extensive experiments on various datasets with different homophily-heterophily properties. The experimental results show consistent and significant improvements against state-of-the-art GNN methods. CCS CONCEPTS• Computing methodologies → Neural networks; • Information systems → Social networks.

show abstract

Graph convolutional and attention models for entity classification in multilayer networks

et al. 2021

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) are powerful tools that are nowadays reaching state of the art performances in a plethora of different tasks such as node classification, link prediction and graph classification. A challenging aspect in this context is to redefine basic deep learning operations, such as convolution, on graph-like structures, where nodes generally have unordered neighborhoods of varying size. State-of-the-art GNN approaches such as Graph Convolutional Networks (GCNs) and Graph Attention Networks (GATs) work on monoplex networks only, i.e., on networks modeling a single type of relation among an homogeneous set of nodes. The aim of this work is to generalize such approaches by proposing a GNN framework for representation learning and semi-supervised classification in multilayer networks with attributed entities, and arbitrary number of layers and intra-layer and inter-layer connections between nodes. We instantiate our framework with two new formulations of GAT and GCN models, namely and , specifically devised for general, attributed multilayer networks. The proposed approaches are evaluated on an entity classification task on nine widely used real-world network datasets coming from different domains and with different structural characteristics. Results show that both our proposed and methods provide effective and efficient solutions to the problem of entity classification in multilayer attributed networks, being faster to learn and offering better accuracy than the competitors. Furthermore, results show how our methods are able to take advantage of the presence of real attributes for the entities, in addition to arbitrary inter-layer connections between the nodes in the various layers.

show abstract

Is Homophily a Necessity for Graph Neural Networks?

Cited by 14 publications

References 41 publications

FMP: Toward Fair Graph Message Passing against Topology Bias

FMP: Toward Fair Graph Message Passing against Topology Bias

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

Graph convolutional and attention models for entity classification in multilayer networks

Contact Info

Product

Resources

About