SIGMA is a unified streaming graph partitioner supporting configurable vertex- and edge-balanced partitioning for distributed GNN training across different system architectures.
hub Mixed citations
Pitfalls of Graph Neural Network Evaluation
Mixed citation behavior. Most common role is background (50%).
40
Pith papers citing it
Background
50% of classified citations
abstract
Semi-supervised node classification in graphs is a fundamental problem in graph mining, and the recently proposed graph neural networks (GNNs) have achieved unparalleled results on this task. Due to their massive success, GNNs have attracted a lot of attention, and many novel architectures have been put forward. In this paper we show that existing evaluation strategies for GNN models have serious shortcomings. We show that using the same train/validation/test splits of the same datasets, as well as making significant changes to the training procedure (e.g. early stopping criteria) precludes a fair comparison of different architectures. We perform a thorough empirical evaluation of four prominent GNN models and show that considering different splits of the data leads to dramatically different rankings of models. Even more importantly, our findings suggest that simpler GNN architectures are able to outperform the more sophisticated ones if the hyperparameters and the training procedure are tuned fairly for all models.
hub tools
citation-role summary
background 5
dataset 3
citation-polarity summary
representative citing papers
FilterMoE uses joint node-channel routing of Chebyshev filter experts through a 3D gating tensor in pre-propagation GNNs and outperforms baselines on nine of eleven benchmarks while ranking first on all three large-scale ones with a 1.53-point average gain.
Contrastive Message Passing lets GNNs apply similarity-preserving transforms to positive edges and dissimilarity-inducing transforms to negative edges via soft positive semidefinite constraints on weights, yielding gains in low-label high-homophily regimes.
HyperGRL places graph nodes on a hypersphere and minimizes Helmholtz free energy with structural binding energy and mean-field repulsive potential, regulated by an adaptive thermostat, to produce discriminative representations.
HSG-12M is a large dataset of spatial multigraphs derived from non-Hermitian crystal energy spectra via the Poly2Graph pipeline, positioned as the first large-scale benchmark of this graph type.
Neighbourhood Transformers apply local self-attention for monophily-aware graph learning, guarantee expressiveness at least as strong as message-passing GNNs, and outperform prior methods on node classification across ten datasets while cutting memory and time costs substantially.
FedLAB organizes multimodal graph knowledge into typed hierarchical codebooks for modality evidence, node semantics, and topology context via federated semantic barycenter pre-training, improving performance by up to 7.53% on benchmarks while enabling semantic traceability.
GraphMNL applies negative learning as cross-branch guidance in multimodal graphs to mitigate semantic imbalance without propagating bias from dominant branches.
Introduces the SORB benchmark showing that sparsification and coarsening effects on influence maximization performance depend strongly on network type and evaluation metric.
UGCA increases Expected Calibration Error of GNNs under adversarial edge perturbations while preserving classification accuracy, with theoretical links between model accuracy, dataset complexity, and vulnerability.
KGEMs for link prediction exhibit high instability in predictions and embeddings from initialization, negative sampling, and other factors, with better MRR not ensuring higher stability.
CE-FedGNN enables federated GNN training on coupled distributed graphs via infrequent aggregated representation exchange, moving-average estimation for staleness, and metric-DP, with O(1/sqrt(T)) convergence and O(T^{3/4}) communication.
ReFi-GAD uses a semantics-aware relational fingerprint and transformer-based model with SNR refinement to align heterogeneous features for generalist graph anomaly detection across unseen graphs.
VISION unifies unsupervised meta-learning and graph in-context learning to enable fine-tuning-free inference for node classification on novel classes by generating class-aware representations conditioned on support set context.
GNSN adds convection governed by a dynamic velocity field to graph message passing, adaptively balancing it with diffusion to handle varying homophily levels and reduce oversmoothing while outperforming baselines on 12 datasets.
Invariant-Stratified Propagation (ISP) enhances GNN expressivity beyond 1-WL by stratifying nodes according to graph invariants and encoding structural heterogeneity in hierarchical strata.
Fed-Listing infers client label proportions in FedGNNs from final-layer gradients, outperforming baselines on four datasets and three architectures even in non-i.i.d. settings.
C3E estimates hidden dimensions and depths for GNNs by treating them as communication channels to reduce over-squashing and improve representation learning.
