arXiv:2509. 06777v2 Announce Type: replace Abstract: Graph Neural Networks (GNNs) suffer from oversquashing, where structural bottlenecks limit message propagation between distant nodes, hindering tasks that require long-range interactions.
arXiv:2608. 02128v1 Announce Type: new Abstract: Training Graph Neural Networks on large graphs is challenged by the memory cost of storing all node representations across layers.
arXiv:2311. 07073v3 Announce Type: replace Abstract: Graph-based message-passing neural networks (MPNNs) have achieved remarkable success in both node and graph-level learning tasks.
arXiv:2607. 17272v1 Announce Type: new Abstract: Node representation learning has advanced rapidly, yet most existing methods rely on per-dataset training and hyperparameter tuning.
Training Graph Neural Networks on large graphs is challenged by the memory cost of storing all node representations across layers. We show that several existing scalable approaches can be written as structured modifications of the GNN propagation matrix, providing a unified perspective that exposes their respective limitations.
arXiv:2603. 06952v2 Announce Type: replace Abstract: As graphs scale to billions of nodes and edges, graph Machine Learning workloads are constrained by the cost of multi-hop traversals over exponentially growing neighborhoods.
arXiv:2601. 23207v2 Announce Type: replace-cross Abstract: Understanding what graph neural networks can learn, especially their ability to learn to execute algorithms, remains a central theoretical challenge.
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.
arXiv:2607. 05017v1 Announce Type: cross Abstract: The performance of deep learning models crucially depends on the settings of hyperparameters like learning rate, initialization scale, and weight decay.
arXiv:2607. 27479v1 Announce Type: new Abstract: The information flow in the graph neural networks (GNNs) is fundamentally constrained by over-squashing, where structural bottlenecks impede long range information propagation.
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.
arXiv:2511. 11046v3 Announce Type: replace-cross Abstract: Graph neural networks (GNNs) have become an indispensable tool for analyzing relational data.
arXiv:2605. 21247v3 Announce Type: replace Abstract: Graph Neural Networks (GNNs) have emerged as a cornerstone of deep learning, with most existing methods rooted in graph signal processing and diffusion equations to model message passing.