CacheDyG introduces a cache‑refine framework that decouples temporal propagation from parameter updates in dynamic graph neural networks. By storing graph‑aware node‑time representations in non‑trainable buffers and updating only a lightweight refiner, residual gate, and link predictor during training, it reduces repeated recomputation of historical structures. Experiments on five benchmarks show that CacheDyG uses fewer trainable parameters, runs faster, and achieves competitive or better predictive performance compared to existing baselines.
By PinHeng Zong, Ye Yuan
arXiv:2608. 06441v1 Announce Type: new Abstract: Full-graph GNN training delivers high accuracy but scales poorly on multi-server clusters due to heavy, irregular inter-node embedding exchanges.
By Guofan Yu, Sitian Chen, Zhenheng Tang, Xiaowen Chu, Amelie Chi Zhou
arXiv:2504. 07337v2 Announce Type: replace Abstract: Aggregating temporal signals from historic interactions is a key step in future link prediction on dynamic graphs.
By Or Feldman, Krishna Sri Ipsit Mantri, Carola-Bibiane Sch\"onlieb, Chaim Baskin, Moshe Eliasof
arXiv:2607. 17374v1 Announce Type: cross Abstract: Graph Neural Network (GNN) inference on billion-scale graphs is challenging due to the large memory footprint of features and embeddings and high disk I/O costs in out-of-core settings.
By Pranjal Naman, Yogesh Simmhan
arXiv:2608. 07733v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) are widely used across domains such as natural sciences, social network analysis, chip design, and recommendation systems.
By Liad Gerstman, Aditya Dhakal, Dejan Milojicic, Avi Mendelson
arXiv:2606. 22180v2 Announce Type: replace-cross Abstract: Graph embedding maps graph nodes into low-dimensional vectors to support applications such as recommendation, fraud detection, and graph-based retrieval-augmented generation (GraphRAG).
By Peng Fang, Arijit Khan, Ziqiang Wu, Zhenli Li, Yibo Zhou, Fang Wang, Dan Feng