SAGE is a self-evolving agentic graph-memory engine that dynamically constructs and refines structured memory graphs via writer-reader feedback, yielding performance gains on multi-hop QA, open-domain retrieval, and long-term agent benchmarks.
RS-GNNs predict random sets over classes using belief functions to jointly produce class probabilities and epistemic uncertainty estimates for graph nodes.
R-GFM constructs multi-scale Riemannian graph-of-graphs to learn geometry-adaptive representations, reducing structural domain generalization error and delivering up to 49% relative gains on downstream graph tasks.
UFO combines flow-based generative replay with instance-level reliability scoring to handle both catastrophic forgetting and catastrophic remembering from noisy supervision in evolving graphs, outperforming baselines on four datasets.
M2D distillation augments input graphs with model-derived features and structure, letting simple student GNNs match teacher performance while exposing mechanisms such as attention and fairness directly in the data.
A large-scale standardized benchmark of GNN attacks and defenses reveals that target node selection and attacked-model training process can completely distort measured attack effectiveness.
citing papers explorer
-
Gate the Filter, Not the Message: Node-Channel Mixtures for Pre-Propagation GNNs
FilterMoE uses joint node-channel routing of Chebyshev filter experts through a 3D gating tensor in pre-propagation GNNs and outperforms baselines on nine of eleven benchmarks while ranking first on all three large-scale ones with a 1.53-point average gain.
-
Learning over Positive and Negative Edges with Contrastive Message Passing
Contrastive Message Passing lets GNNs apply similarity-preserving transforms to positive edges and dissimilarity-inducing transforms to negative edges via soft positive semidefinite constraints on weights, yielding gains in low-label high-homophily regimes.
-
Neighbourhood Transformer: Switchable Attention for Monophily-Aware Graph Learning
Neighbourhood Transformers apply local self-attention for monophily-aware graph learning, guarantee expressiveness at least as strong as message-passing GNNs, and outperform prior methods on node classification across ten datasets while cutting memory and time costs substantially.
-
FedLAB: Traceable Semantic Codebooks for Federated Multimodal Graph Foundation Learning
FedLAB organizes multimodal graph knowledge into typed hierarchical codebooks for modality evidence, node semantics, and topology context via federated semantic barycenter pre-training, improving performance by up to 7.53% on benchmarks while enabling semantic traceability.
-
Multimodal Graph Negative Learning
GraphMNL applies negative learning as cross-branch guidance in multimodal graphs to mitigate semantic imbalance without propagating bias from dominant branches.
-
The Confidence Trap: Calibration Attacks for Graph Neural Networks
UGCA increases Expected Calibration Error of GNNs under adversarial edge perturbations while preserving classification accuracy, with theoretical links between model accuracy, dataset complexity, and vulnerability.
-
Link Prediction or Perdition: the Seeds of Instability in Knowledge Graph Embeddings
KGEMs for link prediction exhibit high instability in predictions and embeddings from initialization, negative sampling, and other factors, with better MRR not ensuring higher stability.
-
Provably Communication-Efficient and Privacy-Preserving Federated Graph Neural Networks
CE-FedGNN enables federated GNN training on coupled distributed graphs via infrequent aggregated representation exchange, moving-average estimation for staleness, and metric-DP, with O(1/sqrt(T)) convergence and O(T^{3/4}) communication.
-
Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach
ReFi-GAD uses a semantics-aware relational fingerprint and transformer-based model with SNR refinement to align heterogeneous features for generalist graph anomaly detection across unseen graphs.
-
Graph Navier Stokes Networks
GNSN adds convection governed by a dynamic velocity field to graph message passing, adaptively balancing it with diffusion to handle varying homophily levels and reduce oversmoothing while outperforming baselines on 12 datasets.
-
Invariant-Stratified Propagation for Expressive Graph Neural Networks
Invariant-Stratified Propagation (ISP) enhances GNN expressivity beyond 1-WL by stratifying nodes according to graph invariants and encoding structural heterogeneity in hierarchical strata.
-
Fed-Listing: Federated Label Distribution Inference in Graph Neural Networks
Fed-Listing infers client label proportions in FedGNNs from final-layer gradients, outperforming baselines on four datasets and three architectures even in non-i.i.d. settings.
