I received my Bachelor’s Degree in Mathematics from Hefei University of Technology in 2020 and my Master’s degree in Computer Science and Information Engineering from Hefei University of Technology in 2023. I am currently a Ph.D. Student in the School of Computer Science and Information Engineering at Hefei University of Technology. Since the fall of 2020, I have been under the supervision of Prof. Kui Yu.

Research Interest

My research interest includes: graph out-of-distribution generalization, causal discovery, and interpretable artificial intelligence.

Academic Services

(a) IEEE Transactions on Emerging Topics in Computational Intelligence, SCI, IF:5.3, reviewer.

News

Papers are on the way

Our paper “Towards Effective Graph Rationalization via Boosting Environment Diversity” is on the way.

Our paper “Graph Generalization via Consistently-Invariant Subgraph Discovery and Selective Environment Augmentation” is on the way.

Paper accepted by Transactions on Knowledge and Data Engineering, February 2025

Our paper “Summary Graph Induced Invariant Learning for Generalizable Graph Learning” has been accepted by the Journal Transactions on Knowledge and Data Engineering (CCF A, SCI Q2)

Paper accepted by Pattern Recongnition, February 2024

Our paper “Discovering causally invariant features for out-of-distribution generalization” is accepted by the Journal Pattern Recongnition (CCF B, SCI Q1)

Paper accepted by the 31st ACM International Conference on Information & Knowledge Management, October, 2022

Our paper “Bootstrap-based causal structure learning” is accepted by the the 31st ACM International Conference on Information & Knowledge Managementn (CCF B)

Paper accepted by the Pacific-Asia Conference on Knowledge Discovery and Data Mining, May 2022

Our paper “A new skeleton-neural DAG learning approach has been accepted by the Pacific-Asia Conference on Knowledge Discovery and Data Mining (CCF C)

Paper accepted by the IEEE International Conference on Big Knowledge, December 2021

Our paper “Improving Gradient-based DAG Learning by Structural Asymmetry” is accepted by the IEEE International Conference on Big Knowledge (EI)

Publications

[1] Ning X, Wang Y, Yu K, et al. Summary Graph Induced Invariant Learning for Generalizable Graph Learning[J]. IEEE Transactions on Knowledge and Data Engineering, 37(6), 3739-3752, 2025.

[2] Wang Y, Yu K, Zhang Y, et al. Towards Effective Graph Rationalization via Boosting Environment Diversity[J]. arXiv preprint arXiv:2412.12880, 2024.

[3] Wang Y, Yu K, Xiang G, et al. Discovering causally invariant features for out-of-distribution generalization[J]. Pattern Recognition, 2024, 150: 110338.

[4] Guo X, Wang Y, Huang X, et al. Bootstrap-based causal structure learning[C]//Proceedings of the 31st ACM international conference on information & knowledge management. 2022: 656-665.

[5] Cao Y, Yu K, Huang X, et al. A new skeleton-neural DAG learning approach[C]//Pacific-Asia Conference on Knowledge Discovery and Data Mining. Cham: Springer International Publishing, 2022: 626-638.

[6] Wang Y, Yang S, Guo X, et al. Improving Gradient-based DAG Learning by Structural Asymmetry[C]//2021 IEEE International Conference on Big Knowledge (ICBK). IEEE, 2021: 1-8.