Publications

A Differential Geometric View and Explainability of GNN on Evolving Graphs
^{Yazheng Liu, Xi Zhang, Sihong Xie
International Conference on Learning Representations (ICLR), 2023
We embed the manifold of GNN predicted distributions and devise the convex optimization to select important paths to explain the evolving graphs in the GNN.}

Trade less Accuracy for Fairness and Trade-off Explanation for GNN
^{Yazheng Liu, Xi Zhang, Sihong Xie
Second International Workshop on Data science for equality, inclusion and well-being challenges, Bigdata workshop, 2022
We define a novel upper bound of group fairness to optimize the adjacency matrix for fairness without significantly harming prediction accuracy. We further propose explanation methods to reveal the trade-offs and the space that one can exploit.}