Menghui Wang — accepted AI-conference papers

2026

Discriminative Mixture-of-Experts on Graphs with Reliable Expert Fusion

Haoyue Deng, Menghui Wang, Yunlong Zhou, Ziwei Zhang, Ran Zhang, Chunming Hu +1

ICML 2026poster

Graph Mixture-of-Experts (Graph-MoE) offers a way to scale GNNs via adaptive capacity allocation, with the goal of allowing different experts to capture diverse graph patterns. Its effectiveness heavily depends on the coordination between routing decisions and expert specialization. However, through…

Cited by 0 Source ↗Scholar ↗

2021

Learning Term Embeddings for Lexical Taxonomies

Jingping Liu, Menghui Wang, Chao Wang, Jiaqing Liang, Lihan Chen, Haiyun Jiang +2

AAAI 2021technical

Lexical taxonomies, a special kind of knowledge graph, are essential for natural language understanding. This paper studies the problem of lexical taxonomy embedding. Most existing graph embedding methods are difficult to apply to lexical taxonomies since 1) they ignore implicit but important inform…

Cited by 7 Source ↗PDF ↗code ↗Scholar ↗