5 papers
Adversarial Label Invariant Graph Data Augmentations for Out-of-Distribution Generalization
Simon Zhang, Ryan P. DeMilt, Kun Jin +1
Out-of-distribution (OoD) generalization occurs when representation learning encounters a distribution shift. This occurs frequently in practice when training and testing data come…
Compression of Voxelized Vector Field Data by Boxes is Hard
Simon Zhang
Voxelized vector field data consists of a vector field over a high dimensional lattice. The lattice consists of integer coordinates called voxels. The voxelized vector field assign…
Approximating 1-Wasserstein Distance between Persistence Diagrams by Graph Sparsification
Tamal K. Dey, Simon Zhang
Persistence diagrams (PD)s play a central role in topological data analysis. This analysis requires computing distances among such diagrams such as the -Wasserstein distance. Ac…
Computing and Learning on Combinatorial Data
Simon Zhang
The twenty-first century is a data-driven era where human activities and behavior, physical phenomena, scientific discoveries, technology advancements, and almost everything that h…
Expressive Higher-Order Link Prediction through Hypergraph Symmetry Breaking
Simon Zhang, Cheng Xin, Tamal K. Dey
A hypergraph consists of a set of nodes along with a collection of subsets of the nodes called hyperedges. Higher-order link prediction is the task of predicting the existence of a…