CoRe-GNN: Multilevel Message passing on Coarsened graphs

ADC-GNN: Adaptive Dual-level Collaborative Graph Neural Networks for Graph Classification

DeltaGNN: Graph Neural Network with Information Flow Control

Graph Neural Networks (GNNs) are popular deep learning models designed to process graph-structured data through recursive neighborhood aggregations in the message passing process. When applied to semi-supervised node classification, the message-passing enables GNNs to understand short-range spatial interactions, but also causes them to suffer from over-smoothing and over-squashing. These challenges hinder model expressiveness and prevent the use of deeper models to capture long-range node interactions (LRIs) within the graph. Popular solutions for LRIs detection are either too expensive to process large graphs due to high time complexity or fail to generalize across diverse graph structures. To address these limitations, we propose a mechanism called information flow control, which leverages a novel connectivity measure, called information flow score, to address over-smoothing and over-squashing with linear computational overhead, supported by theoretical evidence. Building on this mechanism, we introduce DeltaGNN, to the best of our knowledge among the first scalable (featuring linear computational and memory complexity overhead) and generalizable (capable of effectively handling graphs with diverse homophily, density, and topology) architectures for long-range and short-range interaction detection. We benchmark our model across 10 real-world datasets, including graphs with varying sizes, topologies, densities, and homophilic ratios, showing superior performance with limited computational complexity.

SNI-GNN: SmartNIC-Assisted Full-Graph GNN Training with In-Network Embedding Prediction

Full-graph GNN training delivers high accuracy but scales poorly on multi-server clusters due to heavy, irregular internode embedding exchanges. We present SNI-GNN, a SmartNICassisted full-graph training system that reduces communication while preserving accuracy by predicting remote embeddings innetwork. SNI-GNN deploys a lightweight linear-trend predictor on SmartNICs to refine cached historical embeddings, coupled with an importance-based boundary-node sampling policy and an asynchronous DPU-GPU data pipeline with intermediateresult reuse. We provide error and convergence bounds showing that predictor bias remains controlled under bounded secondorder dynamics and yields standard non-convex convergence with inexact gradients. Implemented on NVIDIA BlueField-3, SNI-GNN integrates with state-of-the-art full-graph systems, cuts communication by 21-45%, achieves 1.3-3.6 $\times$ end-to-end speedups over BNS-GCN and up to $1.29 \times$ over baseline SANCUS, with accuracy loss $\leq 0.01$, and scales efficiently to 16 GPUs on graphs with up to tens of millions of edges. These results indicate SmartNIC-based in-network prediction is a practical complement to partitioning and compression techniques for communicationefficient full-graph GNN training at scale.

Two-level domain-decomposition AdaGrad method for scalable training of graph neural networks

Graph neural networks (GNNs) have emerged as a powerful framework for learning from graph-structured data. However, their efficient training remains challenging, particularly in distributed computing environments. This challenge arises from the use of message passing, which couples all graph nodes, leading to expensive optimization steps, high memory requirements, and substantial communication overhead. To alleviate these limitations, we propose a novel domain-decomposition (DD) variant of AG2m, an AdaGrad method enhanced with second-order curvature information and momentum, denoted by DD-AG2m. The proposed DD-AG2m alternates between AG2m optimization on the original (global) graph and AG2m optimization on the partitioned graphs. To incorporate global information at reduced cost, we further introduce a two-level variant (2DD-AG2m) that performs global optimization steps on a coarse graph obtained by randomly subsampling nodes within each subdomain. Numerical experiments spanning graph classification, node-level regression, and spatiotemporal forecasting tasks demonstrate that the proposed DD methods reduce the computational cost required to achieve the same predictive performance by a factor of 4-8. Moreover, for the fixed computational cost, they improve the predictive performance of GNNs by up to 22% compared with the baseline AG2m.

Spectral Gap-Driven Coarsening for Dynamic Graph Neural Networks

Dynamic Graph Neural Networks (DGNNs) suffer from a significant scalability bottleneck due to high computational demands resulting from their innate design to aggregate information both over graph topology and over time. While graph coarsening has successfully mitigated these costs for static graph neural networks, its potential remains largely untapped in the dynamic setting. Bridging this gap is particularly challenging because different DGNN architectures in literature aggregate information across structural topologies and temporal dimensions in different manners. %Hence, we require a coarsening method that can adapt to the complexity of a system evolving over time in different manners. In this work, we first group popular DGNNs into two general categories based on their topological and temporal message passing patterns. We then derive appropriate coarsening criteria for both classes of DGNNs with a goal to maximize the connectivity in the coarsened graph. Specifically, we aim to maximize the spectral gap of a generalized combinatorial Laplacian matrix in each case. In order to determine the quality of the candidate node-pairs to merge in an efficient manner, we derive an estimated change in eigenvalues from first principles using the Matrix Perturbation Theory. This leads to a naturally efficient algorithm Spectral-gap Aware Coarsening of Dynamic networks (SACoD). Experimental results demonstrate that our coarsening technique significantly accelerates dynamic GNN training and inference without compromising predictive performance, offering a practical path toward scalable dynamic graph learning.

Subgraph Filtering for Fair Graph Neural Networks

Graph neural networks (GNNs) can exhibit unfair behavior even when sensitive attributes are excluded from node features, because graph topology and message passing propagate group-correlated signals under sensitive homophily. Existing fairness-aware GNN methods mainly constrain representations or prediction distributions at a global level, without explicitly controlling the local structural pathways through which biased information propagates during aggregation. We propose Subgraph Filtering for Fair Graph Neural Networks (SF-GNN), a lightweight and architecture-agnostic framework that mitigates structural bias at its source. SF-GNN identifies bias-prone edges by combining sensitive homophily with structural propagation amplifiers, including hub participation and triadic closure. It then incorporates stochastic edge filtering into each message-passing step to selectively downweight or remove these edges while preserving the remaining graph structure. Training further incorporates a statistical-parity regularizer with a warm-up schedule to stabilize optimization. Experiments on five benchmark datasets show that SF-GNN achieves consistent fairness improvements while maintaining competitive predictive performance, leading to a better fairness--accuracy trade-off than recent fairness-aware GNN baselines.