• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
成果搜索

author:

Fu, Yang-Geng (Fu, Yang-Geng.) [1] (Scholars:傅仰耿) | Chen, Xinlong (Chen, Xinlong.) [2] | Xu, Shuling (Xu, Shuling.) [3] | Li, Jin (Li, Jin.) [4] | Yao, Xi (Yao, Xi.) [5] | Huang, Ziyang (Huang, Ziyang.) [6] | Wang, Ying-Ming (Wang, Ying-Ming.) [7] (Scholars:王应明)

Indexed by:

EI Scopus SCIE

Abstract:

Graph self-supervised learning is an effective technique for learning common knowledge from unlabeled graph data through pretext tasks. To capture the interrelationships between nodes and their essential roles globally, existing methods use clustering labels as self-supervised signals. However, in some cases, these methods may introduce noise, leading to over-fitting of the model and a reduction in performance. To address these issues, a novel framework for G raph S elf-Supervised S upervised C urriculum L earning based on clustering label smoothing called GSSCL has been proposed. GSSCL clusters knowledge in an easy-to-difficult manner, reducing the heavy dependence on the reliability of clustering and improving the generalizability of the model. Moreover, the Silhouette Coefficient is employed to evaluate the clustering confident scores for all nodes. Some nodes are selected based on high confident scores to perform self-supervised learning. To account for the possibility of complex heterophilous information in graphs (e.g., noisy links), clustering pseudo-label smoothing is performed on K-nearest neighbor graphs built upon the similarities between node features instead of the original graph structures. The obtained multi-scale knowledge is then applied to curriculum learning. Finally, comprehensive experiments conducted across diverse public graph benchmarks demonstrate the superior performance of the proposed framework. It exhibits comparable results to state-of-the-art methods across semi-supervised node classification and clustering tasks.

Keyword:

Clustering label smoothing Curriculum learning Graph neural network Graph self-supervised learning Selection enhancement

Community:

  • [ 1 ] [Fu, Yang-Geng]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Peoples R China
  • [ 2 ] [Chen, Xinlong]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Peoples R China
  • [ 3 ] [Xu, Shuling]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Peoples R China
  • [ 4 ] [Li, Jin]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Peoples R China
  • [ 5 ] [Yao, Xi]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Peoples R China
  • [ 6 ] [Huang, Ziyang]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Peoples R China
  • [ 7 ] [Li, Jin]HKUST Guangzhou, AI Thrust, Informat Hub, Guangzhou 511466, Peoples R China
  • [ 8 ] [Wang, Ying-Ming]Fuzhou Univ, Decis Sci Inst, Fuzhou 350108, Peoples R China
  • [ 9 ] [Wang, Ying-Ming]Wuchang Univ Technol, Coll Business, Wuhan 430223, Peoples R China

Reprint 's Address:

  • [Fu, Yang-Geng]Fuzhou Univ, Coll Comp & Data Sci, Fuzhou 350108, Peoples R China;;

Show more details

Related Keywords:

Related Article:

Source :

NEURAL NETWORKS

ISSN: 0893-6080

Year: 2024

Volume: 181

6 . 0 0 0

JCR@2023

Cited Count:

WoS CC Cited Count: 1

SCOPUS Cited Count: 1

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 1

Online/Total:142/10078411
Address:FZU Library(No.2 Xuyuan Road, Fuzhou, Fujian, PRC Post Code:350116) Contact Us:0591-22865326
Copyright:FZU Library Technical Support:Beijing Aegean Software Co., Ltd. 闽ICP备05005463号-1