Data-Centric Graph Condensation via Diffusion Trajectory Matching
Keywords: Graph Condensation, Distribution Matching
TL;DR: This paper proposes a data centric graph condensation, based on the idea of matching the distribution of the original graph and the synthetic graph.h
Abstract: This paper introduces Data Centric Graph Condensation (named DCGC), a data-centric and model-agnostic method for condensing a large graph into a smaller one by matching the distribution between two graphs. DCGC defines the distribution of a graph as the trajectories of its node signals (such as node features and node labels) induced by a diffusion process over the geometric structure, which accommodates multi-order structural information. Built upon this, DCGC compresses the topological knowledge of the original graph into the orders-of-magnitude smaller synthetic one by aligning their distributions in input space. Compared with existing methods that stick to particular GNN architectures and require solving complicated optimization, DCGC can be flexibly applied for arbitrary off-the-shelf GNNs and achieve graph condensation with a much faster speed. Apart from the cross-architecture generalization ability and training efficiency, experiments demonstrate that DCGC yields consistently superior performance than existing methods on datasets with varying scales and condensation ratios.
Primary Area: learning on graphs and other geometries & topologies
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 11948
Loading