PromptGNN-sim uses GAT-based semantically aware neighborhood selection and structure-aware LLM prompts with bi-directional contrastive alignment to outperform prior GNN, LLM, and fusion methods on text-attributed graph datasets.
hub
and Cangea, C
29 Pith papers cite this work. Polarity classification is still indexing.
29
Pith papers citing it
hub tools
citation-role summary
dataset 1
method 1
citation-polarity summary
representative citing papers
TaLK distills TAG datasets via LM coupled with graph-aware NTK, outperforming baselines and reaching up to 97% full-dataset performance with 1% synthetic data.
Presents GraphInfer-Bench to demonstrate that no evaluated LLM-based method family closes the performance gap on graph inference tasks requiring multi-node reasoning, with plain GNNs matching or exceeding them.
GFFMERGE formulates GNN force field merging as a convex embedding-alignment problem with an analytical solution, recovering near joint-training performance on MD17, MD22, LiPS20 and other benchmarks while delivering 5-27x speedups.
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.
GraphSSR introduces an adaptive SSR pipeline with SSR-SFT data synthesis and SSR-RL (Authenticity-Reinforced and Denoising-Reinforced stages) to overcome one-size-fits-all subgraph noise in zero-shot LLM graph reasoning.
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.
LAGA is a unified multi-agent LLM framework that automates comprehensive quality optimization for text-attributed graphs by running detection, planning, action, and evaluation agents in a closed loop.
DCQ-GNN uses node-adaptive convex-concave quadratic spectral filters to boost selectivity and robustness in GNNs, ranking competitively on heterophilic and homophilic graphs with less degradation under perturbations.
Introduces the SORB benchmark showing that sparsification and coarsening effects on influence maximization performance depend strongly on network type and evaluation metric.
GraspLLM extracts dataset-agnostic structural patterns via motif contrastive learning and aligns contextual subgraphs to LLM tokens, outperforming prior LLM-based methods on TAGs especially in zero-shot settings.
Bidirectional LLM-GNN co-teaching with round-based pseudo-label preference optimization outperforms golden-teacher baselines on few-shot TAG benchmarks by 3-8% absolute gains.
HyRAG improves zero-shot generalization of graph foundation models by indexing and retrieving from tree-structured knowledge in hyperbolic space via multi-granularity retrieval and dual-path fusion.
CANE estimates cluster-specific reliability of noisy LLM pseudo-labels on graphs without ground truth to improve label-free node classification.
S2Aligner decouples semantic and structural components in LLM-as-Aligner pre-training for sparse TAGs and uses structure-oriented reconstruction plus domain risk balancing to improve transferability and reduce generalization gaps.
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.
GTokenLLMs do not fully understand graph tokens, exhibiting over-sensitivity or insensitivity to instruction changes and relying heavily on text for reasoning even when graph information is preserved.
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.
DuConTE is a dual-granularity text encoder that incorporates graph topology into language model attention for improved node representations in text-attributed graphs.
SDM-SCR uses LLMs for semantic disentanglement of signal from noise in text-attributed graphs followed by spectral consistency regularization to improve contrastive learning performance.
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.
GSPELL projects GNN embeddings into LLM space and builds hybrid prompts to produce faithful natural-language explanations and sparse subgraphs for GNN predictions on text-attributed graphs.
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.
Boundary-focused contrastive "gravity" loss on selected boundary nodes improves GNN node classification by about one point over an equal-architecture baseline, but the claimed proofs do not cover the implemented loss.
citing papers explorer
-
DuConTE: Dual-Granularity Text Encoder with Topology-Constrained Attention for Text-attributed Graphs
DuConTE is a dual-granularity text encoder that incorporates graph topology into language model attention for improved node representations in text-attributed graphs.