EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
Collective classification in network data.AI Magazine, 29(3):93, Sep
9 Pith papers cite this work, alongside 3,287 external citations. Polarity classification is still indexing.
9
Pith papers citing it
3,287
external citations · OpenAlex
citation-role summary
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 9roles
dataset 1polarities
use dataset 1representative citing papers
FLAGG makes one-shot graph generators autoregressive through a learned reversal of stochastic node removal and outperforms baselines on datasets spanning different graph sizes and domains.
GNNs are shown to lack continuity under graph resolution changes due to message-passing schemes, with a derived modification enabling consistent multi-scale representations validated experimentally.
GTLM injects graph-aware attention biases into LLMs using only 0.015% extra parameters, enabling native graph processing that matches 7B models with a 1B model on text-attributed graph benchmarks.
PRAETORIAN reduces GNN backdoor attack success rate to 0.55% with 0.62% clean accuracy drop by targeting the need for many or highly influential trigger nodes.
LoGraB creates fragmented graph benchmarks with controls for radius, spectral quality, noise, and coverage, while AFR reconstructs faithful graph islands from spectral patches using fidelity scoring, RANSAC-Procrustes alignment, and adaptive stitching, supported by recovery proofs and strong results
Empirical comparison shows gradient-based explanations for GNN node similarities are actionable, consistent, and retain effects when sparsified, unlike mutual information explanations.
A literature survey that proposes a multidimensional taxonomy for community detection, introduces a general mathematical formalization accommodating disjoint/overlapping/fuzzy structures, reviews modularity functions and both algorithmic and mathematical programming methods, and discusses benchmark
Combining diverse feature and graph representations from multiple extractors with GNNs and rank aggregation improves semi-supervised image classification accuracy.
citing papers explorer
-
Evaluating LLMs on Large-Scale Graph Property Estimation via Random Walks
EstGraph benchmark evaluates LLMs on estimating properties of very large graphs from random-walk samples that fit in context limits.
-
FLAGG: Flexible Autoregressive Graph Generation
FLAGG makes one-shot graph generators autoregressive through a learned reversal of stochastic node removal and outperforms baselines on datasets spanning different graph sizes and domains.
-
Graph Neural Networks Are Not Continuous Across Graph Resolutions
GNNs are shown to lack continuity under graph resolution changes due to message-passing schemes, with a derived modification enabling consistent multi-scale representations validated experimentally.
-
Teaching LLMs to See Graphs: Unifying Text and Structural Reasoning
GTLM injects graph-aware attention biases into LLMs using only 0.015% extra parameters, enabling native graph processing that matches 7B models with a 1B model on text-attributed graph benchmarks.
-
Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors
PRAETORIAN reduces GNN backdoor attack success rate to 0.55% with 0.62% clean accuracy drop by targeting the need for many or highly influential trigger nodes.
-
Spectral Embeddings Leak Graph Topology: Theory, Benchmark, and Adaptive Reconstruction
LoGraB creates fragmented graph benchmarks with controls for radius, spectral quality, noise, and coverage, while AFR reconstructs faithful graph islands from spectral patches using fidelity scoring, RANSAC-Procrustes alignment, and adaptive stitching, supported by recovery proofs and strong results
-
Explaining Graph Neural Networks for Node Similarity on Graphs
Empirical comparison shows gradient-based explanations for GNN node similarities are actionable, consistent, and retain effects when sparsified, unlike mutual information explanations.
-
A Survey of Community Detection from an Operations Research Perspective: Taxonomy, Mathematical Formulations, Modularity Functions, and Benchmark Datasets
A literature survey that proposes a multidimensional taxonomy for community detection, introduces a general mathematical formalization accommodating disjoint/overlapping/fuzzy structures, reviews modularity functions and both algorithmic and mathematical programming methods, and discusses benchmark
-
Graph Neural Networks for Semi-Supervised Image Classification with Multi-Feature Aggregation
Combining diverse feature and graph representations from multiple extractors with GNNs and rank aggregation improves semi-supervised image classification accuracy.