RGE: A Repulsive Graph Rectification for Node Classification via Influence

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 32
  • Download : 0
In real-world graphs, noisy connections are inevitable, which makes it difficult to obtain unbiased node representations. Among various attempts to resolve this problem, a method of estimating the counterfactual effects of these connectivities has recently attracted attention, which mainly uses influence functions for single graph elements (i.e., node and edge). However, in this paper, we argue that there is a strongly interacting group effect between the influences of graph elements due to their connectivity. In the same vein, we observe that edge groups connecting to the same train node exhibit significant differences in their influences, hence no matter how negative each is, removing them at once may have a rather negative effect as a group. Based on this motivation, we propose a new edge-removing strategy, Repulsive edge Group Elimination (RGE), that preferentially removes edges with no interference in groups. Empirically, we demonstrate that RGE consistently outperforms existing methods on the various benchmark datasets.
Publisher
ML Research Press
Issue Date
2023-07-27
Language
English
Citation

40th International Conference on Machine Learning, ICML 2023, pp.32331 - 32348

URI
http://hdl.handle.net/10203/316290
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