Self-supervised Representation Learning on Electronic Health Records with Graph Kernel Infomax

09/01/2022
by   Hao-Ren Yao, et al.
0

Learning Electronic Health Records (EHRs) representation is a preeminent yet under-discovered research topic. It benefits various clinical decision support applications, e.g., medication outcome prediction or patient similarity search. Current approaches focus on task-specific label supervision on vectorized sequential EHR, which is not applicable to large-scale unsupervised scenarios. Recently, contrastive learning shows great success on self-supervised representation learning problems. However, complex temporality often degrades the performance. We propose Graph Kernel Infomax, a self-supervised graph kernel learning approach on the graphical representation of EHR, to overcome the previous problems. Unlike the state-of-the-art, we do not change the graph structure to construct augmented views. Instead, we use Kernel Subspace Augmentation to embed nodes into two geometrically different manifold views. The entire framework is trained by contrasting nodes and graph representations on those two manifold views through the commonly used contrastive objectives. Empirically, using publicly available benchmark EHR datasets, our approach yields performance on clinical downstream tasks that exceeds the state-of-the-art. Theoretically, the variation on distance metrics naturally creates different views as data augmentation without changing graph structures.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/05/2021

Collaborative Graph Contrastive Learning: Data Augmentation Composition May Not be Necessary for Graph Representation Learning

Unsupervised graph representation learning is a non-trivial topic for gr...
research
08/24/2020

Contrastive learning, multi-view redundancy, and linear models

Self-supervised learning is an empirically successful approach to unsupe...
research
11/01/2022

Augmentation Invariant Manifold Learning

Data augmentation is a widely used technique and an essential ingredient...
research
06/11/2019

Graph Convolutional Transformer: Learning the Graphical Structure of Electronic Health Records

Effective modeling of electronic health records (EHR) is rapidly becomin...
research
07/05/2022

Features Based Adaptive Augmentation for Graph Contrastive Learning

Self-Supervised learning aims to eliminate the need for expensive annota...
research
06/07/2021

Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast

We consider graph representation learning in a self-supervised manner. G...
research
06/23/2021

From Canonical Correlation Analysis to Self-supervised Graph Neural Networks

We introduce a conceptually simple yet effective model for self-supervis...

Please sign up or login with your details

Forgot password? Click here to reset