Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching

• URL: http://arxiv.org/abs/2402.04924v5
• Date: Fri, 27 Sep 2024 09:57:42 GMT
• Title: Two Trades is not Baffled: Condensing Graph via Crafting Rational Gradient Matching
• Authors: Tianle Zhang, Yuchen Zhang, Kun Wang, Kai Wang, Beining Yang, Kaipeng Zhang, Wenqi Shao, Ping Liu, Joey Tianyi Zhou, Yang You,
• Abstract summary: Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have raised growing concerns. We propose a novel graph method named textbfCraftextbfTing textbfRationatextbf (textbfCTRL) which offers an optimized starting point closer to the original dataset's feature distribution.
• Score: 50.30124426442228
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Training on large-scale graphs has achieved remarkable results in graph representation learning, but its cost and storage have raised growing concerns. As one of the most promising directions, graph condensation methods address these issues by employing gradient matching, aiming to condense the full graph into a more concise yet information-rich synthetic set. Though encouraging, these strategies primarily emphasize matching directions of the gradients, which leads to deviations in the training trajectories. Such deviations are further magnified by the differences between the condensation and evaluation phases, culminating in accumulated errors, which detrimentally affect the performance of the condensed graphs. In light of this, we propose a novel graph condensation method named \textbf{C}raf\textbf{T}ing \textbf{R}ationa\textbf{L} trajectory (\textbf{CTRL}), which offers an optimized starting point closer to the original dataset's feature distribution and a more refined strategy for gradient matching. Theoretically, CTRL can effectively neutralize the impact of accumulated errors on the performance of condensed graphs. We provide extensive experiments on various graph datasets and downstream tasks to support the effectiveness of CTRL. Code is released at https://github.com/NUS-HPC-AI-Lab/CTRL.

Related papers

• Simple Graph Condensation [30.85754566420301]
  Graph condensation involves tuning Graph Neural Networks (GNNs) on a small condensed graph for use on a large-scale original graph. We introduce the Simple Graph Condensation (SimGC) framework, which aligns the condensed graph with the original graph from the input layer to the prediction layer. SimGC achieves a significant speedup of up to 10 times compared to existing graph condensation methods.
  arXiv  Detail & Related papers  (2024-03-22T05:04:48Z)
• Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching [26.303436980548174]
  Graph condensation aims to reduce the size of a large-scale graph dataset by synthesizing a compact counterpart. Existing methods often fall short of accurately replicating the original graph for certain datasets. In this paper, we make the first attempt toward textitlossless graph condensation by bridging the previously neglected supervision signals.
  arXiv  Detail & Related papers  (2024-02-07T16:32:02Z)
• PUMA: Efficient Continual Graph Learning for Node Classification with Graph Condensation [49.00940417190911]
  Existing graph representation learning models encounter a catastrophic problem when learning with newly incoming graphs. In this paper, we propose a PUdo-label guided Memory bAnkrogation (PUMA) framework to enhance its efficiency and effectiveness.
  arXiv  Detail & Related papers  (2023-12-22T05:09:58Z)
• Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data [91.27527985415007]
  Existing graph condensation methods rely on the joint optimization of nodes and structures in the condensed graph. We advocate a new Structure-Free Graph Condensation paradigm, named SFGC, to distill a large-scale graph into a small-scale graph node set.
  arXiv  Detail & Related papers  (2023-06-05T07:53:52Z)
• Localized Contrastive Learning on Graphs [110.54606263711385]
  We introduce a simple yet effective contrastive model named Localized Graph Contrastive Learning (Local-GCL) In spite of its simplicity, Local-GCL achieves quite competitive performance in self-supervised node representation learning tasks on graphs with various scales and properties.
  arXiv  Detail & Related papers  (2022-12-08T23:36:00Z)
• GraphCoCo: Graph Complementary Contrastive Learning [65.89743197355722]
  Graph Contrastive Learning (GCL) has shown promising performance in graph representation learning (GRL) without the supervision of manual annotations. This paper proposes an effective graph complementary contrastive learning approach named GraphCoCo to tackle the above issue.
  arXiv  Detail & Related papers  (2022-03-24T02:58:36Z)
• Dual Space Graph Contrastive Learning [82.81372024482202]
  We propose a novel graph contrastive learning method, namely textbfDual textbfSpace textbfGraph textbfContrastive (DSGC) Learning. Since both spaces have their own advantages to represent graph data in the embedding spaces, we hope to utilize graph contrastive learning to bridge the spaces and leverage advantages from both sides.
  arXiv  Detail & Related papers  (2022-01-19T04:10:29Z)
• Graph Ordering: Towards the Optimal by Learning [69.72656588714155]
  Graph representation learning has achieved a remarkable success in many graph-based applications, such as node classification, prediction, and community detection. However, for some kind of graph applications, such as graph compression and edge partition, it is very hard to reduce them to some graph representation learning tasks. In this paper, we propose to attack the graph ordering problem behind such applications by a novel learning approach.
  arXiv  Detail & Related papers  (2020-01-18T09:14:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.