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.
arXiv preprint arXiv:2206.13697 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.LG 6years
2026 6roles
background 2representative citing papers
ADR achieves theoretically zero-forgetting class-incremental graph learning by combining backpropagation adaptation with ridge-regression-based layer-wise merging of GNN linear transformations.
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.
SP-ESGC decouples graph condensation into heat-kernel node condensation and pre-trained edge prediction for structure, claiming high efficiency and cross-GNN generalization on real-world datasets.
AHGCDD distills large hypergraphs into informative synthetic versions via anchor-guided joint optimization and dual-level discrimination, achieving better effectiveness and efficiency than prior decoupled HGC approaches.
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
-
TaLK: Text-attributed Graph Dataset Distillation via Coupling Language Model with Graph-Aware Kernel
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.
-
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.
-
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.
-
An Efficient and Scalable Graph Condensation with Structure-Preserving
SP-ESGC decouples graph condensation into heat-kernel node condensation and pre-trained edge prediction for structure, claiming high efficiency and cross-GNN generalization on real-world datasets.
-
Anchor-guided Hypergraph Condensation with Dual-level Discrimination
AHGCDD distills large hypergraphs into informative synthetic versions via anchor-guided joint optimization and dual-level discrimination, achieving better effectiveness and efficiency than prior decoupled HGC approaches.
-
Position: Graph Condensation Needs a Reset -- Move Beyond Full-dataset Training and Model-Dependence
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.