Confidence-Based Feature Imputation for Graphs with Partially Known Features

by   Daeho Um, et al.
Seoul National University

This paper investigates a missing feature imputation problem for graph learning tasks. Several methods have previously addressed learning tasks on graphs with missing features. However, in cases of high rates of missing features, they were unable to avoid significant performance degradation. To overcome this limitation, we introduce a novel concept of channel-wise confidence in a node feature, which is assigned to each imputed channel feature of a node for reflecting certainty of the imputation. We then design pseudo-confidence using the channel-wise shortest path distance between a missing-feature node and its nearest known-feature node to replace unavailable true confidence in an actual learning process. Based on the pseudo-confidence, we propose a novel feature imputation scheme that performs channel-wise inter-node diffusion and node-wise inter-channel propagation. The scheme can endure even at an exceedingly high missing rate (e.g., 99.5%) and it achieves state-of-the-art accuracy for both semi-supervised node classification and link prediction on various datasets containing a high rate of missing features. Codes are available at


page 17

page 18


Missing Data Imputation for Classification Problems

Imputation of missing data is a common application in various classifica...

Graph Convolutional Networks for Graphs Containing Missing Features

Graph Convolutional Network (GCN) has experienced great success in graph...

Leveraging Prototype Patient Representations with Feature-Missing-Aware Calibration to Mitigate EHR Data Sparsity

Electronic Health Record (EHR) data frequently exhibits sparse character...

Select and Calibrate the Low-confidence: Dual-Channel Consistency based Graph Convolutional Networks

The Graph Convolutional Networks (GCNs) have achieved excellent results ...

On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features

While Graph Neural Networks (GNNs) have recently become the de facto sta...

Please sign up or login with your details

Forgot password? Click here to reset