Publications

ReLaSH: Reconstructing Joint Latent Spaces for Efficient Generation of Synthetic Hypergraphs with Hyperlink Attributes

Published in arXiv, 2025

Under review at ICLR 2026. To appear on arXiv. A general generative framework for producing realistic synthetic hypergraph data with hyperlink attributes via training a likelihood-based joint embedding model and reconstructing the joint latent space.

Low-Rank Graphon Learning for Networks

Published in NeurIPS, 2025

A new graphon modeling approach, capable of generating a low-rank connection probability matrix for network data, is proposed along with rigorous analysis.

Recommended citation: Fan, Xinyuan, Feiyan Ma, Chenlei Leng, and Weichi Wu. "Low-Rank Graphon Learning for Networks." In The Thirty-ninth Annual Conference on Neural Information Processing Systems.
Download Paper