Graph condensation: A survey

X Gao, J Yu, T Chen, G Ye, W Zhang… - IEEE Transactions on …, 2025‏ - ieeexplore.ieee.org
The rapid growth of graph data poses significant challenges in storage, transmission, and
particularly the training of graph neural networks (GNNs). To address these challenges …

Towards lossless dataset distillation via difficulty-aligned trajectory matching

Z Guo, K Wang, G Cazenavette, H Li, K Zhang… - arxiv preprint arxiv …, 2023‏ - arxiv.org
The ultimate goal of Dataset Distillation is to synthesize a small synthetic dataset such that a
model trained on this synthetic set will perform equally well as a model trained on the full …

Gc-bench: An open and unified benchmark for graph condensation

Q Sun, Z Chen, B Yang, C Ji, X Fu… - Advances in …, 2025‏ - proceedings.neurips.cc
Graph condensation (GC) has recently garnered considerable attention due to its ability to
reduce large-scale graph datasets while preserving their essential properties. The core …

Acceleration algorithms in gnns: A survey

L Ma, Z Sheng, X Li, X Gao, Z Hao… - … on Knowledge and …, 2025‏ - ieeexplore.ieee.org
Graph Neural Networks have demonstrated remarkable effectiveness in various graph-
based tasks, but their inefficiency in training and inference poses significant challenges for …

Rethinking and accelerating graph condensation: A training-free approach with class partition

X Gao, G Ye, T Chen, W Zhang, J Yu, H Yin - arxiv preprint arxiv …, 2024‏ - arxiv.org
The increasing prevalence of large-scale graphs poses a significant challenge for graph
neural network training, attributed to their substantial computational requirements. In …

Epidemiology-aware neural ode with continuous disease transmission graph

G Wan, Z Liu, MSY Lau, BA Prakash, W ** - arxiv preprint arxiv …, 2024‏ - arxiv.org
Effective epidemic forecasting is critical for public health strategies and efficient medical
resource allocation, especially in the face of rapidly spreading infectious diseases. However …

Gcondenser: Benchmarking graph condensation

Y Liu, R Qiu, Z Huang - arxiv preprint arxiv:2405.14246, 2024‏ - arxiv.org
Large-scale graphs are valuable for graph representation learning, yet the abundant data in
these graphs hinders the efficiency of the training process. Graph condensation (GC) …

Ameliorate spurious correlations in dataset condensation

J Cui, R Wang, Y **ong, CJ Hsieh - Forty-first International …, 2024‏ - openreview.net
Dataset Condensation has emerged as a technique for compressing large datasets into
smaller synthetic counterparts, facilitating downstream training tasks. In this paper, we study …

Disentangled condensation for large-scale graphs

Z **ao, S Liu, Y Wang, T Zheng, M Song - arxiv preprint arxiv:2401.12231, 2024‏ - arxiv.org
Graph condensation has emerged as an intriguing technique to save the expensive training
costs of Graph Neural Networks (GNNs) by substituting a condensed small graph with the …

GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning

G Zhang, H Dong, Y Zhang, Z Li, D Chen… - arxiv preprint arxiv …, 2024‏ - arxiv.org
Training high-quality deep models necessitates vast amounts of data, resulting in
overwhelming computational and memory demands. Recently, data pruning, distillation, and …