A Unified View on Graph Neural Networks as Graph Signal Denoising

Ma, Yao; Liu, Xiaorui; Zhao, Tong; Liu, Yozen; Tang, Jiliang; Shah, Neil

doi:10.1145/3459637.3482225

Cited by 95 publications

(70 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…FMP Scheme. Similar to works (Ma et al, 2021c;Liu et al, 2021), choosing γ = 1 1+λ f and β = 1 2γ , we have…”

Section: D3 Fair Message Passing Schemementioning

confidence: 70%

“…Recent works (Ma et al, 2021c;Zhu et al, 2021) have established the connections between many feature aggregation operations in representative GNNs and a graph signal denoising problem with Laplacian regularization. Here, we only introduce GCN/SGC as an examples to show the connection from a perspective of graph signal denoising.…”

Section: Gnns As Graph Signal Denoisingmentioning

confidence: 99%

“…Feature aggregation in Graph Convolutional Network (GCN) or Simplifying Graph Convolutional Network (SGC) is given by X agg = ÃX trans , where Ã = D− 1 2 Â D− 1 2 is a normalized self-loop adjacency matrix Â = A + I, and D is degree matrix of Ã. Recent works (Ma et al, 2021c;Zhu et al, 2021) provably demonstrate that such feature aggregation is equivalent to one-step gradient descent to minimize tr(F I − Ã)F with initialization F = X trans .…”

Section: Gnns As Graph Signal Denoisingmentioning

confidence: 99%

“…For smoothness objective, many existing popular message passing scheme can be derived based on gradient descent with appropriate step size choice (Ma et al, 2021c;Zhu et al, 2021). However, directly computing the gradient of the fairness term makes the closed-form gradient complicated since the gradient of l 1 norm involves the sign of elements in the vector.…”

Section: Algorithm For Fair Message Passingmentioning

confidence: 99%

“…Spatial-based GNNs variant are popular due to explicit neighbors' information aggregation, including Graph con-volutional networks (GCN) (Kipf & Welling, 2017), graph attention network (GAT) (Veličković et al, 2018). The unified optimization framework are also provided to unify many existing message passing schemes (Ma et al, 2021c). As for fairness in graph data, many works have been developed to achieve fairness in machine learning community (Chuang & Mroueh, 2020), including fair walk (Rahman et al, 2019), adversarial debiasin (Dai & Wang, 2021), Bayesian approach (Buyl & De Bie, 2020), and contrastive learning (Agarwal et al, 2021).…”

Section: Related Workmentioning

confidence: 99%

See 4 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

“…FMP Scheme. Similar to works (Ma et al, 2021c;Liu et al, 2021), choosing γ = 1 1+λ f and β = 1 2γ , we have…”

Section: D3 Fair Message Passing Schemementioning

confidence: 70%

Section: Gnns As Graph Signal Denoisingmentioning

confidence: 99%

Section: Gnns As Graph Signal Denoisingmentioning

confidence: 99%

Section: Algorithm For Fair Message Passingmentioning

confidence: 99%