-
Learning Graph Foundation Models on Riemannian Graph-of-Graphs
R-GFM constructs multi-scale Riemannian graph-of-graphs to learn geometry-adaptive representations, reducing structural domain generalization error and delivering up to 49% relative gains on downstream graph tasks.
-
UFO: A Unified Flow-Oriented Framework for Robust Continual Graph Learning
UFO combines flow-based generative replay with instance-level reliability scoring to handle both catastrophic forgetting and catastrophic remembering from noisy supervision in evolving graphs, outperforming baselines on four datasets.
-
From Model to Data (M2D): Shifting Complexity from GNNs to Graphs for Transparent Graph Learning
M2D distillation augments input graphs with model-derived features and structure, letting simple student GNNs match teacher performance while exposing mechanisms such as attention and fairness directly in the data.
-
Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation
A large-scale standardized benchmark of GNN attacks and defenses reveals that target node selection and attacked-model training process can completely distort measured attack effectiveness.
-
Improving Graph Few-shot Learning with Hyperbolic Space and Denoising Diffusion
IMPRESS improves graph few-shot learning by learning representations in hyperbolic space and using denoising diffusion to better approximate target distributions from few support samples.
-
Toward a universal foundation model for graph-structured data
A pretrained graph model using feature-agnostic structural prompts matches or exceeds supervised baselines and shows strong zero-shot and few-shot transfer on held-out biomedical graphs, with a 21.8% ROC-AUC gain on SagePPI.
-
Analytic Drift Resister for Non-Exemplar Continual Graph Learning
ADR achieves theoretically zero-forgetting class-incremental graph learning by combining backpropagation adaptation with ridge-regression-based layer-wise merging of GNN linear transformations.
-
X-LogSMask: Expand Transformer for Graph-Structured Data
X-LogSMask injects per-head powers of the normalized adjacency matrix via a logarithmic transform into Transformer attention, achieving SOTA results on 13 of 20 graph benchmarks while remaining competitive in a one-layer setup.
-
Text-attributed Graph Condensation via Text Selection and Attribute Matching
TAGSAM is a graph condensation method for text-attributed graphs that uses subgraph text selection and attribute similarity matching, claiming 4.9% average accuracy gain over baselines at fixed size and competitive performance at 1% size.
-
A Graph Foundation Model with Spectral Parsing and Prototype-Guided Spatial Propagation
SPG is a graph foundation model using spectral decomposition via Chebyshev filters and Gromov-Wasserstein prototypes for improved cross-graph transferability.
-
Revisiting Pre-Propagation GNNs: Robust Diffusion Operators and Hidden-State Re-Propagation
Robust diffusion operators and hidden-state re-propagation improve PPGNN accuracy to match message-passing GNNs on benchmarks.
-
Graph Transductive Sharpening: Leveraging Unlabeled Predictions in Node Classification
Transductive Sharpening adds an entropy-minimization term on unlabeled-node predictions to the training objective for graph node classification.
-
Rethinking Generalization in Graph Neural Networks: A Structural Complexity Perspective
GNN generalization depends explicitly on graph structural complexity measured by effective edges, with a new regularization method shown to balance underfitting and overfitting.
-
GP2F: Cross-Domain Graph Prompting with Adaptive Fusion of Pre-trained Graph Neural Networks
GP2F is a dual-branch graph prompting framework that fuses frozen pre-trained knowledge with task-specific adaptation to reduce estimation error and outperform baselines in cross-domain few-shot node and graph classification.
-
Layer Embedding Deep Fusion Graph Neural Network
LEDF-GNN fuses multi-layer embeddings nonlinearly and runs parallel processing on original and reconstructed topologies to capture long-range dependencies and mitigate heterophily-induced misaggregation in deep GNNs.
-
Learning How Much to Think: Difficulty-Aware Dynamic MoEs for Graph Node Classification
D2MoE dynamically allocates expert resources in graph MoEs via difficulty-driven top-p routing based on predictive entropy, yielding higher accuracy and lower memory/time costs on node classification benchmarks.
-
Unified Graph Prompt Learning via Low-Rank Graph Message Prompting
LR-GMP unifies graph prompting via a low-rank Graph Message Prompt paradigm to achieve better generalization than component-specific methods.