GraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 351
  • Download : 0
DC FieldValueLanguage
dc.contributor.authorPark, JoonHyungko
dc.contributor.authorSong, Jaeyunko
dc.contributor.authorYang, Eunhoko
dc.date.accessioned2022-12-06T01:01:24Z-
dc.date.available2022-12-06T01:01:24Z-
dc.date.created2022-12-04-
dc.date.issued2022-04-26-
dc.identifier.citationThe Tenth International Conference on Learning Representations, ICLR 2022-
dc.identifier.urihttp://hdl.handle.net/10203/301727-
dc.description.abstractIn many real-world node classification scenarios, nodes are highly class-imbalanced, where graph neural networks (GNNs) can be readily biased to major class instances. Albeit existing class imbalance approaches in other domains can alleviate this issue to some extent, they do not consider the impact of message passing between nodes. In this paper, we hypothesize that overfitting to the neighbor sets of minor class due to message passing is a major challenge for class-imbalanced node classification. To tackle this issue, we propose GraphENS, a novel augmentation method that synthesizes the whole ego network for minor class (minor node and its one-hop neighbors) by combining two different ego networks based on their similarity. Additionally, we introduce a saliency-based node mixing method to exploit the abundant class-generic attributes of other nodes while blocking the injection of class-specific features. Our approach consistently outperforms the baselines over multiple node classification benchmark datasets and architectures.-
dc.languageEnglish-
dc.publisherInternational Conference on Learning Representations (ICLR)-
dc.titleGraphENS: Neighbor-Aware Ego Network Synthesis for Class-Imbalanced Node Classification-
dc.typeConference-
dc.type.rimsCONF-
dc.citation.publicationnameThe Tenth International Conference on Learning Representations, ICLR 2022-
dc.identifier.conferencecountryUS-
dc.identifier.conferencelocationVirtual-
dc.contributor.localauthorYang, Eunho-
Appears in Collection
AI-Conference Papers(학술대회논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0