DPGAN: A Dual-Path Generative Adversarial Network for Missing Data Imputation in Graphs

TL;DR

DPGAN introduces a dual-path GAN framework that effectively imputes missing data in graphs by capturing global and local representations, avoiding over-smoothing, and focusing on local subgraph fidelity for improved accuracy.

Contribution

The paper proposes a novel dual-path GAN architecture with specialized generator and discriminator to enhance missing data imputation in graphs, addressing over-smoothing and local fidelity issues.

Findings

Outperforms existing imputation algorithms on benchmark datasets

Effectively captures long-range dependencies in graph data

Reduces over-smoothing in GNN-based imputation methods

Abstract

Missing data imputation poses a paramount challenge when dealing with graph data. Prior works typically are based on feature propagation or graph autoencoders to address this issue. However, these methods usually encounter the over-smoothing issue when dealing with missing data, as the graph neural network (GNN) modules are not explicitly designed for handling missing data. This paper proposes a novel framework, called Dual-Path Generative Adversarial Network (DPGAN), that can deal simultaneously with missing data and avoid over-smoothing problems. The crux of our work is that it admits both global and local representations of the input graph signal, which can capture the long-range dependencies. It is realized via our proposed generator, consisting of two key components, i.e., MLPUNet++ and GraphUNet++. Our generator is trained with a designated discriminator via an adversarial process. In particular, to avoid assessing the entire graph as did in the literature, our discriminator focuses on the local subgraph fidelity, thereby boosting the quality of the local imputation. The subgraph size is adjustable, allowing for control over the intensity of adversarial regularization. Comprehensive experiments across various benchmark datasets substantiate that DPGAN consistently rivals, if not outperforms, existing state-of-the-art imputation algorithms. The code is provided at \url{https://github.com/momoxia/DPGAN}.