Addressing Structural Distribution Shift in Explanations for Graph Neural Networks
Published in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2026
This work formalizes structural distribution shift between original graphs and explanation subgraphs. It introduces proxy graphs that retain essential explanatory information while better matching the training distribution, improving the quality and reliability of GNN explanations.
Recommended citation: Zhuomin Chen, Hojat Allah Salehi, Esteban Schafir, Xu Zheng, Jiaxing Zhang, Hua Wei, Jingchao Ni, Farhad Shirani, Dongsheng Luo. 2026. Addressing Structural Distribution Shift in Explanations for Graph Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence.
Recommended citation: Zhuomin Chen, Hojat Allah Salehi, Esteban Schafir, Xu Zheng, Jiaxing Zhang, Hua Wei, Jingchao Ni, Farhad Shirani, Dongsheng Luo. 2026. Addressing Structural Distribution Shift in Explanations for Graph Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. doi:10.1109/TPAMI.2026.3690304. https://doi.org/10.1109/TPAMI.2026.3690304