Structure-Preserving Graph Representation Learning
- URL: http://arxiv.org/abs/2209.00793v1
- Date: Fri, 2 Sep 2022 02:49:19 GMT
- Title: Structure-Preserving Graph Representation Learning
- Authors: Ruiyi Fang, Liangjian Wen, Zhao Kang, Jianzhuang Liu
- Abstract summary: We propose a novel Structure-Preserving Graph Representation Learning (SPGRL) method to fully capture the structure information of graphs.
Specifically, to reduce the uncertainty and misinformation of the original graph, we construct a feature graph as a complementary view via k-Nearest Neighbor method.
Our method has quite superior performance on semi-supervised node classification task and excellent robustness under noise perturbation on graph structure or node features.
- Score: 43.43429108503634
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Though graph representation learning (GRL) has made significant progress, it
is still a challenge to extract and embed the rich topological structure and
feature information in an adequate way. Most existing methods focus on local
structure and fail to fully incorporate the global topological structure. To
this end, we propose a novel Structure-Preserving Graph Representation Learning
(SPGRL) method, to fully capture the structure information of graphs.
Specifically, to reduce the uncertainty and misinformation of the original
graph, we construct a feature graph as a complementary view via k-Nearest
Neighbor method. The feature graph can be used to contrast at node-level to
capture the local relation. Besides, we retain the global topological structure
information by maximizing the mutual information (MI) of the whole graph and
feature embeddings, which is theoretically reduced to exchanging the feature
embeddings of the feature and the original graphs to reconstruct themselves.
Extensive experiments show that our method has quite superior performance on
semi-supervised node classification task and excellent robustness under noise
perturbation on graph structure or node features.
Related papers
- Node Classification via Semantic-Structural Attention-Enhanced Graph Convolutional Networks [0.9463895540925061]
We introduce the semantic-structural attention-enhanced graph convolutional network (SSA-GCN)
It not only models the graph structure but also extracts generalized unsupervised features to enhance classification performance.
Our experiments on the Cora and CiteSeer datasets demonstrate the performance improvements achieved by our proposed method.
arXiv Detail & Related papers (2024-03-24T06:28:54Z) - Graph Data Condensation via Self-expressive Graph Structure Reconstruction [7.4525875528900665]
We introduce a novel framework named textbfGraph Data textbfCondensation via textbfSelf-expressive Graph Structure textbfReconstruction.
Our method explicitly incorporates the original graph structure into the condensing process and captures the nuanced interdependencies between the condensed nodes.
arXiv Detail & Related papers (2024-03-12T03:54:25Z) - GraphEdit: Large Language Models for Graph Structure Learning [62.618818029177355]
Graph Structure Learning (GSL) focuses on capturing intrinsic dependencies and interactions among nodes in graph-structured data.
Existing GSL methods heavily depend on explicit graph structural information as supervision signals.
We propose GraphEdit, an approach that leverages large language models (LLMs) to learn complex node relationships in graph-structured data.
arXiv Detail & Related papers (2024-02-23T08:29:42Z) - Semantic Graph Neural Network with Multi-measure Learning for
Semi-supervised Classification [5.000404730573809]
Graph Neural Networks (GNNs) have attracted increasing attention in recent years.
Recent studies have shown that GNNs are vulnerable to the complex underlying structure of the graph.
We propose a novel framework for semi-supervised classification.
arXiv Detail & Related papers (2022-12-04T06:17:11Z) - Towards Unsupervised Deep Graph Structure Learning [67.58720734177325]
We propose an unsupervised graph structure learning paradigm, where the learned graph topology is optimized by data itself without any external guidance.
Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph.
arXiv Detail & Related papers (2022-01-17T11:57:29Z) - Self-supervised Consensus Representation Learning for Attributed Graph [15.729417511103602]
We introduce self-supervised learning mechanism to graph representation learning.
We propose a novel Self-supervised Consensus Representation Learning framework.
Our proposed SCRL method treats graph from two perspectives: topology graph and feature graph.
arXiv Detail & Related papers (2021-08-10T07:53:09Z) - Self-supervised Graph-level Representation Learning with Local and
Global Structure [71.45196938842608]
We propose a unified framework called Local-instance and Global-semantic Learning (GraphLoG) for self-supervised whole-graph representation learning.
Besides preserving the local similarities, GraphLoG introduces the hierarchical prototypes to capture the global semantic clusters.
An efficient online expectation-maximization (EM) algorithm is further developed for learning the model.
arXiv Detail & Related papers (2021-06-08T05:25:38Z) - Hierarchical Adaptive Pooling by Capturing High-order Dependency for
Graph Representation Learning [18.423192209359158]
Graph neural networks (GNN) have been proven to be mature enough for handling graph-structured data on node-level graph representation learning tasks.
This paper proposes a hierarchical graph-level representation learning framework, which is adaptively sensitive to graph structures.
arXiv Detail & Related papers (2021-04-13T06:22:24Z) - Graph Information Bottleneck [77.21967740646784]
Graph Neural Networks (GNNs) provide an expressive way to fuse information from network structure and node features.
Inheriting from the general Information Bottleneck (IB), GIB aims to learn the minimal sufficient representation for a given task.
We show that our proposed models are more robust than state-of-the-art graph defense models.
arXiv Detail & Related papers (2020-10-24T07:13:00Z) - GraphOpt: Learning Optimization Models of Graph Formation [72.75384705298303]
We propose an end-to-end framework that learns an implicit model of graph structure formation and discovers an underlying optimization mechanism.
The learned objective can serve as an explanation for the observed graph properties, thereby lending itself to transfer across different graphs within a domain.
GraphOpt poses link formation in graphs as a sequential decision-making process and solves it using maximum entropy inverse reinforcement learning algorithm.
arXiv Detail & Related papers (2020-07-07T16:51:39Z)
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.