Rethinking The Memory Staleness Problem In Dynamics GNN

TL;DR

This paper addresses the memory staleness issue in dynamic graph neural networks by proposing an embedding update method that incorporates similar nodes, achieving comparable or slightly improved results over existing models like TGN.

Contribution

It introduces a novel embedding module that includes similar nodes to mitigate memory staleness in dynamic GNNs, offering a potential pathway for further enhancements.

Findings

Achieved similar results to TGN with slight improvements.

The method shows promise for better memory updates in dynamic graphs.

Potential for further improvement with hyper-parameter tuning.

Abstract

The staleness problem is a well-known problem when working with dynamic data, due to the absence of events for a long time. Since the memory of the node is updated only when the node is involved in an event, its memory becomes stale. Usually, it refers to a lack of events such as a temporal deactivation of a social account. To overcome the memory staleness problem aggregate information from the nodes neighbors memory in addition to the nodes memory. Inspired by that, we design an updated embedding module that inserts the most similar node in addition to the nodes neighbors. Our method achieved similar results to the TGN, with a slight improvement. This could indicate a potential improvement after fine-tuning our hyper-parameters, especially the time threshold, and using a learnable similarity metric.