LGJan 27, 2025

ScaDyG:A New Paradigm for Large-scale Dynamic Graph Learning

arXiv:2501.16002v21 citationsh-index: 10IEEE Trans Neural Netw Learn Syst
Originality Highly original
AI Analysis

This addresses scalability problems for large-scale dynamic graph applications in industry, representing a novel paradigm rather than an incremental improvement.

The paper tackles scalability issues in dynamic graph learning by proposing ScaDyG, a new paradigm that segments historical interactions and uses hypernetwork-driven aggregation, achieving comparable or better performance than state-of-the-art methods on 12 datasets with fewer parameters and higher efficiency.

Dynamic graphs (DGs), which capture time-evolving relationships between graph entities, have widespread real-world applications. To efficiently encode DGs for downstream tasks, most dynamic graph neural networks follow the traditional message-passing mechanism and extend it with time-based techniques. Despite their effectiveness, the growth of historical interactions introduces significant scalability issues, particularly in industry scenarios. To address this limitation, we propose ScaDyG, with the core idea of designing a time-aware scalable learning paradigm as follows: 1) Time-aware Topology Reformulation: ScaDyG first segments historical interactions into time steps (intra and inter) based on dynamic modeling, enabling weight-free and time-aware graph propagation within pre-processing. 2) Dynamic Temporal Encoding: To further achieve fine-grained graph propagation within time steps, ScaDyG integrates temporal encoding through a combination of exponential functions in a scalable manner. 3) Hypernetwork-driven Message Aggregation: After obtaining the propagated features (i.e., messages), ScaDyG utilizes hypernetwork to analyze historical dependencies, implementing node-wise representation by an adaptive temporal fusion. Extensive experiments on 12 datasets demonstrate that ScaDyG performs comparably well or even outperforms other SOTA methods in both node and link-level downstream tasks, with fewer learnable parameters and higher efficiency.

Foundations

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

Your Notes