LGAINESep 22, 2022

Memory-Augmented Graph Neural Networks: A Brain-Inspired Review

arXiv:2209.10818v27 citationsh-index: 32
Originality Synthesis-oriented
AI Analysis

This is an incremental review that organizes existing literature for researchers in graph neural networks and memory systems.

The paper reviews memory-augmented graph neural networks (GNNs) by proposing a taxonomy and criteria for comparison based on brain-inspired theories, without presenting new experimental results or concrete numbers.

We provide a comprehensive review of the existing literature on memory-augmented GNNs. We review these works through the lens of psychology and neuroscience, which has several established theories on how multiple memory systems and mechanisms operate in biological brains. We propose a taxonomy of memory-augmented GNNs and a set of criteria for comparing their memory mechanisms. We also provide critical discussions on the limitations of these works. Finally, we discuss the challenges and future directions for this area.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes