Leveraging Temporal Graph Networks Using Module Decoupling

TL;DR

This paper introduces LDTGN, a lightweight, decoupled model for dynamic graph learning that enables frequent updates with high throughput, outperforming previous methods especially in rapid-update scenarios.

Contribution

The paper proposes a novel decoupling strategy for temporal graph networks, resulting in an efficient model that balances frequent updates and high throughput.

Findings

LDTGN achieves state-of-the-art results on dynamic graph benchmarks.

Our method outperforms previous approaches by over 20% in rapid-update scenarios.

LDTGN maintains high throughput while enabling frequent model updates.

Abstract

Modern approaches for learning on dynamic graphs have adopted the use of batches instead of applying updates one by one. The use of batches allows these techniques to become helpful in streaming scenarios where updates to graphs are received at extreme speeds. Using batches, however, forces the models to update infrequently, which results in the degradation of their performance. In this work, we suggest a decoupling strategy that enables the models to update frequently while using batches. By decoupling the core modules of temporal graph networks and implementing them using a minimal number of learnable parameters, we have developed the Lightweight Decoupled Temporal Graph Network (LDTGN), an exceptionally efficient model for learning on dynamic graphs. LDTG was validated on various dynamic graph benchmarks, providing comparable or state-of-the-art results with significantly higher throughput than previous art. Notably, our method outperforms previous approaches by more than 20\% on benchmarks that require rapid model update rates, such as USLegis or UNTrade. The code to reproduce our experiments is available at \href{https://orfeld415.github.io/module-decoupling}{this http url}.