Introduces graph-label conditioned (GLC) and embedding-label conditioned (ELC) reconstruction attacks on GNNs that achieve high-quality graph recovery in black-box settings on NCI1, PROTEINS and AIDS datasets using four distributional metrics.
hub
TUDataset: A collection of benchmark datasets for learning with graphs
26 Pith papers cite this work. Polarity classification is still indexing.
26
Pith papers citing it
abstract
Recently, there has been an increasing interest in (supervised) learning with graph data, especially using graph neural networks. However, the development of meaningful benchmark datasets and standardized evaluation procedures is lagging, consequently hindering advancements in this area. To address this, we introduce the TUDataset for graph classification and regression. The collection consists of over 120 datasets of varying sizes from a wide range of applications. We provide Python-based data loaders, kernel and graph neural network baseline implementations, and evaluation tools. Here, we give an overview of the datasets, standardized evaluation procedures, and provide baseline experiments. All datasets are available at www.graphlearning.io. The experiments are fully reproducible from the code available at www.github.com/chrsmrrs/tudataset.
hub tools
citation-role summary
background 2
dataset 2
citation-polarity summary
representative citing papers
AbstainGNN is a framework that jointly models prediction and abstention in GNNs for graph classification, using a PAC-Bayesian-derived unified objective and two-stage training to achieve better accuracy at given rejection rates than prior abstention methods.
Quantum-inspired observables reveal poor signal routing in standard spectral GNNs and motivate Schrödinger GNNs with superior propagation capacity.
GraphIP-Bench is a new unified benchmark showing GNN model extraction succeeds at moderate query budgets while most defenses fail to prevent it or retain verification signals on surrogates.
Higher-order persistence diagrams are defined recursively via interval containments, and their aggregations can be evaluated in nearly linear time using zeta transforms instead of explicit pair enumeration.
CTQWformer fuses continuous-time quantum walks into a graph transformer and recurrent module to outperform standard GNNs and graph kernels on classification benchmarks.
Concept Graph Convolutions perform message passing on node concepts to increase interpretability of graph neural networks without losing task performance.
R2G is a multi-view circuit graph benchmark showing that representation choice affects GNN accuracy more than model architecture, with node-centric views and deeper decoders performing best.
HyperX is the first end-to-end FPGA accelerator for Nyström-based HDC graph classification, delivering 6.85× speedup and 169× energy efficiency over CPU baselines plus 3.4% average accuracy gain on TUDataset benchmarks.
Logic-based Weisfeiler-Leman variants enable graph-to-table conversion for classification that matches GNN and graph transformer accuracy while running 5-20x faster without GPUs.
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.
RelSC is a new graph regression benchmark from program graphs with execution time labels, released in homogeneous (RelSC-H) and multi-relational (RelSC-M) variants to study representation effects.
The paper demonstrates a black-box model extraction attack on graph classification models that leverages binary subgraph explanations to guide Monte Carlo edge sensitivity estimation with concentration guarantees.
A label-free Group Lasso method estimates important subgraphs in pretrained GNNs by incorporating domain structural knowledge.
Independent quantum signal injection into graph DEQs yields higher test accuracy and fewer solver iterations than state-dependent or backbone-dependent injection and classical equilibrium models on NCI1, PROTEINS, and MUTAG benchmarks.
GraphNetz supplies an automated statistical pipeline for GNN benchmarking that includes per-cell confidence intervals, paired tests with multiple-comparison correction, and critical-difference diagrams across tasks and datasets.
Subgraph Concept Network is a new GNN architecture that distills meaningful concepts at node, subgraph, and graph levels via soft clustering to improve explainability while maintaining competitive accuracy.
HISTOGRAPH applies unified layer-wise attention followed by node-wise attention over historical GNN activations to improve graph classification, especially in deep models.
Adaptive canonicalization selects input canonical forms by maximizing network predictive confidence to yield continuous symmetry-preserving models with universal approximation for equivariant geometric networks.
GLIP is a joint GNN-LLM pretraining framework that uses augmentation, multi-token selection, a diffusion projector, and combined contrastive plus semantic losses to boost graph classification and reasoning after fine-tuning on limited labels.
Quantum-oriented embeddings deliver consistent gains on structure-driven graph datasets while classical baselines perform adequately on attribute-limited social graphs, under identical training pipelines across five TU datasets and binned QM9.
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.
OpenGLT benchmark finds no single GNN architecture dominates graph-level tasks, with subgraph-based models strongest in expressiveness, graph learning and SSL models in robustness, node and pooling models in efficiency, and graph topology partially guiding architecture choice.
The paper claims current graph condensation approaches are flawed due to full-dataset training requirements, high overhead, poor generalization, and misleading evaluation metrics, calling for a reset toward lightweight and architecture-agnostic methods.
citing papers explorer
-
GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
GraphIP-Bench is a new unified benchmark showing GNN model extraction succeeds at moderate query budgets while most defenses fail to prevent it or retain verification signals on surrogates.