Towards Robust Inductive Graph Incremental Learning via Experience Replay

02/07/2023
by   Junwei Su, et al.
0

Inductive node-wise graph incremental learning is a challenging task due to the dynamic nature of evolving graphs and the dependencies between nodes. In this paper, we propose a novel experience replay framework, called Structure-Evolution-Aware Experience Replay (SEA-ER), that addresses these challenges by leveraging the topological awareness of GNNs and importance reweighting technique. Our framework effectively addresses the data dependency of node prediction problems in evolving graphs, with a theoretical guarantee that supports its effectiveness. Through empirical evaluation, we demonstrate that our proposed framework outperforms the current state-of-the-art GNN experience replay methods on several benchmark datasets, as measured by metrics such as accuracy and forgetting.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/22/2020

Continual Graph Learning

Graph Neural Networks (GNNs) have recently received significant research...
research
05/15/2018

Advances in Experience Replay

This project combines recent advances in experience replay techniques, n...
research
02/23/2023

Detachedly Learn a Classifier for Class-Incremental Learning

In continual learning, model needs to continually learn a feature extrac...
research
08/07/2023

AdaER: An Adaptive Experience Replay Approach for Continual Lifelong Learning

Continual lifelong learning is an machine learning framework inspired by...
research
12/20/2021

Lifelong Learning in Evolving Graphs with Limited Labeled Data and Unseen Class Detection

Large-scale graph data in the real-world are often dynamic rather than s...
research
04/19/2023

Quantum deep Q learning with distributed prioritized experience replay

This paper introduces the QDQN-DPER framework to enhance the efficiency ...
research
12/20/2021

Proving Theorems using Incremental Learning and Hindsight Experience Replay

Traditional automated theorem provers for first-order logic depend on sp...

Please sign up or login with your details

Forgot password? Click here to reset