Scalable and Efficient Joint Spiking Embedding Predictive Architecture for Large-Scale Dynamic Graphs
This paper proposes SG-JEPA, a method for learning predictive embeddings for large-scale dynamic graphs by partitioning nodes into context and target sets and encoding sequential inputs into spike count embeddings.
SG-JEPA avoids the complex machinery of existing self-supervised methods by partitioning nodes and encoding sequential inputs as spike count embeddings.
Before reading this…
Applications
- →fraud detection
- →recommender systems
To understand this paper, make sure you know these concepts first:
- Understanding of graph learningfind papers →
- Familiarity with spiking neuronsfind papers →
Abstract
More Like ThisDynamic graph learning aims to capture evolving structural and semantic patterns in real-world systems, such as fraud detection and recommender systems. Due to the scarcity of labeled data in real-world dynamic graphs, recent studies have introduced generative or contrastive paradigms (e.g., masked graph autoencoders or graph contrastive learning) to generate task-agnostic graph embeddings. However, these methods typically rely on complex edge-level reconstruction objectives and tailored graph augmentation strategies. This incurs substantial computational overhead when scaling to large-scale dynamic graphs. In this paper, we propose SG-JEPA, a joint spiking embedding predictive architecture for large-scale dynamic graphs. In contrast to existing self-supervised methods, SG-JEPA partitions nodes into context and target sets along the temporal dimension to learn embeddings that are predictive of each other via additional spatial-temporal information. Furthermore, through encoding sequential inputs into coarse-to-fine spike count embeddings, spiking neurons enable SG-JEPA to adapt to the varying computational constraints of downstream tasks. Extensive experiments demonstrate that SG-JEPA achieves competitive or even superior performance over discriminative baselines on node classification, while effectively scaling to the dynamic graph with 13 million edges. SG-JEPA avoids the complex machinery (negative sampling, graph augmentations, edge-level reconstruction, etc.), resulting in superior training efficiency and memory scalability compared with prior self-supervised dynamic graph baselines.