EXGC: Bridging Efficiency and Explainability in Graph Condensation
- URL: http://arxiv.org/abs/2402.05962v1
- Date: Mon, 5 Feb 2024 06:03:38 GMT
- Title: EXGC: Bridging Efficiency and Explainability in Graph Condensation
- Authors: Junfeng Fang and Xinglin Li and Yongduo Sui and Yuan Gao and Guibin
Zhang and Kun Wang and Xiang Wang and Xiangnan He
- Abstract summary: Graph condensation (GCond) has been introduced to distill large real datasets into a more concise yet information-rich synthetic graph.
Despite acceleration efforts, existing GCond methods mainly grapple with efficiency, especially on expansive web data graphs.
We propose the Efficient and eXplainable Graph Condensation method, which can markedly boost efficiency and inject explainability.
- Score: 30.60535282372542
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Graph representation learning on vast datasets, like web data, has made
significant strides. However, the associated computational and storage
overheads raise concerns. In sight of this, Graph condensation (GCond) has been
introduced to distill these large real datasets into a more concise yet
information-rich synthetic graph. Despite acceleration efforts, existing GCond
methods mainly grapple with efficiency, especially on expansive web data
graphs. Hence, in this work, we pinpoint two major inefficiencies of current
paradigms: (1) the concurrent updating of a vast parameter set, and (2)
pronounced parameter redundancy. To counteract these two limitations
correspondingly, we first (1) employ the Mean-Field variational approximation
for convergence acceleration, and then (2) propose the objective of Gradient
Information Bottleneck (GDIB) to prune redundancy. By incorporating the leading
explanation techniques (e.g., GNNExplainer and GSAT) to instantiate the GDIB,
our EXGC, the Efficient and eXplainable Graph Condensation method is proposed,
which can markedly boost efficiency and inject explainability. Our extensive
evaluations across eight datasets underscore EXGC's superiority and relevance.
Code is available at https://github.com/MangoKiller/EXGC.
Related papers
- GC-Bench: An Open and Unified Benchmark for Graph Condensation [54.70801435138878]
We develop a comprehensive Graph Condensation Benchmark (GC-Bench) to analyze the performance of graph condensation.
GC-Bench systematically investigates the characteristics of graph condensation in terms of the following dimensions: effectiveness, transferability, and complexity.
We have developed an easy-to-use library for training and evaluating different GC methods to facilitate reproducible research.
arXiv Detail & Related papers (2024-06-30T07:47:34Z) - A Scalable and Effective Alternative to Graph Transformers [19.018320937729264]
Graph Transformers (GTs) were introduced, utilizing self-attention mechanism to model pairwise node relationships.
GTs suffer from complexity w.r.t. the number of nodes in the graph, hindering their applicability to large graphs.
We present Graph-Enhanced Contextual Operator (GECO), a scalable and effective alternative to GTs.
arXiv Detail & Related papers (2024-06-17T19:57:34Z) - GCondenser: Benchmarking Graph Condensation [26.458605619132385]
This paper proposes the first large-scale graph condensation benchmark, GCondenser, to holistically evaluate and compare mainstream GC methods.
GCondenser includes a standardised GC paradigm, consisting of condensation, validation, and evaluation procedures, as well as enabling extensions to new GC methods and datasets.
arXiv Detail & Related papers (2024-05-23T07:25:31Z) - Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition [56.26113670151363]
Graph condensation is a data-centric solution to replace the large graph with a small yet informative condensed graph.
Existing GC methods suffer from intricate optimization processes, necessitating excessive computing resources.
We propose a training-free GC framework termed Class-partitioned Graph Condensation (CGC)
CGC achieves state-of-the-art performance with a more efficient condensation process.
arXiv Detail & Related papers (2024-05-22T14:57:09Z) - Enhancing Real-World Complex Network Representations with Hyperedge
Augmentation [27.24150788635981]
We present a novel graph augmentation method that constructs virtual hyperedges directly form the raw data, and produces auxiliary node features by extracting from the virtual hyperedge information.
Our empirical study shows that HyperAug consistently and significantly outperforms GNN baselines and other graph augmentation methods.
We provide 23 novel real-world graph datasets across various domains including social media, biology, and e-commerce.
arXiv Detail & Related papers (2024-02-20T14:18:43Z) - 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) - Explainable Sparse Knowledge Graph Completion via High-order Graph
Reasoning Network [111.67744771462873]
This paper proposes a novel explainable model for sparse Knowledge Graphs (KGs)
It combines high-order reasoning into a graph convolutional network, namely HoGRN.
It can not only improve the generalization ability to mitigate the information insufficiency issue but also provide interpretability.
arXiv Detail & Related papers (2022-07-14T10:16:56Z) - 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) - Graph Highway Networks [77.38665506495553]
Graph Convolution Networks (GCN) are widely used in learning graph representations due to their effectiveness and efficiency.
They suffer from the notorious over-smoothing problem, in which the learned representations converge to alike vectors when many layers are stacked.
We propose Graph Highway Networks (GHNet) which utilize gating units to balance the trade-off between homogeneity and heterogeneity in the GCN learning process.
arXiv Detail & Related papers (2020-04-09T16:26:43Z)
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.